core: release 0.3.60 (#31249)

"Alanis Morissette" spelling error

Thank you for contributing to LangChain!

- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, core, etc. is being
modified. Use "docs: ..." for purely docs changes, "infra: ..." for CI
changes.
  - Example: "core: add foobar LLM"


- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!


- [ ] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.


- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.

.github/dependabot.yml

@@ -0,0 +1,11 @@
+# Please see the documentation for all configuration options:
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+# and
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"

.github/workflows/check-broken-links.yml

@@ -12,7 +12,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - name: Use Node.js 18.x
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: 18.x
           cache: "yarn"

.github/workflows/codspeed.yml

@@ -21,12 +21,12 @@ jobs:
 
       # We have to use 3.12, 3.13 is not yet supported
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@v6
         with:
           python-version: "3.12"
 
       # Using this action is still necessary for CodSpeed to work
-      - uses: actions/setup-python@v3
+      - uses: actions/setup-python@v5
         with:
           python-version: "3.12"
 

Makefile

@@ -48,7 +48,7 @@ api_docs_quick_preview:
 api_docs_clean:
 	find ./docs/api_reference -name '*_api_reference.rst' -delete
 	git clean -fdX ./docs/api_reference
-	rm docs/api_reference/index.md
+	rm -f docs/api_reference/index.md
 	
 
 ## api_docs_linkcheck: Run linkchecker on the API Reference documentation.

cookbook/agent_vectorstore.ipynb

@@ -22,7 +22,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 1,
+   "id": "e8d63d14-138d-4aa5-a741-7fd3537d00aa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
    "id": "2e87c10a",
    "metadata": {},
    "outputs": [],
@@ -37,7 +49,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 3,
    "id": "0b7b772b",
    "metadata": {},
    "outputs": [],
@@ -54,19 +66,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 4,
    "id": "f2675861",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Running Chroma using direct local API.\n",
-      "Using DuckDB in-memory for database. Data will be transient.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain_community.document_loaders import TextLoader\n",
     "\n",
@@ -81,7 +84,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "bc5403d4",
    "metadata": {},
    "outputs": [],
@@ -93,17 +96,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "1431cded",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "USER_AGENT environment variable not set, consider setting it to identify your requests.\n"
+     ]
+    }
+   ],
    "source": [
     "from langchain_community.document_loaders import WebBaseLoader"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "915d3ff3",
    "metadata": {},
    "outputs": [],
@@ -113,16 +124,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "96a2edf8",
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
+     "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Running Chroma using direct local API.\n",
-      "Using DuckDB in-memory for database. Data will be transient.\n"
+      "Created a chunk of size 2122, which is longer than the specified 1000\n",
+      "Created a chunk of size 3187, which is longer than the specified 1000\n",
+      "Created a chunk of size 1017, which is longer than the specified 1000\n",
+      "Created a chunk of size 1049, which is longer than the specified 1000\n",
+      "Created a chunk of size 1256, which is longer than the specified 1000\n",
+      "Created a chunk of size 2321, which is longer than the specified 1000\n"
      ]
     }
    ],
@@ -135,14 +150,6 @@
     ")"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "71ecef90",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "markdown",
    "id": "c0a6c031",
@@ -153,31 +160,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 9,
    "id": "eb142786",
    "metadata": {},
    "outputs": [],
    "source": [
     "# Import things that are needed generically\n",
-    "from langchain.agents import AgentType, Tool, initialize_agent\n",
-    "from langchain_openai import OpenAI"
+    "from langchain.agents import Tool"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 10,
    "id": "850bc4e9",
    "metadata": {},
    "outputs": [],
    "source": [
     "tools = [\n",
     "    Tool(\n",
-    "        name=\"State of Union QA System\",\n",
+    "        name=\"state_of_union_qa_system\",\n",
     "        func=state_of_union.run,\n",
     "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\",\n",
     "    ),\n",
     "    Tool(\n",
-    "        name=\"Ruff QA System\",\n",
+    "        name=\"ruff_qa_system\",\n",
     "        func=ruff.run,\n",
     "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.\",\n",
     "    ),\n",
@@ -186,94 +192,116 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
-   "id": "fc47f230",
+   "execution_count": 11,
+   "id": "70c461d8-aaca-4f2a-9a93-bf35841cc615",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Construct the agent. We will use the default agent type here.\n",
-    "# See documentation for a full list of options.\n",
-    "agent = initialize_agent(\n",
-    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
-    ")"
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
-   "id": "10ca2db8",
+   "execution_count": 12,
+   "id": "a6d2b911-3044-4430-a35b-75832bb45334",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
       "\n",
+      "What did biden say about ketanji brown jackson in the state of the union address?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "Tool Calls:\n",
+      "  state_of_union_qa_system (call_26QlRdsptjEJJZjFsAUjEbaH)\n",
+      " Call ID: call_26QlRdsptjEJJZjFsAUjEbaH\n",
+      "  Args:\n",
+      "    __arg1: What did Biden say about Ketanji Brown Jackson in the state of the union address?\n",
+      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
+      "Name: state_of_union_qa_system\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m I need to find out what Biden said about Ketanji Brown Jackson in the State of the Union address.\n",
-      "Action: State of Union QA System\n",
-      "Action Input: What did Biden say about Ketanji Brown Jackson in the State of the Union address?\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
+      " Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "In the State of the Union address, Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n"
      ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "\"Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
-      ]
-     },
-     "execution_count": 46,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [
-    "agent.run(\n",
-    "    \"What did biden say about ketanji brown jackson in the state of the union address?\"\n",
-    ")"
+    "input_message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": \"What did biden say about ketanji brown jackson in the state of the union address?\",\n",
+    "}\n",
+    "\n",
+    "for step in agent.stream(\n",
+    "    {\"messages\": [input_message]},\n",
+    "    stream_mode=\"values\",\n",
+    "):\n",
+    "    step[\"messages\"][-1].pretty_print()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
-   "id": "4e91b811",
+   "execution_count": 13,
+   "id": "e836b4cd-abf7-49eb-be0e-b9ad501213f3",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
+      "\n",
+      "Why use ruff over flake8?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "Tool Calls:\n",
+      "  ruff_qa_system (call_KqDoWeO9bo9OAXdxOsCb6msC)\n",
+      " Call ID: call_KqDoWeO9bo9OAXdxOsCb6msC\n",
+      "  Args:\n",
+      "    __arg1: Why use ruff over flake8?\n",
+      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
+      "Name: ruff_qa_system\n",
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m I need to find out the advantages of using ruff over flake8\n",
-      "Action: Ruff QA System\n",
-      "Action Input: What are the advantages of using ruff over flake8?\u001b[0m\n",
-      "Observation: \u001b[33;1m\u001b[1;3m Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.\u001b[0m\n",
+      "There are a few reasons why someone might choose to use Ruff over Flake8:\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "1. Larger rule set: Ruff implements over 800 rules, while Flake8 only implements around 200. This means that Ruff can catch more potential issues in your code.\n",
+      "\n",
+      "2. Better compatibility with other tools: Ruff is designed to work well with other tools like Black, isort, and type checkers like Mypy. This means that you can use Ruff alongside these tools to get more comprehensive feedback on your code.\n",
+      "\n",
+      "3. Automatic fixing of lint violations: Unlike Flake8, Ruff is capable of automatically fixing its own lint violations. This can save you time and effort when fixing issues in your code.\n",
+      "\n",
+      "4. Native implementation of popular Flake8 plugins: Ruff re-implements some of the most popular Flake8 plugins natively, which means you don't have to install and configure multiple plugins to get the same functionality.\n",
+      "\n",
+      "Overall, Ruff offers a more comprehensive and user-friendly experience compared to Flake8, making it a popular choice for many developers.\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "\n",
+      "You might choose to use Ruff over Flake8 for several reasons:\n",
+      "\n",
+      "1. Ruff has a much larger rule set, implementing over 800 rules compared to Flake8's roughly 200, so it can catch more potential issues.\n",
+      "2. Ruff is designed to work better with other tools like Black, isort, and type checkers like Mypy, providing more comprehensive code feedback.\n",
+      "3. Ruff can automatically fix its own lint violations, which Flake8 cannot, saving time and effort.\n",
+      "4. Ruff natively implements some popular Flake8 plugins, so you don't need to install and configure multiple plugins separately.\n",
+      "\n",
+      "Overall, Ruff offers a more comprehensive and user-friendly experience compared to Flake8.\n"
      ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.'"
-      ]
-     },
-     "execution_count": 47,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [
-    "agent.run(\"Why use ruff over flake8?\")"
+    "input_message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": \"Why use ruff over flake8?\",\n",
+    "}\n",
+    "\n",
+    "for step in agent.stream(\n",
+    "    {\"messages\": [input_message]},\n",
+    "    stream_mode=\"values\",\n",
+    "):\n",
+    "    step[\"messages\"][-1].pretty_print()"
    ]
   },
   {
@@ -296,20 +324,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 14,
    "id": "f59b377e",
    "metadata": {},
    "outputs": [],
    "source": [
     "tools = [\n",
     "    Tool(\n",
-    "        name=\"State of Union QA System\",\n",
+    "        name=\"state_of_union_qa_system\",\n",
     "        func=state_of_union.run,\n",
     "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\",\n",
     "        return_direct=True,\n",
     "    ),\n",
     "    Tool(\n",
-    "        name=\"Ruff QA System\",\n",
+    "        name=\"ruff_qa_system\",\n",
     "        func=ruff.run,\n",
     "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.\",\n",
     "        return_direct=True,\n",
@@ -319,90 +347,92 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
-   "id": "8615707a",
+   "execution_count": 15,
+   "id": "06f69c0f-c83d-4b7f-a1c8-7614aced3bae",
    "metadata": {},
    "outputs": [],
    "source": [
-    "agent = initialize_agent(\n",
-    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
-    ")"
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
-   "id": "36e718a9",
+   "execution_count": 16,
+   "id": "a6b38c12-ac25-43c0-b9c2-2b1985ab4825",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
       "\n",
+      "What did biden say about ketanji brown jackson in the state of the union address?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "Tool Calls:\n",
+      "  state_of_union_qa_system (call_yjxh11OnZiauoyTAn9npWdxj)\n",
+      " Call ID: call_yjxh11OnZiauoyTAn9npWdxj\n",
+      "  Args:\n",
+      "    __arg1: What did Biden say about Ketanji Brown Jackson in the state of the union address?\n",
+      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
+      "Name: state_of_union_qa_system\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m I need to find out what Biden said about Ketanji Brown Jackson in the State of the Union address.\n",
-      "Action: State of Union QA System\n",
-      "Action Input: What did Biden say about Ketanji Brown Jackson in the State of the Union address?\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      " Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n"
      ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "\" Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
-      ]
-     },
-     "execution_count": 50,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [
-    "agent.run(\n",
-    "    \"What did biden say about ketanji brown jackson in the state of the union address?\"\n",
-    ")"
+    "input_message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": \"What did biden say about ketanji brown jackson in the state of the union address?\",\n",
+    "}\n",
+    "\n",
+    "for step in agent.stream(\n",
+    "    {\"messages\": [input_message]},\n",
+    "    stream_mode=\"values\",\n",
+    "):\n",
+    "    step[\"messages\"][-1].pretty_print()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
-   "id": "edfd0a1a",
+   "execution_count": 17,
+   "id": "88f08d86-7972-4148-8128-3ac8898ad68a",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
       "\n",
+      "Why use ruff over flake8?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "Tool Calls:\n",
+      "  ruff_qa_system (call_GiWWfwF6wbbRFQrHlHbhRtGW)\n",
+      " Call ID: call_GiWWfwF6wbbRFQrHlHbhRtGW\n",
+      "  Args:\n",
+      "    __arg1: What are the advantages of using ruff over flake8 for Python linting?\n",
+      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
+      "Name: ruff_qa_system\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m I need to find out the advantages of using ruff over flake8\n",
-      "Action: Ruff QA System\n",
-      "Action Input: What are the advantages of using ruff over flake8?\u001b[0m\n",
-      "Observation: \u001b[33;1m\u001b[1;3m Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      " Ruff has a larger rule set, supports automatic fixing of lint violations, and does not require the installation of additional plugins. It also has better compatibility with Black and can be used alongside a type checker for more comprehensive code analysis.\n"
      ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "' Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.'"
-      ]
-     },
-     "execution_count": 51,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [
-    "agent.run(\"Why use ruff over flake8?\")"
+    "input_message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": \"Why use ruff over flake8?\",\n",
+    "}\n",
+    "\n",
+    "for step in agent.stream(\n",
+    "    {\"messages\": [input_message]},\n",
+    "    stream_mode=\"values\",\n",
+    "):\n",
+    "    step[\"messages\"][-1].pretty_print()"
    ]
   },
   {
@@ -417,19 +447,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 57,
+   "execution_count": 18,
    "id": "d397a233",
    "metadata": {},
    "outputs": [],
    "source": [
     "tools = [\n",
     "    Tool(\n",
-    "        name=\"State of Union QA System\",\n",
+    "        name=\"state_of_union_qa_system\",\n",
     "        func=state_of_union.run,\n",
     "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question, not referencing any obscure pronouns from the conversation before.\",\n",
     "    ),\n",
     "    Tool(\n",
-    "        name=\"Ruff QA System\",\n",
+    "        name=\"ruff_qa_system\",\n",
     "        func=ruff.run,\n",
     "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question, not referencing any obscure pronouns from the conversation before.\",\n",
     "    ),\n",
@@ -438,60 +468,60 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 58,
-   "id": "06157240",
+   "execution_count": 19,
+   "id": "41743f29-150d-40ba-aa8e-3a63c32216aa",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Construct the agent. We will use the default agent type here.\n",
-    "# See documentation for a full list of options.\n",
-    "agent = initialize_agent(\n",
-    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
-    ")"
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
-   "id": "b492b520",
+   "execution_count": 20,
+   "id": "e20e81dd-284a-4d07-9160-63a84b65cba8",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
       "\n",
+      "What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "Tool Calls:\n",
+      "  ruff_qa_system (call_VOnxiOEehauQyVOTjDJkR5L2)\n",
+      " Call ID: call_VOnxiOEehauQyVOTjDJkR5L2\n",
+      "  Args:\n",
+      "    __arg1: What tool does ruff use to run over Jupyter Notebooks?\n",
+      "  state_of_union_qa_system (call_AbSsXAxwe4JtCRhga926SxOZ)\n",
+      " Call ID: call_AbSsXAxwe4JtCRhga926SxOZ\n",
+      "  Args:\n",
+      "    __arg1: Did the president mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union?\n",
+      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
+      "Name: state_of_union_qa_system\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m I need to find out what tool ruff uses to run over Jupyter Notebooks, and if the president mentioned it in the state of the union.\n",
-      "Action: Ruff QA System\n",
-      "Action Input: What tool does ruff use to run over Jupyter Notebooks?\u001b[0m\n",
-      "Observation: \u001b[33;1m\u001b[1;3m Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.html\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now need to find out if the president mentioned this tool in the state of the union.\n",
-      "Action: State of Union QA System\n",
-      "Action Input: Did the president mention nbQA in the state of the union?\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
-      "Final Answer: No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
+      " No, the president did not mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union.\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "Ruff does not support source.organizeImports and source.fixAll code actions in Jupyter Notebooks. Additionally, the president did not mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union.\n"
      ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'No, the president did not mention nbQA in the state of the union.'"
-      ]
-     },
-     "execution_count": 59,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [
-    "agent.run(\n",
-    "    \"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\"\n",
-    ")"
+    "input_message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": \"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\",\n",
+    "}\n",
+    "\n",
+    "for step in agent.stream(\n",
+    "    {\"messages\": [input_message]},\n",
+    "    stream_mode=\"values\",\n",
+    "):\n",
+    "    step[\"messages\"][-1].pretty_print()"
    ]
   },
   {
@@ -519,7 +549,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.12.4"
   }
  },
  "nbformat": 4,

docs/docs/concepts/tools.mdx

@@ -192,7 +192,7 @@ All Toolkits expose a `get_tools` method which returns a list of tools. You can
 
 ```python
 # Initialize a toolkit
-toolkit = ExampleTookit(...)
+toolkit = ExampleToolkit(...)
 
 # Get list of tools
 tools = toolkit.get_tools()

docs/docs/how_to/custom_tools.ipynb

@@ -530,7 +530,7 @@
     "\n",
     "    def _run(\n",
     "        self, a: int, b: int, run_manager: Optional[CallbackManagerForToolRun] = None\n",
-    "    ) -> str:\n",
+    "    ) -> int:\n",
     "        \"\"\"Use the tool.\"\"\"\n",
     "        return a * b\n",
     "\n",
@@ -539,7 +539,7 @@
     "        a: int,\n",
     "        b: int,\n",
     "        run_manager: Optional[AsyncCallbackManagerForToolRun] = None,\n",
-    "    ) -> str:\n",
+    "    ) -> int:\n",
     "        \"\"\"Use the tool asynchronously.\"\"\"\n",
     "        # If the calculation is cheap, you can just delegate to the sync implementation\n",
     "        # as shown below.\n",

docs/docs/how_to/document_loader_custom.ipynb

@@ -67,9 +67,34 @@
     "When implementing a document loader do **NOT** provide parameters via the `lazy_load` or `alazy_load` methods.\n",
     "\n",
     "All configuration is expected to be passed through the initializer (__init__). This was a design choice made by LangChain to make sure that once a document loader has been instantiated it has all the information needed to load documents.\n",
-    ":::\n",
-    "\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "520edbbabde7df6e",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
     "\n",
+    "Install **langchain-core** and **langchain_community**."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "936bd5fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain_core langchain_community"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a93f17a87d323bdd",
+   "metadata": {},
+   "source": [
     "### Implementation\n",
     "\n",
     "Let's create an example of a standard document loader that loads a file and creates a document from each line in the file."
@@ -77,9 +102,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "20f128c1-1a2c-43b9-9e7b-cf9b3a86d1db",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:56.764714Z",
+     "start_time": "2025-04-21T08:49:56.623508Z"
+    },
     "tags": []
    },
    "outputs": [],
@@ -122,7 +151,7 @@
     "        self,\n",
     "    ) -> AsyncIterator[Document]:  # <-- Does not take any arguments\n",
     "        \"\"\"An async lazy loader that reads a file line by line.\"\"\"\n",
-    "        # Requires aiofiles (install with pip)\n",
+    "        # Requires aiofiles\n",
     "        # https://github.com/Tinche/aiofiles\n",
     "        import aiofiles\n",
     "\n",
@@ -151,9 +180,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "b1751198-c6dd-4149-95bd-6370ce8fa06f",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:56.776521Z",
+     "start_time": "2025-04-21T08:49:56.773511Z"
+    },
     "tags": []
    },
    "outputs": [],
@@ -167,9 +200,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
+   "id": "c5210428",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -q aiofiles"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
    "id": "71ef1482-f9de-4852-b5a4-0938f350612e",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:57.972675Z",
+     "start_time": "2025-04-21T08:49:57.969411Z"
+    },
     "tags": []
    },
    "outputs": [
@@ -179,10 +226,12 @@
      "text": [
       "\n",
       "<class 'langchain_core.documents.base.Document'>\n",
-      "page_content='meow meow🐱 \\n' metadata={'line_number': 0, 'source': './meow.txt'}\n",
+      "page_content='meow meow🐱 \n",
+      "' metadata={'line_number': 0, 'source': './meow.txt'}\n",
       "\n",
       "<class 'langchain_core.documents.base.Document'>\n",
-      "page_content=' meow meow🐱 \\n' metadata={'line_number': 1, 'source': './meow.txt'}\n",
+      "page_content=' meow meow🐱 \n",
+      "' metadata={'line_number': 1, 'source': './meow.txt'}\n",
       "\n",
       "<class 'langchain_core.documents.base.Document'>\n",
       "page_content=' meow😻😻' metadata={'line_number': 2, 'source': './meow.txt'}\n"
@@ -199,9 +248,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "id": "1588e78c-e81a-4d40-b36c-634242c84a6a",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:58.028989Z",
+     "start_time": "2025-04-21T08:49:58.021972Z"
+    },
     "tags": []
    },
    "outputs": [
@@ -211,10 +264,12 @@
      "text": [
       "\n",
       "<class 'langchain_core.documents.base.Document'>\n",
-      "page_content='meow meow🐱 \\n' metadata={'line_number': 0, 'source': './meow.txt'}\n",
+      "page_content='meow meow🐱 \n",
+      "' metadata={'line_number': 0, 'source': './meow.txt'}\n",
       "\n",
       "<class 'langchain_core.documents.base.Document'>\n",
-      "page_content=' meow meow🐱 \\n' metadata={'line_number': 1, 'source': './meow.txt'}\n",
+      "page_content=' meow meow🐱 \n",
+      "' metadata={'line_number': 1, 'source': './meow.txt'}\n",
       "\n",
       "<class 'langchain_core.documents.base.Document'>\n",
       "page_content=' meow😻😻' metadata={'line_number': 2, 'source': './meow.txt'}\n"
@@ -245,21 +300,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "df5ad46a-9e00-4073-8505-489fc4f3799e",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:58.078111Z",
+     "start_time": "2025-04-21T08:49:58.071421Z"
+    },
     "tags": []
    },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='meow meow🐱 \\n', metadata={'line_number': 0, 'source': './meow.txt'}),\n",
-       " Document(page_content=' meow meow🐱 \\n', metadata={'line_number': 1, 'source': './meow.txt'}),\n",
-       " Document(page_content=' meow😻😻', metadata={'line_number': 2, 'source': './meow.txt'})]"
+       "[Document(metadata={'line_number': 0, 'source': './meow.txt'}, page_content='meow meow🐱 \\n'),\n",
+       " Document(metadata={'line_number': 1, 'source': './meow.txt'}, page_content=' meow meow🐱 \\n'),\n",
+       " Document(metadata={'line_number': 2, 'source': './meow.txt'}, page_content=' meow😻😻')]"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -286,9 +345,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "209f6a91-2f15-4cb2-9237-f79fc9493b82",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:58.124363Z",
+     "start_time": "2025-04-21T08:49:58.120782Z"
+    },
     "tags": []
    },
    "outputs": [],
@@ -313,9 +376,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "b1275c59-06d4-458f-abd2-fcbad0bde442",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:58.172506Z",
+     "start_time": "2025-04-21T08:49:58.167416Z"
+    },
     "tags": []
    },
    "outputs": [],
@@ -326,21 +393,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "id": "56a3d707-2086-413b-ae82-50e92ddb27f6",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:58.218426Z",
+     "start_time": "2025-04-21T08:49:58.214684Z"
+    },
     "tags": []
    },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='meow meow🐱 \\n', metadata={'line_number': 1, 'source': './meow.txt'}),\n",
-       " Document(page_content=' meow meow🐱 \\n', metadata={'line_number': 2, 'source': './meow.txt'}),\n",
-       " Document(page_content=' meow😻😻', metadata={'line_number': 3, 'source': './meow.txt'})]"
+       "[Document(metadata={'line_number': 1, 'source': './meow.txt'}, page_content='meow meow🐱 \\n'),\n",
+       " Document(metadata={'line_number': 2, 'source': './meow.txt'}, page_content=' meow meow🐱 \\n'),\n",
+       " Document(metadata={'line_number': 3, 'source': './meow.txt'}, page_content=' meow😻😻')]"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -359,20 +430,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 11,
    "id": "20d03092-ba35-47d7-b612-9d1631c261cd",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:58.267755Z",
+     "start_time": "2025-04-21T08:49:58.264369Z"
+    },
     "tags": []
    },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='some data from memory\\n', metadata={'line_number': 1, 'source': None}),\n",
-       " Document(page_content='meow', metadata={'line_number': 2, 'source': None})]"
+       "[Document(metadata={'line_number': 1, 'source': None}, page_content='some data from memory\\n'),\n",
+       " Document(metadata={'line_number': 2, 'source': None}, page_content='meow')]"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -394,9 +469,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 12,
    "id": "a9e92e0e-c8da-401c-b8c6-f0676004cf58",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:58.330432Z",
+     "start_time": "2025-04-21T08:49:58.327223Z"
+    },
     "tags": []
    },
    "outputs": [],
@@ -406,9 +485,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 13,
    "id": "6b559d30-8b0c-4e45-86b1-e4602d9aaa7e",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:58.383905Z",
+     "start_time": "2025-04-21T08:49:58.380658Z"
+    },
     "tags": []
    },
    "outputs": [
@@ -418,7 +501,7 @@
        "'utf-8'"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -429,9 +512,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 14,
    "id": "2f7b145a-9c6f-47f9-9487-1f4b25aff46f",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:58.443829Z",
+     "start_time": "2025-04-21T08:49:58.440222Z"
+    },
     "tags": []
    },
    "outputs": [
@@ -441,7 +528,7 @@
        "b'meow meow\\xf0\\x9f\\x90\\xb1 \\n meow meow\\xf0\\x9f\\x90\\xb1 \\n meow\\xf0\\x9f\\x98\\xbb\\xf0\\x9f\\x98\\xbb'"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -452,9 +539,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 15,
    "id": "9b9482fa-c49c-42cd-a2ef-80bc93214631",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:58.498609Z",
+     "start_time": "2025-04-21T08:49:58.494903Z"
+    },
     "tags": []
    },
    "outputs": [
@@ -464,7 +555,7 @@
        "'meow meow🐱 \\n meow meow🐱 \\n meow😻😻'"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -475,19 +566,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 16,
    "id": "04cc7a81-290e-4ef8-b7e1-d885fcc59ece",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:58.551353Z",
+     "start_time": "2025-04-21T08:49:58.547518Z"
+    },
     "tags": []
    },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<contextlib._GeneratorContextManager at 0x743f34324450>"
+       "<contextlib._GeneratorContextManager at 0x74b8d42e9940>"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -498,9 +593,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 17,
    "id": "ec8de0ab-51d7-4e41-82c9-3ce0a6fdc2cd",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:58.599576Z",
+     "start_time": "2025-04-21T08:49:58.596567Z"
+    },
     "tags": []
    },
    "outputs": [
@@ -510,7 +609,7 @@
        "{'foo': 'bar'}"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -521,9 +620,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 18,
    "id": "19eae991-ae48-43c2-8952-7347cdb76a34",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:58.649634Z",
+     "start_time": "2025-04-21T08:49:58.646313Z"
+    },
     "tags": []
    },
    "outputs": [
@@ -533,7 +636,7 @@
        "'./meow.txt'"
       ]
      },
-     "execution_count": 16,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -551,65 +654,50 @@
     "\n",
     "While a parser encapsulates the logic needed to parse binary data into documents, *blob loaders* encapsulate the logic that's necessary to load blobs from a given storage location.\n",
     "\n",
-    "At the moment, `LangChain` only supports `FileSystemBlobLoader`.\n",
+    "At the moment, `LangChain` supports `FileSystemBlobLoader` and `CloudBlobLoader`.\n",
     "\n",
     "You can use the `FileSystemBlobLoader` to load blobs and then use the parser to parse them."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 19,
    "id": "c093becb-2e84-4329-89e3-956a3bd765e5",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:49:58.718259Z",
+     "start_time": "2025-04-21T08:49:58.705367Z"
+    },
     "tags": []
    },
    "outputs": [],
    "source": [
     "from langchain_community.document_loaders.blob_loaders import FileSystemBlobLoader\n",
     "\n",
-    "blob_loader = FileSystemBlobLoader(path=\".\", glob=\"*.mdx\", show_progress=True)"
+    "filesystem_blob_loader = FileSystemBlobLoader(\n",
+    "    path=\".\", glob=\"*.mdx\", show_progress=True\n",
+    ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
-   "id": "77739dab-2a1e-4b64-8daa-fee8aa029972",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "45e85d3f63224bb59db02a40ae2e3268",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "  0%|          | 0/8 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "page_content='# Microsoft Office\\n' metadata={'line_number': 1, 'source': 'office_file.mdx'}\n",
-      "page_content='# Markdown\\n' metadata={'line_number': 1, 'source': 'markdown.mdx'}\n",
-      "page_content='# JSON\\n' metadata={'line_number': 1, 'source': 'json.mdx'}\n",
-      "page_content='---\\n' metadata={'line_number': 1, 'source': 'pdf.mdx'}\n",
-      "page_content='---\\n' metadata={'line_number': 1, 'source': 'index.mdx'}\n",
-      "page_content='# File Directory\\n' metadata={'line_number': 1, 'source': 'file_directory.mdx'}\n",
-      "page_content='# CSV\\n' metadata={'line_number': 1, 'source': 'csv.mdx'}\n",
-      "page_content='# HTML\\n' metadata={'line_number': 1, 'source': 'html.mdx'}\n"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "id": "21b91bad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -q tqdm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "40be670b",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "parser = MyParser()\n",
-    "for blob in blob_loader.yield_blobs():\n",
+    "for blob in filesystem_blob_loader.yield_blobs():\n",
     "    for doc in parser.lazy_parse(blob):\n",
     "        print(doc)\n",
     "        break"
@@ -620,56 +708,104 @@
    "id": "f016390c-d38b-4261-946d-34eefe546df7",
    "metadata": {},
    "source": [
-    "### Generic Loader\n",
-    "\n",
-    "LangChain has a `GenericLoader` abstraction which composes a `BlobLoader` with a `BaseBlobParser`.\n",
-    "\n",
-    "`GenericLoader` is meant to provide standardized classmethods that make it easy to use existing `BlobLoader` implementations. At the moment, only the `FileSystemBlobLoader` is supported."
+    "Or, you can use `CloudBlobLoader` to load blobs from a cloud storage location (Supports s3://, az://, gs://, file:// schemes)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
-   "id": "1de74daf-70ee-4616-9089-d28e26b16851",
+   "execution_count": null,
+   "id": "8210714e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -q 'cloudpathlib[s3]'"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d3f84501-b0aa-4a60-aad2-5109cbd37d4f",
+   "metadata": {},
+   "source": [
+    "```python\n",
+    "from cloudpathlib import S3Client, S3Path\n",
+    "from langchain_community.document_loaders.blob_loaders import CloudBlobLoader\n",
+    "\n",
+    "client = S3Client(no_sign_request=True)\n",
+    "client.set_as_default_client()\n",
+    "\n",
+    "path = S3Path(\n",
+    "    \"s3://bucket-01\", client=client\n",
+    ")  # Supports s3://, az://, gs://, file:// schemes.\n",
+    "\n",
+    "cloud_loader = CloudBlobLoader(path, glob=\"**/*.pdf\", show_progress=True)\n",
+    "\n",
+    "for blob in cloud_loader.yield_blobs():\n",
+    "    print(blob)\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "40c361ba4cd30164",
+   "metadata": {},
+   "source": [
+    "### Generic Loader\n",
+    "\n",
+    "LangChain has a `GenericLoader` abstraction which composes a `BlobLoader` with a `BaseBlobParser`.\n",
+    "\n",
+    "`GenericLoader` is meant to provide standardized classmethods that make it easy to use existing `BlobLoader` implementations. At the moment, the `FileSystemBlobLoader` and `CloudBlobLoader` are supported. See example below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "5dfb2be02fe662c5",
    "metadata": {
-    "tags": []
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:50:16.244917Z",
+     "start_time": "2025-04-21T08:50:15.527562Z"
+    }
    },
    "outputs": [
     {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "5f1f6810a71a4909ac9fe1e8f8cb9e0a",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "  0%|          | 0/8 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 7/7 [00:00<00:00, 1224.82it/s]"
+     ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "page_content='# Microsoft Office\\n' metadata={'line_number': 1, 'source': 'office_file.mdx'}\n",
-      "page_content='\\n' metadata={'line_number': 2, 'source': 'office_file.mdx'}\n",
-      "page_content='>[The Microsoft Office](https://www.office.com/) suite of productivity software includes Microsoft Word, Microsoft Excel, Microsoft PowerPoint, Microsoft Outlook, and Microsoft OneNote. It is available for Microsoft Windows and macOS operating systems. It is also available on Android and iOS.\\n' metadata={'line_number': 3, 'source': 'office_file.mdx'}\n",
-      "page_content='\\n' metadata={'line_number': 4, 'source': 'office_file.mdx'}\n",
-      "page_content='This covers how to load commonly used file formats including `DOCX`, `XLSX` and `PPTX` documents into a document format that we can use downstream.\\n' metadata={'line_number': 5, 'source': 'office_file.mdx'}\n",
+      "page_content='# Text embedding models\n",
+      "' metadata={'line_number': 1, 'source': 'embed_text.mdx'}\n",
+      "page_content='\n",
+      "' metadata={'line_number': 2, 'source': 'embed_text.mdx'}\n",
+      "page_content=':::info\n",
+      "' metadata={'line_number': 3, 'source': 'embed_text.mdx'}\n",
+      "page_content='Head to [Integrations](/docs/integrations/text_embedding/) for documentation on built-in integrations with text embedding model providers.\n",
+      "' metadata={'line_number': 4, 'source': 'embed_text.mdx'}\n",
+      "page_content=':::\n",
+      "' metadata={'line_number': 5, 'source': 'embed_text.mdx'}\n",
       "... output truncated for demo purposes\n"
      ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
     }
    ],
    "source": [
     "from langchain_community.document_loaders.generic import GenericLoader\n",
     "\n",
-    "loader = GenericLoader.from_filesystem(\n",
-    "    path=\".\", glob=\"*.mdx\", show_progress=True, parser=MyParser()\n",
+    "generic_loader_filesystem = GenericLoader(\n",
+    "    blob_loader=filesystem_blob_loader, blob_parser=parser\n",
     ")\n",
-    "\n",
-    "for idx, doc in enumerate(loader.lazy_load()):\n",
+    "for idx, doc in enumerate(generic_loader_filesystem.lazy_load()):\n",
     "    if idx < 5:\n",
     "        print(doc)\n",
     "\n",
@@ -690,9 +826,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 28,
    "id": "23633102-dc44-4fed-a4e1-8159489101c8",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:50:34.841862Z",
+     "start_time": "2025-04-21T08:50:34.838375Z"
+    },
     "tags": []
    },
    "outputs": [],
@@ -709,37 +849,46 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 29,
    "id": "dc95be85-4a29-4c6f-a260-08afa3c95538",
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T08:50:34.901734Z",
+     "start_time": "2025-04-21T08:50:34.888098Z"
+    },
     "tags": []
    },
    "outputs": [
     {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "4320598ea3b44a52b1873e1c801db312",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "  0%|          | 0/8 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 7/7 [00:00<00:00, 814.86it/s]"
+     ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "page_content='# Microsoft Office\\n' metadata={'line_number': 1, 'source': 'office_file.mdx'}\n",
-      "page_content='\\n' metadata={'line_number': 2, 'source': 'office_file.mdx'}\n",
-      "page_content='>[The Microsoft Office](https://www.office.com/) suite of productivity software includes Microsoft Word, Microsoft Excel, Microsoft PowerPoint, Microsoft Outlook, and Microsoft OneNote. It is available for Microsoft Windows and macOS operating systems. It is also available on Android and iOS.\\n' metadata={'line_number': 3, 'source': 'office_file.mdx'}\n",
-      "page_content='\\n' metadata={'line_number': 4, 'source': 'office_file.mdx'}\n",
-      "page_content='This covers how to load commonly used file formats including `DOCX`, `XLSX` and `PPTX` documents into a document format that we can use downstream.\\n' metadata={'line_number': 5, 'source': 'office_file.mdx'}\n",
+      "page_content='# Text embedding models\n",
+      "' metadata={'line_number': 1, 'source': 'embed_text.mdx'}\n",
+      "page_content='\n",
+      "' metadata={'line_number': 2, 'source': 'embed_text.mdx'}\n",
+      "page_content=':::info\n",
+      "' metadata={'line_number': 3, 'source': 'embed_text.mdx'}\n",
+      "page_content='Head to [Integrations](/docs/integrations/text_embedding/) for documentation on built-in integrations with text embedding model providers.\n",
+      "' metadata={'line_number': 4, 'source': 'embed_text.mdx'}\n",
+      "page_content=':::\n",
+      "' metadata={'line_number': 5, 'source': 'embed_text.mdx'}\n",
       "... output truncated for demo purposes\n"
      ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
     }
    ],
    "source": [
@@ -769,7 +918,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/sql_large_db.ipynb

@@ -162,7 +162,7 @@
     "\n",
     "table_chain = prompt | llm_with_tools | output_parser\n",
     "\n",
-    "table_chain.invoke({\"input\": \"What are all the genres of Alanis Morisette songs\"})"
+    "table_chain.invoke({\"input\": \"What are all the genres of Alanis Morissette songs\"})"
    ]
   },
   {
@@ -206,7 +206,7 @@
     ")\n",
     "\n",
     "category_chain = prompt | llm_with_tools | output_parser\n",
-    "category_chain.invoke({\"input\": \"What are all the genres of Alanis Morisette songs\"})"
+    "category_chain.invoke({\"input\": \"What are all the genres of Alanis Morissette songs\"})"
    ]
   },
   {
@@ -261,7 +261,7 @@
     "\n",
     "\n",
     "table_chain = category_chain | get_tables\n",
-    "table_chain.invoke({\"input\": \"What are all the genres of Alanis Morisette songs\"})"
+    "table_chain.invoke({\"input\": \"What are all the genres of Alanis Morissette songs\"})"
    ]
   },
   {
@@ -313,7 +313,7 @@
    ],
    "source": [
     "query = full_chain.invoke(\n",
-    "    {\"question\": \"What are all the genres of Alanis Morisette songs\"}\n",
+    "    {\"question\": \"What are all the genres of Alanis Morissette songs\"}\n",
     ")\n",
     "print(query)"
    ]

docs/docs/integrations/callbacks/llmonitor.md

@@ -83,21 +83,28 @@ agent_executor.run("how many letters in the word educa?", callbacks=[handler])
 Another example:
 
 ```python
-from langchain.agents import load_tools, initialize_agent, AgentType
-from langchain_openai import OpenAI
-from langchain_community.callbacks.llmonitor_callback import LLMonitorCallbackHandler
+import os
 
+from langchain_community.agent_toolkits.load_tools import load_tools
+from langchain_community.callbacks.llmonitor_callback import LLMonitorCallbackHandler
+from langchain_openai import ChatOpenAI
+from langgraph.prebuilt import create_react_agent
+
+os.environ["LLMONITOR_APP_ID"] = ""
+os.environ["OPENAI_API_KEY"] = ""
+os.environ["SERPAPI_API_KEY"] = ""
 
 handler = LLMonitorCallbackHandler()
-
-llm = OpenAI(temperature=0)
+llm = ChatOpenAI(temperature=0, callbacks=[handler])
 tools = load_tools(["serpapi", "llm-math"], llm=llm)
-agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, metadata={ "agent_name": "GirlfriendAgeFinder" })  # <- recommended, assign a custom name
+agent = create_react_agent("openai:gpt-4.1-mini", tools)
 
-agent.run(
-    "Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?",
-    callbacks=[handler],
-)
+input_message = {
+    "role": "user",
+    "content": "What's the weather in SF?",
+}
+
+agent.invoke({"messages": [input_message]})
 ```
 
 ## User Tracking
@@ -110,7 +117,7 @@ with identify("user-123"):
     llm.invoke("Tell me a joke")
 
 with identify("user-456", user_props={"email": "user456@test.com"}):
-    agent.run("Who is Leo DiCaprio's girlfriend?")
+    agent.invoke(...)
 ```
 ## Support
 

docs/docs/integrations/chat/cloudflare_workersai.ipynb

@@ -41,7 +41,7 @@
     "### Credentials\n",
     "\n",
     "\n",
-    "Head to https://www.cloudflare.com/developer-platform/products/workers-ai/ to sign up to CloudflareWorkersAI and generate an API key. Once you've done this set the CF_API_KEY environment variable and the CF_ACCOUNT_ID environment variable:"
+    "Head to https://www.cloudflare.com/developer-platform/products/workers-ai/ to sign up to CloudflareWorkersAI and generate an API key. Once you've done this set the CF_AI_API_KEY environment variable and the CF_ACCOUNT_ID environment variable:"
    ]
   },
   {
@@ -56,8 +56,8 @@
     "import getpass\n",
     "import os\n",
     "\n",
-    "if not os.getenv(\"CF_API_KEY\"):\n",
-    "    os.environ[\"CF_API_KEY\"] = getpass.getpass(\n",
+    "if not os.getenv(\"CF_AI_API_KEY\"):\n",
+    "    os.environ[\"CF_AI_API_KEY\"] = getpass.getpass(\n",
     "        \"Enter your CloudflareWorkersAI API key: \"\n",
     "    )\n",
     "\n",

docs/docs/integrations/providers/aerospike.mdx

@@ -8,17 +8,19 @@
 Install the AVS Python SDK and AVS langchain vector store:
 
 ```bash
-pip install aerospike-vector-search langchain-community
+pip install aerospike-vector-search langchain-aerospike
+```
 
-See the documentation for the Ptyhon SDK [here](https://aerospike-vector-search-python-client.readthedocs.io/en/latest/index.html).
-The documentation for the AVS langchain vector store is [here](https://python.langchain.com/api_reference/community/vectorstores/langchain_community.vectorstores.aerospike.Aerospike.html).
+See the documentation for the Python SDK [here](https://aerospike-vector-search-python-client.readthedocs.io/en/latest/index.html).
+The documentation for the AVS langchain vector store is [here](https://langchain-aerospike.readthedocs.io/en/latest/).
 
 ## Vector Store
 
 To import this vectorstore:
 
 ```python
-from langchain_community.vectorstores import Aerospike
+from langchain_aerospike.vectorstores import Aerospike
+```
 
 See a usage example [here](https://python.langchain.com/docs/integrations/vectorstores/aerospike/).
 

docs/docs/integrations/providers/brightdata.mdx

@@ -0,0 +1,34 @@
+# Bright Data
+
+[Bright Data](https://brightdata.com) is a web data platform that provides tools for web scraping, SERP collection, and accessing geo-restricted content.
+
+Bright Data allows developers to extract structured data from websites, perform search engine queries, and access content that might be otherwise blocked or geo-restricted. The platform is designed to help overcome common web scraping challenges including anti-bot systems, CAPTCHAs, and IP blocks.
+
+## Installation and Setup
+
+```bash
+pip install langchain-brightdata
+```
+
+You'll need to set up your Bright Data API key:
+
+```python
+import os
+os.environ["BRIGHT_DATA_API_KEY"] = "your-api-key"
+```
+
+Or you can pass it directly when initializing tools:
+
+```python
+from langchain_bright_data import BrightDataSERP
+
+tool = BrightDataSERP(bright_data_api_key="your-api-key")
+```
+
+## Tools
+
+The Bright Data integration provides several tools:
+
+- [BrightDataSERP](/docs/integrations/tools/brightdata_serp) - Search engine results collection with geo-targeting
+- [BrightDataUnblocker](/docs/integrations/tools/brightdata_unlocker) - Access ANY public website that might be geo-restricted or bot-protected
+- [BrightDataWebScraperAPI](/docs/integrations/tools/brightdata-webscraperapi) - Extract structured data from 100+ ppoular domains, e.g. Amazon product details and LinkedIn profiles

docs/docs/integrations/providers/dataforseo.mdx

@@ -32,7 +32,7 @@ For a detailed walkthrough of this wrapper, see [this notebook](/docs/integratio
 You can also load this wrapper as a Tool to use with an Agent:
 
 ```python
-from langchain.agents import load_tools
+from langchain_community.agent_toolkits.load_tools import load_tools
 tools = load_tools(["dataforseo-api-search"])
 ```
 

docs/docs/integrations/providers/doctran.mdx

@@ -1,8 +1,8 @@
 # Doctran
 
->[Doctran](https://github.com/psychic-api/doctran) is a python package. It uses LLMs and open-source 
-> NLP libraries to transform raw text into clean, structured, information-dense documents 
-> that are optimized for vector space retrieval. You can think of `Doctran` as a black box where 
+>[Doctran](https://github.com/psychic-api/doctran) is a python package. It uses LLMs and open-source
+> NLP libraries to transform raw text into clean, structured, information-dense documents
+> that are optimized for vector space retrieval. You can think of `Doctran` as a black box where
 > messy strings go in and nice, clean, labelled strings come out.
 
 
@@ -19,19 +19,19 @@ pip install doctran
 See a [usage example for DoctranQATransformer](/docs/integrations/document_transformers/doctran_interrogate_document).
 
 ```python
-from langchain_community.document_loaders import DoctranQATransformer
+from langchain_community.document_transformers import DoctranQATransformer
 ```
 ### Property Extractor
 
 See a [usage example for DoctranPropertyExtractor](/docs/integrations/document_transformers/doctran_extract_properties).
 
 ```python
-from langchain_community.document_loaders import DoctranPropertyExtractor
+from langchain_community.document_transformers import DoctranPropertyExtractor
 ```
 ### Document Translator
 
 See a [usage example for DoctranTextTranslator](/docs/integrations/document_transformers/doctran_translate_document).
 
 ```python
-from langchain_community.document_loaders import DoctranTextTranslator
+from langchain_community.document_transformers import DoctranTextTranslator
 ```

docs/docs/integrations/providers/friendli.mdx

@@ -1,6 +1,6 @@
 # Friendli AI
 
-> [FriendliAI](https://friendli.ai/) enhances AI application performance and optimizes 
+> [FriendliAI](https://friendli.ai/) enhances AI application performance and optimizes
 > cost savings with scalable, efficient deployment options, tailored for high-demand AI workloads.
 
 ## Installation and setup
@@ -11,8 +11,8 @@ Install the `friendli-client` python package.
 pip install -U langchain_community friendli-client
 ```
 
-Sign in to [Friendli Suite](https://suite.friendli.ai/) to create a Personal Access Token, 
-and set it as the `FRIENDLI_TOKEN` environment variabzle.
+Sign in to [Friendli Suite](https://suite.friendli.ai/) to create a Personal Access Token,
+and set it as the `FRIENDLI_TOKEN` environment variable.
 
 
 ## Chat models

docs/docs/integrations/providers/gel.mdx

@@ -0,0 +1,56 @@
+# Gel
+
+[Gel](https://www.geldata.com/) is a powerful data platform built on top of PostgreSQL.
+
+- Think in objects and graphs instead of tables and JOINs.
+- Use the advanced Python SDK, integrated GUI, migrations engine, Auth and AI layers, and much more.
+- Run locally, remotely, or in a [fully managed cloud](https://www.geldata.com/cloud).
+
+## Installation
+
+```bash
+pip install langchain-gel
+```
+
+## Setup
+
+1. Run `gel project init`
+2. Edit the schema. You need the following types to use the LangChain vectorstore:
+
+```gel
+using extension pgvector;
+                                    
+module default {
+    scalar type EmbeddingVector extending ext::pgvector::vector<1536>;
+
+    type Record {
+        required collection: str;
+        text: str;
+        embedding: EmbeddingVector; 
+        external_id: str {
+            constraint exclusive;
+        };
+        metadata: json;
+
+        index ext::pgvector::hnsw_cosine(m := 16, ef_construction := 128)
+            on (.embedding)
+    } 
+}
+```
+
+> Note: this is the minimal setup. Feel free to add as many types, properties and links as you want!
+> Learn more about taking advantage of Gel's schema by reading the [docs](https://docs.geldata.com/learn/schema).
+
+3. Run the migration: `gel migration create && gel migrate`.
+
+## Usage
+
+```python
+from langchain_gel import GelVectorStore
+
+vector_store = GelVectorStore(
+    embeddings=embeddings,
+) 
+```
+
+See the full usage example [here](/docs/integrations/vectorstores/gel).

docs/docs/integrations/providers/golden.mdx

@@ -27,7 +27,7 @@ For a more detailed walkthrough of this wrapper, see [this notebook](/docs/integ
 You can also easily load this wrapper as a Tool (to use with an Agent).
 You can do this with:
 ```python
-from langchain.agents import load_tools
+from langchain_community.agent_toolkits.load_tools import load_tools
 tools = load_tools(["golden-query"])
 ```
 

docs/docs/integrations/providers/google.mdx

@@ -880,7 +880,7 @@ from langchain_community.tools import GoogleSearchRun, GoogleSearchResults
 
 Agent Loading:
 ```python
-from langchain.agents import load_tools
+from langchain_community.agent_toolkits.load_tools import load_tools
 tools = load_tools(["google-search"])
 ```
 
@@ -1313,7 +1313,7 @@ from langchain_community.tools import GoogleSearchRun, GoogleSearchResults
 
 Agent Loading:
 ```python
-from langchain.agents import load_tools
+from langchain_community.agent_toolkits.load_tools import load_tools
 tools = load_tools(["google-search"])
 ```
 

docs/docs/integrations/providers/google_serper.mdx

@@ -67,7 +67,7 @@ For a more detailed walkthrough of this wrapper, see [this notebook](/docs/integ
 You can also easily load this wrapper as a Tool (to use with an Agent).
 You can do this with:
 ```python
-from langchain.agents import load_tools
+from langchain_community.agent_toolkits.load_tools import load_tools
 tools = load_tools(["google-serper"])
 ```
 

docs/docs/integrations/providers/milvus.mdx

@@ -21,13 +21,3 @@ To import this vectorstore:
 from langchain_milvus import Milvus
 ```
 
-## Retrievers
-
-See a [usage example](/docs/integrations/retrievers/milvus_hybrid_search).
-
-To import this vectorstore:
-```python
-from langchain_milvus.retrievers import MilvusCollectionHybridSearchRetriever
-from langchain_milvus.utils.sparse import BM25SparseEmbedding
-```
-

docs/docs/integrations/providers/openweathermap.mdx

@@ -37,8 +37,12 @@ You can also easily load this wrapper as a Tool (to use with an Agent).
 You can do this with:
 
 ```python
-from langchain.agents import load_tools
-tools = load_tools(["openweathermap-api"])
+import os
+from langchain_community.utilities import OpenWeatherMapAPIWrapper
+
+os.environ["OPENWEATHERMAP_API_KEY"] = ""
+weather = OpenWeatherMapAPIWrapper()
+tools = [weather.run]
 ```
 
 For more information on tools, see [this page](/docs/how_to/tools_builtin).

docs/docs/integrations/providers/searchapi.mdx

@@ -73,7 +73,7 @@ You can also easily load this wrapper as a Tool (to use with an Agent).
 You can do this with:
 
 ```python
-from langchain.agents import load_tools
+from langchain_community.agent_toolkits.load_tools import load_tools
 tools = load_tools(["searchapi"])
 ```
 

docs/docs/integrations/providers/searx.mdx

@@ -52,7 +52,7 @@ You can also load this wrapper as a Tool (to use with an Agent).
 You can do this with:
 
 ```python
-from langchain.agents import load_tools
+from langchain_community.agent_toolkits.load_tools import load_tools
 tools = load_tools(["searx-search"],
                     searx_host="http://localhost:8888",
                     engines=["github"])

docs/docs/integrations/providers/serpapi.mdx

@@ -24,7 +24,7 @@ For a more detailed walkthrough of this wrapper, see [this notebook](/docs/integ
 You can also easily load this wrapper as a Tool (to use with an Agent).
 You can do this with:
 ```python
-from langchain.agents import load_tools
+from langchain_community.agent_toolkits.load_tools import load_tools
 tools = load_tools(["serpapi"])
 ```
 

docs/docs/integrations/providers/stackexchange.mdx

@@ -29,7 +29,7 @@ For a more detailed walkthrough of this wrapper, see [this notebook](/docs/integ
 You can also easily load this wrapper as a Tool (to use with an Agent).
 You can do this with:
 ```python
-from langchain.agents import load_tools
+from langchain_community.agent_toolkits.load_tools import load_tools
 tools = load_tools(["stackexchange"])
 ```
 

docs/docs/integrations/providers/wolfram_alpha.mdx

@@ -32,7 +32,7 @@ For a more detailed walkthrough of this wrapper, see [this notebook](/docs/integ
 You can also easily load this wrapper as a Tool (to use with an Agent).
 You can do this with:
 ```python
-from langchain.agents import load_tools
+from langchain_community.agent_toolkits.load_tools import load_tools
 tools = load_tools(["wolfram-alpha"])
 ```
 

docs/docs/integrations/retrievers/milvus_hybrid_search.ipynb

@@ -1,639 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "raw",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: Milvus Hybrid Search\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Milvus Hybrid Search Retriever\n",
-    "\n",
-    "> [Milvus](https://milvus.io/docs) is an open-source vector database built to power embedding similarity search and AI applications. Milvus makes unstructured data search more accessible, and provides a consistent user experience regardless of the deployment environment.\n",
-    "\n",
-    "This will help you getting started with the Milvus Hybrid Search [retriever](/docs/concepts/retrievers), which combines the strengths of both dense and sparse vector search. For detailed documentation of all `MilvusCollectionHybridSearchRetriever` features and configurations head to the [API reference](https://python.langchain.com/api_reference/milvus/retrievers/langchain_milvus.retrievers.milvus_hybrid_search.MilvusCollectionHybridSearchRetriever.html).\n",
-    "\n",
-    "See also the Milvus Multi-Vector Search [docs](https://milvus.io/docs/multi-vector-search.md).\n",
-    "\n",
-    "### Integration details\n",
-    "\n",
-    "import {ItemTable} from \"@theme/FeatureTables\";\n",
-    "\n",
-    "<ItemTable category=\"document_retrievers\" item=\"MilvusCollectionHybridSearchRetriever\" />\n",
-    "\n",
-    "## Setup\n",
-    "\n",
-    "If you want to get automated tracing from individual queries, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
-    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
-   "source": [
-    "### Installation\n",
-    "\n",
-    "This retriever lives in the `langchain-milvus` package. This guide requires the following dependencies:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    },
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "%pip install --upgrade --quiet pymilvus[model] langchain-milvus langchain-openai"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import PromptTemplate\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "from langchain_milvus.retrievers import MilvusCollectionHybridSearchRetriever\n",
-    "from langchain_milvus.utils.sparse import BM25SparseEmbedding\n",
-    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
-    "from pymilvus import (\n",
-    "    Collection,\n",
-    "    CollectionSchema,\n",
-    "    DataType,\n",
-    "    FieldSchema,\n",
-    "    WeightedRanker,\n",
-    "    connections,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Start the Milvus service\n",
-    "\n",
-    "Please refer to the [Milvus documentation](https://milvus.io/docs/install_standalone-docker.md) to start the Milvus service.\n",
-    "\n",
-    "After starting milvus, you need to specify your milvus connection URI."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    },
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "CONNECTION_URI = \"http://localhost:19530\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
-   "source": [
-    "### Prepare OpenAI API Key\n",
-    "\n",
-    "Please refer to the [OpenAI documentation](https://platform.openai.com/account/api-keys) to obtain your OpenAI API key, and set it as an environment variable.\n",
-    "\n",
-    "```shell\n",
-    "export OPENAI_API_KEY=<your_api_key>\n",
-    "```\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Prepare dense and sparse embedding functions\n",
-    "\n",
-    "Let us fictionalize 10 fake descriptions of novels. In actual production, it may be a large amount of text data."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "texts = [\n",
-    "    \"In 'The Whispering Walls' by Ava Moreno, a young journalist named Sophia uncovers a decades-old conspiracy hidden within the crumbling walls of an ancient mansion, where the whispers of the past threaten to destroy her own sanity.\",\n",
-    "    \"In 'The Last Refuge' by Ethan Blackwood, a group of survivors must band together to escape a post-apocalyptic wasteland, where the last remnants of humanity cling to life in a desperate bid for survival.\",\n",
-    "    \"In 'The Memory Thief' by Lila Rose, a charismatic thief with the ability to steal and manipulate memories is hired by a mysterious client to pull off a daring heist, but soon finds themselves trapped in a web of deceit and betrayal.\",\n",
-    "    \"In 'The City of Echoes' by Julian Saint Clair, a brilliant detective must navigate a labyrinthine metropolis where time is currency, and the rich can live forever, but at a terrible cost to the poor.\",\n",
-    "    \"In 'The Starlight Serenade' by Ruby Flynn, a shy astronomer discovers a mysterious melody emanating from a distant star, which leads her on a journey to uncover the secrets of the universe and her own heart.\",\n",
-    "    \"In 'The Shadow Weaver' by Piper Redding, a young orphan discovers she has the ability to weave powerful illusions, but soon finds herself at the center of a deadly game of cat and mouse between rival factions vying for control of the mystical arts.\",\n",
-    "    \"In 'The Lost Expedition' by Caspian Grey, a team of explorers ventures into the heart of the Amazon rainforest in search of a lost city, but soon finds themselves hunted by a ruthless treasure hunter and the treacherous jungle itself.\",\n",
-    "    \"In 'The Clockwork Kingdom' by Augusta Wynter, a brilliant inventor discovers a hidden world of clockwork machines and ancient magic, where a rebellion is brewing against the tyrannical ruler of the land.\",\n",
-    "    \"In 'The Phantom Pilgrim' by Rowan Welles, a charismatic smuggler is hired by a mysterious organization to transport a valuable artifact across a war-torn continent, but soon finds themselves pursued by deadly assassins and rival factions.\",\n",
-    "    \"In 'The Dreamwalker's Journey' by Lyra Snow, a young dreamwalker discovers she has the ability to enter people's dreams, but soon finds herself trapped in a surreal world of nightmares and illusions, where the boundaries between reality and fantasy blur.\",\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We will use the [OpenAI Embedding](https://platform.openai.com/docs/guides/embeddings) to generate dense vectors, and the [BM25 algorithm](https://en.wikipedia.org/wiki/Okapi_BM25) to generate sparse vectors.\n",
-    "\n",
-    "Initialize dense embedding function and get dimension"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "1536"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "dense_embedding_func = OpenAIEmbeddings()\n",
-    "dense_dim = len(dense_embedding_func.embed_query(texts[1]))\n",
-    "dense_dim"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Initialize sparse embedding function.\n",
-    "\n",
-    "Note that the output of sparse embedding is a set of sparse vectors, which represents the index and weight of the keywords of the input text."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{0: 0.4270424944042204,\n",
-       " 21: 1.845826690498331,\n",
-       " 22: 1.845826690498331,\n",
-       " 23: 1.845826690498331,\n",
-       " 24: 1.845826690498331,\n",
-       " 25: 1.845826690498331,\n",
-       " 26: 1.845826690498331,\n",
-       " 27: 1.2237754316221157,\n",
-       " 28: 1.845826690498331,\n",
-       " 29: 1.845826690498331,\n",
-       " 30: 1.845826690498331,\n",
-       " 31: 1.845826690498331,\n",
-       " 32: 1.845826690498331,\n",
-       " 33: 1.845826690498331,\n",
-       " 34: 1.845826690498331,\n",
-       " 35: 1.845826690498331,\n",
-       " 36: 1.845826690498331,\n",
-       " 37: 1.845826690498331,\n",
-       " 38: 1.845826690498331,\n",
-       " 39: 1.845826690498331}"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "sparse_embedding_func = BM25SparseEmbedding(corpus=texts)\n",
-    "sparse_embedding_func.embed_query(texts[1])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create Milvus Collection and load data\n",
-    "\n",
-    "Initialize connection URI and establish connection"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "connections.connect(uri=CONNECTION_URI)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Define field names and their data types"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pk_field = \"doc_id\"\n",
-    "dense_field = \"dense_vector\"\n",
-    "sparse_field = \"sparse_vector\"\n",
-    "text_field = \"text\"\n",
-    "fields = [\n",
-    "    FieldSchema(\n",
-    "        name=pk_field,\n",
-    "        dtype=DataType.VARCHAR,\n",
-    "        is_primary=True,\n",
-    "        auto_id=True,\n",
-    "        max_length=100,\n",
-    "    ),\n",
-    "    FieldSchema(name=dense_field, dtype=DataType.FLOAT_VECTOR, dim=dense_dim),\n",
-    "    FieldSchema(name=sparse_field, dtype=DataType.SPARSE_FLOAT_VECTOR),\n",
-    "    FieldSchema(name=text_field, dtype=DataType.VARCHAR, max_length=65_535),\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Create a collection with the defined schema"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "schema = CollectionSchema(fields=fields, enable_dynamic_field=False)\n",
-    "collection = Collection(\n",
-    "    name=\"IntroductionToTheNovels\", schema=schema, consistency_level=\"Strong\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Define index for dense and sparse vectors"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "dense_index = {\"index_type\": \"FLAT\", \"metric_type\": \"IP\"}\n",
-    "collection.create_index(\"dense_vector\", dense_index)\n",
-    "sparse_index = {\"index_type\": \"SPARSE_INVERTED_INDEX\", \"metric_type\": \"IP\"}\n",
-    "collection.create_index(\"sparse_vector\", sparse_index)\n",
-    "collection.flush()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Insert entities into the collection and load the collection"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "entities = []\n",
-    "for text in texts:\n",
-    "    entity = {\n",
-    "        dense_field: dense_embedding_func.embed_documents([text])[0],\n",
-    "        sparse_field: sparse_embedding_func.embed_documents([text])[0],\n",
-    "        text_field: text,\n",
-    "    }\n",
-    "    entities.append(entity)\n",
-    "collection.insert(entities)\n",
-    "collection.load()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Instantiation\n",
-    "\n",
-    "Now we can instantiate our retriever, defining search parameters for sparse and dense fields:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "sparse_search_params = {\"metric_type\": \"IP\"}\n",
-    "dense_search_params = {\"metric_type\": \"IP\", \"params\": {}}\n",
-    "retriever = MilvusCollectionHybridSearchRetriever(\n",
-    "    collection=collection,\n",
-    "    rerank=WeightedRanker(0.5, 0.5),\n",
-    "    anns_fields=[dense_field, sparse_field],\n",
-    "    field_embeddings=[dense_embedding_func, sparse_embedding_func],\n",
-    "    field_search_params=[dense_search_params, sparse_search_params],\n",
-    "    top_k=3,\n",
-    "    text_field=text_field,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
-   "source": [
-    "In the input parameters of this Retriever, we use a dense embedding and a sparse embedding to perform hybrid search on the two fields of this Collection, and use WeightedRanker for reranking. Finally, 3 top-K Documents will be returned."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Usage"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[Document(page_content=\"In 'The Lost Expedition' by Caspian Grey, a team of explorers ventures into the heart of the Amazon rainforest in search of a lost city, but soon finds themselves hunted by a ruthless treasure hunter and the treacherous jungle itself.\", metadata={'doc_id': '449281835035545843'}),\n",
-       " Document(page_content=\"In 'The Phantom Pilgrim' by Rowan Welles, a charismatic smuggler is hired by a mysterious organization to transport a valuable artifact across a war-torn continent, but soon finds themselves pursued by deadly assassins and rival factions.\", metadata={'doc_id': '449281835035545845'}),\n",
-       " Document(page_content=\"In 'The Dreamwalker's Journey' by Lyra Snow, a young dreamwalker discovers she has the ability to enter people's dreams, but soon finds herself trapped in a surreal world of nightmares and illusions, where the boundaries between reality and fantasy blur.\", metadata={'doc_id': '449281835035545846'})]"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "retriever.invoke(\"What are the story about ventures?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Use within a chain\n",
-    "\n",
-    "Initialize ChatOpenAI and define a prompt template"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "llm = ChatOpenAI()\n",
-    "\n",
-    "PROMPT_TEMPLATE = \"\"\"\n",
-    "Human: You are an AI assistant, and provides answers to questions by using fact based and statistical information when possible.\n",
-    "Use the following pieces of information to provide a concise answer to the question enclosed in <question> tags.\n",
-    "\n",
-    "<context>\n",
-    "{context}\n",
-    "</context>\n",
-    "\n",
-    "<question>\n",
-    "{question}\n",
-    "</question>\n",
-    "\n",
-    "Assistant:\"\"\"\n",
-    "\n",
-    "prompt = PromptTemplate(\n",
-    "    template=PROMPT_TEMPLATE, input_variables=[\"context\", \"question\"]\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
-   "source": [
-    "Define a function for formatting documents"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    },
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "def format_docs(docs):\n",
-    "    return \"\\n\\n\".join(doc.page_content for doc in docs)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
-   "source": [
-    "Define a chain using the retriever and other components"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    },
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "rag_chain = (\n",
-    "    {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
-    "    | prompt\n",
-    "    | llm\n",
-    "    | StrOutputParser()\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
-   "source": [
-    "Perform a query using the defined chain"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    },
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"Lila Rose has written 'The Memory Thief,' which follows a charismatic thief with the ability to steal and manipulate memories as they navigate a daring heist and a web of deceit and betrayal.\""
-      ]
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "rag_chain.invoke(\"What novels has Lila written and what are their contents?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
-   "source": [
-    "Drop the collection"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    },
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "collection.drop()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## API reference\n",
-    "\n",
-    "For detailed documentation of all `MilvusCollectionHybridSearchRetriever` features and configurations head to the [API reference](https://python.langchain.com/api_reference/milvus/retrievers/langchain_milvus.retrievers.milvus_hybrid_search.MilvusCollectionHybridSearchRetriever.html)."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

docs/docs/integrations/text_embedding/cloudflare_workersai.ipynb

@@ -12,24 +12,36 @@
     "\n",
     ">[Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai/) allows you to run machine learning models, on the `Cloudflare` network, from your code via REST API.\n",
     "\n",
-    ">[Cloudflare AI document](https://developers.cloudflare.com/workers-ai/models/text-embeddings/) listed all text embeddings models available.\n",
+    ">[Workers AI Developer Docs](https://developers.cloudflare.com/workers-ai/models/text-embeddings/) lists all text embeddings models available.\n",
     "\n",
     "## Setting up\n",
     "\n",
-    "Both Cloudflare account ID and API token are required. Find how to obtain them from [this document](https://developers.cloudflare.com/workers-ai/get-started/rest-api/).\n"
+    "Both a Cloudflare Account ID and Workers AI API token are required. Find how to obtain them from [this document](https://developers.cloudflare.com/workers-ai/get-started/rest-api/).\n",
+    "\n",
+    "You can pass these parameters explicitly or define as environmental variables.\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 11,
    "id": "f60023b8",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-05-13T06:00:30.121204Z",
+     "start_time": "2025-05-13T06:00:30.117936Z"
+    }
+   },
    "outputs": [],
    "source": [
-    "import getpass\n",
+    "import os\n",
     "\n",
-    "my_account_id = getpass.getpass(\"Enter your Cloudflare account ID:\\n\\n\")\n",
-    "my_api_token = getpass.getpass(\"Enter your Cloudflare API token:\\n\\n\")"
+    "from dotenv import load_dotenv\n",
+    "\n",
+    "load_dotenv(\".env\")\n",
+    "\n",
+    "cf_acct_id = os.getenv(\"CF_ACCOUNT_ID\")\n",
+    "\n",
+    "cf_ai_token = os.getenv(\"CF_AI_API_TOKEN\")"
    ]
   },
   {
@@ -42,9 +54,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 12,
    "id": "92c5b61e",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-05-13T06:00:31.224996Z",
+     "start_time": "2025-05-13T06:00:31.222981Z"
+    }
+   },
    "outputs": [],
    "source": [
     "from langchain_cloudflare.embeddings import (\n",
@@ -54,25 +71,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 13,
    "id": "062547b9",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-05-13T06:00:32.515031Z",
+     "start_time": "2025-05-13T06:00:31.798590Z"
+    }
+   },
    "outputs": [
     {
      "data": {
-      "text/plain": [
-       "(384, [-0.033627357333898544, 0.03982774540781975, 0.03559349477291107])"
-      ]
+      "text/plain": "(384, [-0.033660888671875, 0.039764404296875, 0.03558349609375])"
      },
-     "execution_count": 3,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "embeddings = CloudflareWorkersAIEmbeddings(\n",
-    "    account_id=my_account_id,\n",
-    "    api_token=my_api_token,\n",
+    "    account_id=cf_acct_id,\n",
+    "    api_token=cf_ai_token,\n",
     "    model_name=\"@cf/baai/bge-small-en-v1.5\",\n",
     ")\n",
     "# single string embeddings\n",
@@ -82,17 +102,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 14,
    "id": "e1dcc4bd",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-05-13T06:00:33.106160Z",
+     "start_time": "2025-05-13T06:00:32.847232Z"
+    }
+   },
    "outputs": [
     {
      "data": {
-      "text/plain": [
-       "(3, 384)"
-      ]
+      "text/plain": "(3, 384)"
      },
-     "execution_count": 4,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -102,14 +125,6 @@
     "batch_query_result = embeddings.embed_documents([\"test1\", \"test2\", \"test3\"])\n",
     "len(batch_query_result), len(batch_query_result[0])"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "52de8b88",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

docs/docs/integrations/tools/brightdata-webscraperapi.ipynb

@@ -0,0 +1,292 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# BrightDataWebScraperAPI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "[Bright Data](https://brightdata.com/) provides a powerful Web Scraper API that allows you to extract structured data from 100+ ppular domains, including Amazon product details, LinkedIn profiles, and more, making it particularly useful for AI agents requiring reliable structured web data feeds."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Overview"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Integration details\n",
+    "\n",
+    "|Class|Package|Serializable|JS support|Package latest|\n",
+    "|:--|:--|:-:|:-:|:-:|\n",
+    "|[BrightDataWebScraperAPI](https://pypi.org/project/langchain-brightdata/)|[langchain-brightdata](https://pypi.org/project/langchain-brightdata/)|✅|❌|![PyPI - Version](https://img.shields.io/pypi/v/langchain-brightdata?style=flat-square&label=%20)|\n",
+    "\n",
+    "### Tool features\n",
+    "\n",
+    "|Native async|Returns artifact|Return data|Pricing|\n",
+    "|:-:|:-:|:--|:-:|\n",
+    "|❌|❌|Structured data from websites (Amazon products, LinkedIn profiles, etc.)|Requires Bright Data account|\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "The integration lives in the `langchain-brightdata` package.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "pip install langchain-brightdata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You'll need a Bright Data API key to use this tool. You can set it as an environment variable:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"BRIGHT_DATA_API_KEY\"] = \"your-api-key\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Or pass it directly when initializing the tool:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_brightdata import BrightDataWebScraperAPI\n",
+    "\n",
+    "scraper_tool = BrightDataWebScraperAPI(bright_data_api_key=\"your-api-key\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Here we show how to instantiate an instance of the BrightDataWebScraperAPI tool. This tool allows you to extract structured data from various websites including Amazon product details, LinkedIn profiles, and more using Bright Data's Dataset API.\n",
+    "\n",
+    "The tool accepts various parameters during instantiation:\n",
+    "\n",
+    "- `bright_data_api_key` (required, str): Your Bright Data API key for authentication.\n",
+    "- `dataset_mapping` (optional, Dict[str, str]): A dictionary mapping dataset types to their corresponding Bright Data dataset IDs. The default mapping includes:\n",
+    "    - \"amazon_product\": \"gd_l7q7dkf244hwjntr0\"\n",
+    "    - \"amazon_product_reviews\": \"gd_le8e811kzy4ggddlq\"\n",
+    "    - \"linkedin_person_profile\": \"gd_l1viktl72bvl7bjuj0\"\n",
+    "    - \"linkedin_company_profile\": \"gd_l1vikfnt1wgvvqz95w\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Invocation\n",
+    "\n",
+    "### Basic Usage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_brightdata import BrightDataWebScraperAPI\n",
+    "\n",
+    "# Initialize the tool\n",
+    "scraper_tool = BrightDataWebScraperAPI(\n",
+    "    bright_data_api_key=\"your-api-key\"  # Optional if set in environment variables\n",
+    ")\n",
+    "\n",
+    "# Extract Amazon product data\n",
+    "results = scraper_tool.invoke(\n",
+    "    {\"url\": \"https://www.amazon.com/dp/B08L5TNJHG\", \"dataset_type\": \"amazon_product\"}\n",
+    ")\n",
+    "\n",
+    "print(results)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Advanced Usage with Parameters"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_brightdata import BrightDataWebScraperAPI\n",
+    "\n",
+    "# Initialize with default parameters\n",
+    "scraper_tool = BrightDataWebScraperAPI(bright_data_api_key=\"your-api-key\")\n",
+    "\n",
+    "# Extract Amazon product data with location-specific pricing\n",
+    "results = scraper_tool.invoke(\n",
+    "    {\n",
+    "        \"url\": \"https://www.amazon.com/dp/B08L5TNJHG\",\n",
+    "        \"dataset_type\": \"amazon_product\",\n",
+    "        \"zipcode\": \"10001\",  # Get pricing for New York City\n",
+    "    }\n",
+    ")\n",
+    "\n",
+    "print(results)\n",
+    "\n",
+    "# Extract LinkedIn profile data\n",
+    "linkedin_results = scraper_tool.invoke(\n",
+    "    {\n",
+    "        \"url\": \"https://www.linkedin.com/in/satyanadella/\",\n",
+    "        \"dataset_type\": \"linkedin_person_profile\",\n",
+    "    }\n",
+    ")\n",
+    "\n",
+    "print(linkedin_results)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Customization Options\n",
+    "\n",
+    "The BrightDataWebScraperAPI tool accepts several parameters for customization:\n",
+    "\n",
+    "|Parameter|Type|Description|\n",
+    "|:--|:--|:--|\n",
+    "|`url`|str|The URL to extract data from|\n",
+    "|`dataset_type`|str|Type of dataset to use (e.g., \"amazon_product\")|\n",
+    "|`zipcode`|str|Optional zipcode for location-specific data|\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Available Dataset Types\n",
+    "\n",
+    "The tool supports the following dataset types for structured data extraction:\n",
+    "\n",
+    "|Dataset Type|Description|\n",
+    "|:--|:--|\n",
+    "|`amazon_product`|Extract detailed Amazon product data|\n",
+    "|`amazon_product_reviews`|Extract Amazon product reviews|\n",
+    "|`linkedin_person_profile`|Extract LinkedIn person profile data|\n",
+    "|`linkedin_company_profile`|Extract LinkedIn company profile data|\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Use within an agent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_brightdata import BrightDataWebScraperAPI\n",
+    "from langchain_google_genai import ChatGoogleGenerativeAI\n",
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "# Initialize the LLM\n",
+    "llm = ChatGoogleGenerativeAI(model=\"gemini-2.0-flash\", google_api_key=\"your-api-key\")\n",
+    "\n",
+    "# Initialize the Bright Data Web Scraper API tool\n",
+    "scraper_tool = BrightDataWebScraperAPI(bright_data_api_key=\"your-api-key\")\n",
+    "\n",
+    "# Create the agent with the tool\n",
+    "agent = create_react_agent(llm, [scraper_tool])\n",
+    "\n",
+    "# Provide a user query\n",
+    "user_input = \"Scrape Amazon product data for https://www.amazon.com/dp/B0D2Q9397Y?th=1 in New York (zipcode 10001).\"\n",
+    "\n",
+    "# Stream the agent's step-by-step output\n",
+    "for step in agent.stream(\n",
+    "    {\"messages\": user_input},\n",
+    "    stream_mode=\"values\",\n",
+    "):\n",
+    "    step[\"messages\"][-1].pretty_print()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "- [Bright Data API Documentation](https://docs.brightdata.com/scraping-automation/web-scraper-api/overview)"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/integrations/tools/brightdata_serp.ipynb

@@ -0,0 +1,294 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "a6f91f20",
+   "metadata": {},
+   "source": [
+    "# BrightDataSERP\n",
+    "\n",
+    "[Bright Data](https://brightdata.com/) provides a powerful SERP API that allows you to query search engines (Google,Bing.DuckDuckGo,Yandex) with geo-targeting and advanced customization options, particularly useful for AI agents requiring real-time web information.\n",
+    "\n",
+    "\n",
+    "## Overview\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "\n",
+    "|Class|Package|Serializable|JS support|Package latest|\n",
+    "|:--|:--|:-:|:-:|:-:|\n",
+    "|[BrightDataSERP](https://pypi.org/project/langchain-brightdata/)|[langchain-brightdata](https://pypi.org/project/langchain-brightdata/)|✅|❌|![PyPI - Version](https://img.shields.io/pypi/v/langchain-brightdata?style=flat-square&label=%20)|\n",
+    "\n",
+    "\n",
+    "### Tool features\n",
+    "\n",
+    "\n",
+    "|Native async|Returns artifact|Return data|Pricing|\n",
+    "|:-:|:-:|:--|:-:|\n",
+    "|❌|❌|Title, URL, snippet, position, and other search result data|Requires Bright Data account|\n",
+    "\n",
+    "\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "The integration lives in the `langchain-brightdata` package."
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "id": "f85b4089",
+   "metadata": {},
+   "source": [
+    "pip install langchain-brightdata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b15e9266",
+   "metadata": {},
+   "source": [
+    "### Credentials\n",
+    "\n",
+    "You'll need a Bright Data API key to use this tool. You can set it as an environment variable:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "e0b178a2-8816-40ca-b57c-ccdd86dde9c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"BRIGHT_DATA_API_KEY\"] = \"your-api-key\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bc5ab717-fd27-4c59-b912-bdd099541478",
+   "metadata": {},
+   "source": [
+    "Or pass it directly when initializing the tool:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "a6c2f136-6367-4f1f-825d-ae741e1bf281",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_brightdata import BrightDataSERP\n",
+    "\n",
+    "serp_tool = BrightDataSERP(bright_data_api_key=\"your-api-key\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "eed8cfcc",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Here we show how to instantiate an instance of the BrightDataSERP tool. This tool allows you to perform search engine queries with various customization options including geo-targeting, language preferences, device type simulation, and specific search types using Bright Data's SERP API.\n",
+    "\n",
+    "The tool accepts various parameters during instantiation:\n",
+    "\n",
+    "- `bright_data_api_key` (required, str): Your Bright Data API key for authentication.\n",
+    "- `search_engine` (optional, str): Search engine to use for queries. Default is \"google\". Other options include \"bing\", \"yahoo\", \"yandex\", \"DuckDuckGo\" etc.\n",
+    "- `country` (optional, str): Two-letter country code for localized search results (e.g., \"us\", \"gb\", \"de\", \"jp\"). Default is \"us\".\n",
+    "- `language` (optional, str): Two-letter language code for the search results (e.g., \"en\", \"es\", \"fr\", \"de\"). Default is \"en\".\n",
+    "- `results_count` (optional, int): Number of search results to return. Default is 10. Maximum value is typically 100.\n",
+    "- `search_type` (optional, str): Type of search to perform. Options include:\n",
+    "    - None (default): Regular web search\n",
+    "    - \"isch\": Images search\n",
+    "    - \"shop\": Shopping search\n",
+    "    - \"nws\": News search\n",
+    "    - \"jobs\": Jobs search\n",
+    "- `device_type` (optional, str): Device type to simulate for the search. Options include:\n",
+    "    - None (default): Desktop device\n",
+    "    - \"mobile\": Generic mobile device\n",
+    "    - \"ios\": iOS device (iPhone)\n",
+    "    - \"android\": Android device\n",
+    "- `parse_results` (optional, bool): Whether to return parsed JSON results. Default is False, which returns raw HTML response."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1c97218f-f366-479d-8bf7-fe9f2f6df73f",
+   "metadata": {},
+   "source": [
+    "## Invocation"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "902dc1fd",
+   "metadata": {},
+   "source": [
+    "### Basic Usage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8b3ddfe9-ca79-494c-a7ab-1f56d9407a64",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_brightdata import BrightDataSERP\n",
+    "\n",
+    "# Initialize the tool\n",
+    "serp_tool = BrightDataSERP(\n",
+    "    bright_data_api_key=\"your-api-key\"  # Optional if set in environment variables\n",
+    ")\n",
+    "\n",
+    "# Run a basic search\n",
+    "results = serp_tool.invoke(\"latest AI research papers\")\n",
+    "\n",
+    "print(results)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "74147a1a",
+   "metadata": {},
+   "source": [
+    "### Advanced Usage with Parameters"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "65310a8b-eb0c-4d9e-a618-4f4abe2414fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_brightdata import BrightDataSERP\n",
+    "\n",
+    "# Initialize with default parameters\n",
+    "serp_tool = BrightDataSERP(\n",
+    "    bright_data_api_key=\"your-api-key\",\n",
+    "    search_engine=\"google\",  # Default\n",
+    "    country=\"us\",  # Default\n",
+    "    language=\"en\",  # Default\n",
+    "    results_count=10,  # Default\n",
+    "    parse_results=True,  # Get structured JSON results\n",
+    ")\n",
+    "\n",
+    "# Use with specific parameters for this search\n",
+    "results = serp_tool.invoke(\n",
+    "    {\n",
+    "        \"query\": \"best electric vehicles\",\n",
+    "        \"country\": \"de\",  # Get results as if searching from Germany\n",
+    "        \"language\": \"de\",  # Get results in German\n",
+    "        \"search_type\": \"shop\",  # Get shopping results\n",
+    "        \"device_type\": \"mobile\",  # Simulate a mobile device\n",
+    "        \"results_count\": 15,\n",
+    "    }\n",
+    ")\n",
+    "\n",
+    "print(results)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d6e73897",
+   "metadata": {},
+   "source": [
+    "## Customization Options\n",
+    "\n",
+    "The BrightDataSERP tool accepts several parameters for customization:\n",
+    "\n",
+    "|Parameter|Type|Description|\n",
+    "|:--|:--|:--|\n",
+    "|`query`|str|The search query to perform|\n",
+    "|`search_engine`|str|Search engine to use (default: \"google\")|\n",
+    "|`country`|str|Two-letter country code for localized results (default: \"us\")|\n",
+    "|`language`|str|Two-letter language code (default: \"en\")|\n",
+    "|`results_count`|int|Number of results to return (default: 10)|\n",
+    "|`search_type`|str|Type of search: None (web), \"isch\" (images), \"shop\", \"nws\" (news), \"jobs\"|\n",
+    "|`device_type`|str|Device type: None (desktop), \"mobile\", \"ios\", \"android\"|\n",
+    "|`parse_results`|bool|Whether to return structured JSON (default: False)|\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e3353ce6",
+   "metadata": {},
+   "source": [
+    "## Use within an agent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8c91c32f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_brightdata import BrightDataSERP\n",
+    "from langchain_google_genai import ChatGoogleGenerativeAI\n",
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "# Initialize the LLM\n",
+    "llm = ChatGoogleGenerativeAI(model=\"gemini-2.0-flash\", google_api_key=\"your-api-key\")\n",
+    "\n",
+    "# Initialize the Bright Data SERP tool\n",
+    "serp_tool = BrightDataSERP(\n",
+    "    bright_data_api_key=\"your-api-key\",\n",
+    "    search_engine=\"google\",\n",
+    "    country=\"us\",\n",
+    "    language=\"en\",\n",
+    "    results_count=10,\n",
+    "    parse_results=True,\n",
+    ")\n",
+    "\n",
+    "# Create the agent\n",
+    "agent = create_react_agent(llm, [serp_tool])\n",
+    "\n",
+    "# Provide a user query\n",
+    "user_input = \"Search for 'best electric vehicles' shopping results in Germany in German using mobile.\"\n",
+    "\n",
+    "# Stream the agent's output step-by-step\n",
+    "for step in agent.stream(\n",
+    "    {\"messages\": user_input},\n",
+    "    stream_mode=\"values\",\n",
+    "):\n",
+    "    step[\"messages\"][-1].pretty_print()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e8dec55a",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "- [Bright Data API Documentation](https://docs.brightdata.com/scraping-automation/serp-api/introduction)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/tools/brightdata_unlocker.ipynb

@@ -0,0 +1,314 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# BrightDataUnlocker"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "[Bright Data](https://brightdata.com/) provides a powerful Web Unlocker API that allows you to access websites that might be protected by anti-bot measures, geo-restrictions, or other access limitations, making it particularly useful for AI agents requiring reliable web content extraction."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Overview"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Integration details"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "|Class|Package|Serializable|JS support|Package latest|\n",
+    "|:--|:--|:-:|:-:|:-:|\n",
+    "|[BrightDataUnlocker](https://pypi.org/project/langchain-brightdata/)|[langchain-brightdata](https://pypi.org/project/langchain-brightdata/)|✅|❌|![PyPI - Version](https://img.shields.io/pypi/v/langchain-brightdata?style=flat-square&label=%20)|\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Tool features"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "|Native async|Returns artifact|Return data|Pricing|\n",
+    "|:-:|:-:|:--|:-:|\n",
+    "|❌|❌|HTML, Markdown, or screenshot of web pages|Requires Bright Data account|\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The integration lives in the `langchain-brightdata` package."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "pip install langchain-brightdata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You'll need a Bright Data API key to use this tool. You can set it as an environment variable:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"BRIGHT_DATA_API_KEY\"] = \"your-api-key\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Or pass it directly when initializing the tool:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_brightdata import BrightDataUnlocker\n",
+    "\n",
+    "unlocker_tool = BrightDataUnlocker(bright_data_api_key=\"your-api-key\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Here we show how to instantiate an instance of the BrightDataUnlocker tool. This tool allows you to access websites that may be protected by anti-bot measures, geo-restrictions, or other access limitations using Bright Data's Web Unlocker service.\n",
+    "\n",
+    "The tool accepts various parameters during instantiation:\n",
+    "\n",
+    "- `bright_data_api_key` (required, str): Your Bright Data API key for authentication.\n",
+    "- `format` (optional, Literal[\"raw\"]): Format of the response content. Default is \"raw\".\n",
+    "- `country` (optional, str): Two-letter country code for geo-specific access (e.g., \"us\", \"gb\", \"de\", \"jp\"). Set this when you need to view the website as if accessing from a specific country. Default is None.\n",
+    "- `zone` (optional, str): Bright Data zone to use for the request. The \"unlocker\" zone is optimized for accessing websites that might block regular requests. Default is \"unlocker\".\n",
+    "- `data_format` (optional, Literal[\"html\", \"markdown\", \"screenshot\"]): Output format for the retrieved content. Options include:\n",
+    "    - \"html\" - Returns the standard HTML content (default)\n",
+    "    - \"markdown\" - Returns content converted to markdown format\n",
+    "    - \"screenshot\" - Returns a PNG screenshot of the rendered page"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Invocation"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Basic Usage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_brightdata import BrightDataUnlocker\n",
+    "\n",
+    "# Initialize the tool\n",
+    "unlocker_tool = BrightDataUnlocker(\n",
+    "    bright_data_api_key=\"your-api-key\"  # Optional if set in environment variables\n",
+    ")\n",
+    "\n",
+    "# Access a webpage\n",
+    "result = unlocker_tool.invoke(\"https://example.com\")\n",
+    "\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Advanced Usage with Parameters"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_brightdata import BrightDataUnlocker\n",
+    "\n",
+    "unlocker_tool = BrightDataUnlocker(\n",
+    "    bright_data_api_key=\"your-api-key\",\n",
+    ")\n",
+    "\n",
+    "# Access a webpage with specific parameters\n",
+    "result = unlocker_tool.invoke(\n",
+    "    {\n",
+    "        \"url\": \"https://example.com/region-restricted-content\",\n",
+    "        \"country\": \"gb\",  # Access as if from Great Britain\n",
+    "        \"data_format\": \"html\",  # Get content in markdown format\n",
+    "        \"zone\": \"unlocker\",  # Use the unlocker zone\n",
+    "    }\n",
+    ")\n",
+    "\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Customization Options"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The BrightDataUnlocker tool accepts several parameters for customization:\n",
+    "\n",
+    "|Parameter|Type|Description|\n",
+    "|:--|:--|:--|\n",
+    "|`url`|str|The URL to access|\n",
+    "|`format`|str|Format of the response content (default: \"raw\")|\n",
+    "|`country`|str|Two-letter country code for geo-specific access (e.g., \"us\", \"gb\")|\n",
+    "|`zone`|str|Bright Data zone to use (default: \"unlocker\")|\n",
+    "|`data_format`|str|Output format: None (HTML), \"markdown\", or \"screenshot\"|\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Data Format Options\n",
+    "\n",
+    "The `data_format` parameter allows you to specify how the content should be returned:\n",
+    "\n",
+    "- `None` or `\"html\"` (default): Returns the standard HTML content of the page\n",
+    "- `\"markdown\"`: Returns the content converted to markdown format, which is useful for feeding directly to LLMs\n",
+    "- `\"screenshot\"`: Returns a PNG screenshot of the rendered page, useful for visual analysis"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Use within an agent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_brightdata import BrightDataUnlocker\n",
+    "from langchain_google_genai import ChatGoogleGenerativeAI\n",
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "# Initialize the LLM\n",
+    "llm = ChatGoogleGenerativeAI(model=\"gemini-2.0-flash\", google_api_key=\"your-api-key\")\n",
+    "\n",
+    "# Initialize the tool\n",
+    "bright_data_tool = BrightDataUnlocker(bright_data_api_key=\"your-api-key\")\n",
+    "\n",
+    "# Create the agent\n",
+    "agent = create_react_agent(llm, [bright_data_tool])\n",
+    "\n",
+    "# Input URLs or prompt\n",
+    "user_input = \"Get the content from https://example.com/region-restricted-page - access it from GB\"\n",
+    "\n",
+    "# Stream the agent's output step by step\n",
+    "for step in agent.stream(\n",
+    "    {\"messages\": user_input},\n",
+    "    stream_mode=\"values\",\n",
+    "):\n",
+    "    step[\"messages\"][-1].pretty_print()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "- [Bright Data API Documentation](https://docs.brightdata.com/scraping-automation/web-unlocker/introduction)"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/integrations/tools/google_finance.ipynb

@@ -15,11 +15,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
    "source": [
-    "%pip install --upgrade --quiet  google-search-results langchain-community"
+    "%pip install --upgrade --quiet google-search-results langchain-community"
    ]
   },
   {
@@ -31,31 +39,39 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
     "import os\n",
     "\n",
-    "from langchain_community.tools.google_finance import GoogleFinanceQueryRun\n",
-    "from langchain_community.utilities.google_finance import GoogleFinanceAPIWrapper\n",
-    "\n",
-    "os.environ[\"SERPAPI_API_KEY\"] = \"[your serpapi key]\"\n",
-    "tool = GoogleFinanceQueryRun(api_wrapper=GoogleFinanceAPIWrapper())"
+    "os.environ[\"SERPAPI_API_KEY\"] = \"\""
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.tools.google_finance import GoogleFinanceQueryRun\n",
+    "from langchain_community.utilities.google_finance import GoogleFinanceAPIWrapper\n",
+    "\n",
+    "tool = GoogleFinanceQueryRun(api_wrapper=GoogleFinanceAPIWrapper())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'\\nQuery: Google\\nstock: GOOGL:NASDAQ\\nprice: $161.96\\npercentage: 1.68\\nmovement: Up\\n'"
+       "'\\nQuery: Google\\nstock: GOOGL:NASDAQ\\nprice: $159.96\\npercentage: 0.94\\nmovement: Up\\nus: price = 42210.57, movement = Down\\neurope: price = 23638.56, movement = Up\\nasia: price = 38183.26, movement = Up\\n'"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -73,9 +89,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
    "source": [
     "%pip install --upgrade --quiet langgraph langchain-openai"
    ]
@@ -89,7 +113,41 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
+    "os.environ[\"SERP_API_KEY\"] = \"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import init_chat_model\n",
+    "\n",
+    "llm = init_chat_model(\"gpt-4o-mini\", model_provider=\"openai\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.agent_toolkits.load_tools import load_tools\n",
+    "\n",
+    "tools = load_tools([\"google-scholar\", \"google-finance\"], llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -101,8 +159,8 @@
       "What is Google's stock?\n",
       "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
       "Tool Calls:\n",
-      "  google_finance (call_u676mJAkdojgkW806ZGSE8mF)\n",
-      " Call ID: call_u676mJAkdojgkW806ZGSE8mF\n",
+      "  google_finance (call_8m0txCtxNuQaAv9UlomPhSA1)\n",
+      " Call ID: call_8m0txCtxNuQaAv9UlomPhSA1\n",
       "  Args:\n",
       "    query: Google\n",
       "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
@@ -111,28 +169,22 @@
       "\n",
       "Query: Google\n",
       "stock: GOOGL:NASDAQ\n",
-      "price: $161.96\n",
-      "percentage: 1.68\n",
+      "price: $159.96\n",
+      "percentage: 0.94\n",
       "movement: Up\n",
+      "us: price = 42210.57, movement = Down\n",
+      "europe: price = 23638.56, movement = Up\n",
+      "asia: price = 38183.26, movement = Up\n",
       "\n",
       "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
       "\n",
-      "Google's stock (Ticker: GOOGL) is currently priced at $161.96, showing an increase of 1.68%.\n"
+      "Google's stock, listed as GOOGL on NASDAQ, is currently priced at $159.96, with a movement up by 0.94%.\n"
      ]
     }
    ],
    "source": [
-    "import os\n",
-    "\n",
-    "from langchain.agents import load_tools\n",
-    "from langchain.chat_models import init_chat_model\n",
     "from langgraph.prebuilt import create_react_agent\n",
     "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = \"[your openai key]\"\n",
-    "os.environ[\"SERP_API_KEY\"] = \"[your serpapi key]\"\n",
-    "\n",
-    "llm = init_chat_model(\"gpt-4o-mini\", model_provider=\"openai\")\n",
-    "tools = load_tools([\"google-scholar\", \"google-finance\"], llm=llm)\n",
     "agent = create_react_agent(llm, tools)\n",
     "\n",
     "events = agent.stream(\n",
@@ -142,11 +194,18 @@
     "for event in events:\n",
     "    event[\"messages\"][-1].pretty_print()"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "venv",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -160,9 +219,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.7"
+   "version": "3.12.4"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/docs/integrations/tools/graphql.ipynb

@@ -83,7 +83,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.agents import load_tools\n",
+    "from langchain_community.agent_toolkits.load_tools import load_tools\n",
     "\n",
     "tools = load_tools(\n",
     "    [\"graphql\"],\n",
@@ -223,7 +223,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.13.2"
+   "version": "3.12.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/tools/searchapi.ipynb

@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 1,
    "id": "70871a99-ffee-47d7-8e02-82eb99971f28",
    "metadata": {},
    "outputs": [],
@@ -51,7 +51,7 @@
     {
      "data": {
       "text/plain": [
-       "'Barack Hussein Obama II'"
+       "'Barack Obama Full name: Barack Hussein Obama II'"
       ]
      },
      "execution_count": 4,
@@ -73,7 +73,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 5,
    "id": "17a9b1ad-6e84-4949-8ebd-8c52f6b296e3",
    "metadata": {},
    "outputs": [],
@@ -83,48 +83,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "id": "cf8970a5-00e1-46bd-ba53-6a974eebbc10",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m Yes.\n",
-      "Follow up: How old was Plato when he died?\u001b[0m\n",
-      "Intermediate answer: \u001b[36;1m\u001b[1;3meighty\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mFollow up: How old was Socrates when he died?\u001b[0m\n",
-      "Intermediate answer: \u001b[36;1m\u001b[1;3m| Socrates | \n",
-      "| -------- | \n",
-      "| Born | c. 470 BC Deme Alopece, Athens | \n",
-      "| Died | 399 BC (aged approximately 71) Athens | \n",
-      "| Cause of death | Execution by forced suicide by poisoning | \n",
-      "| Spouse(s) | Xanthippe, Myrto | \n",
-      "\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mFollow up: How old was Aristotle when he died?\u001b[0m\n",
-      "Intermediate answer: \u001b[36;1m\u001b[1;3m62 years\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mSo the final answer is: Plato\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Plato'"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "from langchain.agents import AgentType, initialize_agent\n",
     "from langchain_community.utilities import SearchApiAPIWrapper\n",
     "from langchain_core.tools import Tool\n",
     "from langchain_openai import OpenAI\n",
@@ -133,16 +96,88 @@
     "search = SearchApiAPIWrapper()\n",
     "tools = [\n",
     "    Tool(\n",
-    "        name=\"Intermediate Answer\",\n",
+    "        name=\"intermediate_answer\",\n",
     "        func=search.run,\n",
     "        description=\"useful for when you need to ask with search\",\n",
     "    )\n",
-    "]\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "4198dda8-b7a9-4ae9-bcb6-b95e2c7681b9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langgraph.prebuilt import create_react_agent\n",
     "\n",
-    "self_ask_with_search = initialize_agent(\n",
-    "    tools, llm, agent=AgentType.SELF_ASK_WITH_SEARCH, verbose=True\n",
-    ")\n",
-    "self_ask_with_search.run(\"Who lived longer: Plato, Socrates, or Aristotle?\")"
+    "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "c24ad140-d41f-4e99-a42f-11371c3897b5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
+      "\n",
+      "Who lived longer: Plato, Socrates, or Aristotle?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "Tool Calls:\n",
+      "  intermediate_answer (call_Q0JquDV3SWfnn3rkwJkJaffG)\n",
+      " Call ID: call_Q0JquDV3SWfnn3rkwJkJaffG\n",
+      "  Args:\n",
+      "    __arg1: Lifespan of Plato\n",
+      "  intermediate_answer (call_j9rXzVlrCcGc8HOFnKUH6j5E)\n",
+      " Call ID: call_j9rXzVlrCcGc8HOFnKUH6j5E\n",
+      "  Args:\n",
+      "    __arg1: Lifespan of Socrates\n",
+      "  intermediate_answer (call_IBQT2qn5PzDE6q0ZyfPdhRaX)\n",
+      " Call ID: call_IBQT2qn5PzDE6q0ZyfPdhRaX\n",
+      "  Args:\n",
+      "    __arg1: Lifespan of Aristotle\n",
+      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
+      "Name: intermediate_answer\n",
+      "\n",
+      "384–322 BC was an Ancient Greek philosopher and polymath. His writings cover a broad range of subjects spanning the natural sciences, philosophy, linguistics, ...\n",
+      "The Greek philosopher Aristotle (384-322 B.C.) made significant and lasting contributions to nearly every aspect of human knowledge, ...\n",
+      "Aristotle's lifespan (384 - 322) (jan 1, 384 BC – jan 1, 322 BC). Added to timeline: Political Philosophy timeline. ByEdoardo. 25 Aug 2020.\n",
+      "Aristotle was one of the greatest philosophers and scientists the world has ever seen. He was born in 384 bc at Stagirus, a Greek seaport on the coast of Thrace ...\n",
+      "393–c. 370 bce), king of Macedonia and grandfather of Alexander the Great (reigned 336–323 bce). After his father's death in 367, Aristotle ...\n",
+      "It is difficult to rule out that possibility decisively, since little is known about the period of Aristotle's life from 341–335. He evidently ...\n",
+      "Lifespan: c. 384 B.C. to 322 B.C.; Contributions: Considered one of the greatest thinkers in various fields including politics, psychology, and ...\n",
+      "Aristotle (Greek: Ἀριστοτέλης Aristotélēs, pronounced [aristotélɛːs]) lived 384–322 BC.\n",
+      "Aristotle (384 B.C.E.—322 B.C.E.). Aristotle is a towering figure in ancient Greek philosophy, who made important contributions to logic, criticism, ...\n",
+      "Aristotle. Born: 384 BC in Stagirus, Macedonia, Greece Died: 322 BC in Chalcis, Euboea, Greece. Aristotle was not primarily a mathematician but made ...\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "\n",
+      "Based on the information:\n",
+      "\n",
+      "- Plato reportedly lived to be around eighty or eighty-one years old.\n",
+      "- Socrates' exact lifespan is not directly stated here, but he is known historically to have lived approximately from 470 BC to 399 BC, making him around 71 years old.\n",
+      "- Aristotle lived from 384 BC to 322 BC, which means he was about 62 years old.\n",
+      "\n",
+      "Therefore, Plato lived longer than both Socrates and Aristotle.\n"
+     ]
+    }
+   ],
+   "source": [
+    "input_message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": \"Who lived longer: Plato, Socrates, or Aristotle?\",\n",
+    "}\n",
+    "\n",
+    "for step in agent.stream(\n",
+    "    {\"messages\": [input_message]},\n",
+    "    stream_mode=\"values\",\n",
+    "):\n",
+    "    step[\"messages\"][-1].pretty_print()"
    ]
   },
   {
@@ -157,7 +192,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "6d0b4411-780a-4dcf-91b6-f3544e31e532",
    "metadata": {},
    "outputs": [],
@@ -167,17 +202,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "id": "34e79449-6b33-4b45-9306-7e3dab1b8599",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'Azure AI Engineer Be an XpanderCandidatar-meCandidatar-meCandidatar-me\\n\\nShare:\\n\\nAzure AI Engineer\\n\\nA área Digital Xperience da Xpand IT é uma equipa tecnológica de rápido crescimento que se concentra em tecnologias Microsoft e Mobile. A sua principal missão é fornecer soluções de software de alta qualidade que atendam às necessidades do utilizador final, num mundo tecnológico continuamente exigente e em ritmo acelerado, proporcionando a melhor experiência em termos de personalização, performance'"
+       "'No good search result found'"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -196,7 +231,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "id": "b16b7cd9-f0fe-4030-a36b-bbb52b19da18",
    "metadata": {},
    "outputs": [],
@@ -206,7 +241,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 12,
    "id": "e8adb325-2ad0-4a39-9bc2-d220ec3a29be",
    "metadata": {},
    "outputs": [
@@ -214,22 +249,22 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'search_metadata': {'id': 'search_qVdXG2jzvrlqTzayeYoaOb8A',\n",
+      "{'search_metadata': {'id': 'search_6Lpb2Z8vDqdsPRbrGkVgQzRy',\n",
       "                     'status': 'Success',\n",
-      "                     'created_at': '2023-09-25T15:22:30Z',\n",
-      "                     'request_time_taken': 3.21,\n",
-      "                     'parsing_time_taken': 0.03,\n",
-      "                     'total_time_taken': 3.24,\n",
+      "                     'created_at': '2025-05-11T03:39:28Z',\n",
+      "                     'request_time_taken': 0.86,\n",
+      "                     'parsing_time_taken': 0.01,\n",
+      "                     'total_time_taken': 0.87,\n",
       "                     'request_url': 'https://scholar.google.com/scholar?q=Large+Language+Models&hl=en',\n",
-      "                     'html_url': 'https://www.searchapi.io/api/v1/searches/search_qVdXG2jzvrlqTzayeYoaOb8A.html',\n",
-      "                     'json_url': 'https://www.searchapi.io/api/v1/searches/search_qVdXG2jzvrlqTzayeYoaOb8A'},\n",
+      "                     'html_url': 'https://www.searchapi.io/api/v1/searches/search_6Lpb2Z8vDqdsPRbrGkVgQzRy.html',\n",
+      "                     'json_url': 'https://www.searchapi.io/api/v1/searches/search_6Lpb2Z8vDqdsPRbrGkVgQzRy'},\n",
       " 'search_parameters': {'engine': 'google_scholar',\n",
       "                       'q': 'Large Language Models',\n",
       "                       'hl': 'en'},\n",
       " 'search_information': {'query_displayed': 'Large Language Models',\n",
-      "                        'total_results': 6420000,\n",
+      "                        'total_results': 6390000,\n",
       "                        'page': 1,\n",
-      "                        'time_taken_displayed': 0.06},\n",
+      "                        'time_taken_displayed': 0.08},\n",
       " 'organic_results': [{'position': 1,\n",
       "                      'title': 'ChatGPT for good? On opportunities and '\n",
       "                               'challenges of large language models for '\n",
@@ -245,15 +280,15 @@
       "                                 'we argue that large language models in '\n",
       "                                 'education require …',\n",
       "                      'inline_links': {'cited_by': {'cites_id': '8166055256995715258',\n",
-      "                                                    'total': 410,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cites=8166055256995715258&as_sdt=5,33&sciodt=0,33&hl=en'},\n",
+      "                                                    'total': 4675,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cites=8166055256995715258&as_sdt=2005&sciodt=0,5&hl=en'},\n",
       "                                       'versions': {'cluster_id': '8166055256995715258',\n",
-      "                                                    'total': 10,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cluster=8166055256995715258&hl=en&as_sdt=0,33'},\n",
-      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:uthwmf2nU3EJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,33'},\n",
-      "                      'resource': {'name': 'edarxiv.org',\n",
+      "                                                    'total': 16,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cluster=8166055256995715258&hl=en&as_sdt=0,5'},\n",
+      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:uthwmf2nU3EJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5'},\n",
+      "                      'resource': {'name': 'osf.io',\n",
       "                                   'format': 'PDF',\n",
-      "                                   'link': 'https://edarxiv.org/5er8f/download?format=pdf'},\n",
+      "                                   'link': 'https://osf.io/preprints/edarxiv/5er8f/download'},\n",
       "                      'authors': [{'name': 'E Kasneci',\n",
       "                                   'id': 'bZVkVvoAAAAJ',\n",
       "                                   'link': 'https://scholar.google.com/citations?user=bZVkVvoAAAAJ&hl=en&oi=sra'},\n",
@@ -267,6 +302,82 @@
       "                                   'id': 'TjfQ8QkAAAAJ',\n",
       "                                   'link': 'https://scholar.google.com/citations?user=TjfQ8QkAAAAJ&hl=en&oi=sra'}]},\n",
       "                     {'position': 2,\n",
+      "                      'title': 'A survey on evaluation of large language '\n",
+      "                               'models',\n",
+      "                      'data_cid': 'o93zfHYlUTIJ',\n",
+      "                      'link': 'https://dl.acm.org/doi/abs/10.1145/3641289',\n",
+      "                      'publication': 'Y Chang, X Wang, J Wang, Y Wu, L Yang… - '\n",
+      "                                     'ACM transactions on …, 2024 - dl.acm.org',\n",
+      "                      'snippet': '… 3.1 Natural Language Processing Tasks … '\n",
+      "                                 'the development of language models, '\n",
+      "                                 'particularly large language models, was to '\n",
+      "                                 'enhance performance on natural language '\n",
+      "                                 'processing tasks, …',\n",
+      "                      'inline_links': {'cited_by': {'cites_id': '3625720365842685347',\n",
+      "                                                    'total': 2864,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cites=3625720365842685347&as_sdt=2005&sciodt=0,5&hl=en'},\n",
+      "                                       'versions': {'cluster_id': '3625720365842685347',\n",
+      "                                                    'total': 8,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cluster=3625720365842685347&hl=en&as_sdt=0,5'},\n",
+      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:o93zfHYlUTIJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5'},\n",
+      "                      'resource': {'name': 'acm.org',\n",
+      "                                   'format': 'PDF',\n",
+      "                                   'link': 'https://dl.acm.org/doi/pdf/10.1145/3641289'},\n",
+      "                      'authors': [{'name': 'Y Chang',\n",
+      "                                   'id': 'Hw-lrpAAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=Hw-lrpAAAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'X Wang',\n",
+      "                                   'id': 'Q7Ieos8AAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=Q7Ieos8AAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'J Wang',\n",
+      "                                   'id': 'hBZ_tKsAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=hBZ_tKsAAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'Y Wu',\n",
+      "                                   'id': 'KVeRu2QAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=KVeRu2QAAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'L Yang',\n",
+      "                                   'id': 'go3sFxcAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=go3sFxcAAAAJ&hl=en&oi=sra'}]},\n",
+      "                     {'position': 3,\n",
+      "                      'title': 'A comprehensive overview of large language '\n",
+      "                               'models',\n",
+      "                      'data_cid': 'UDLkJGuOVl4J',\n",
+      "                      'link': 'https://arxiv.org/abs/2307.06435',\n",
+      "                      'publication': 'H Naveed, AU Khan, S Qiu, M Saqib, S '\n",
+      "                                     'Anwar… - arXiv preprint arXiv …, 2023 - '\n",
+      "                                     'arxiv.org',\n",
+      "                      'snippet': '… Large Language Models (LLMs) have recently '\n",
+      "                                 'demonstrated remarkable capabilities in '\n",
+      "                                 'natural language processing tasks and '\n",
+      "                                 'beyond. This success of LLMs has led to a '\n",
+      "                                 'large influx of …',\n",
+      "                      'inline_links': {'cited_by': {'cites_id': '6797777278393922128',\n",
+      "                                                    'total': 990,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cites=6797777278393922128&as_sdt=2005&sciodt=0,5&hl=en'},\n",
+      "                                       'versions': {'cluster_id': '6797777278393922128',\n",
+      "                                                    'total': 4,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cluster=6797777278393922128&hl=en&as_sdt=0,5'},\n",
+      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:UDLkJGuOVl4J:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5',\n",
+      "                                       'cached_page_link': 'https://scholar.googleusercontent.com/scholar?q=cache:UDLkJGuOVl4J:scholar.google.com/+Large+Language+Models&hl=en&as_sdt=0,5'},\n",
+      "                      'resource': {'name': 'arxiv.org',\n",
+      "                                   'format': 'PDF',\n",
+      "                                   'link': 'https://arxiv.org/pdf/2307.06435'},\n",
+      "                      'authors': [{'name': 'H Naveed',\n",
+      "                                   'id': 'k5dpooQAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=k5dpooQAAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'AU Khan',\n",
+      "                                   'id': 'sbOhz2UAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=sbOhz2UAAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'S Qiu',\n",
+      "                                   'id': 'OPNVthUAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=OPNVthUAAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'M Saqib',\n",
+      "                                   'id': 'KvbLR3gAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=KvbLR3gAAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'S Anwar',\n",
+      "                                   'id': 'vPJIHywAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=vPJIHywAAAAJ&hl=en&oi=sra'}]},\n",
+      "                     {'position': 4,\n",
       "                      'title': 'Large language models in medicine',\n",
       "                      'data_cid': 'Ph9AwHTmhzAJ',\n",
       "                      'link': 'https://www.nature.com/articles/s41591-023-02448-8',\n",
@@ -279,11 +390,15 @@
       "                                 '(LLaMA) as its backend model 30 . Finally, '\n",
       "                                 'cheap imitations of …',\n",
       "                      'inline_links': {'cited_by': {'cites_id': '3497017024792502078',\n",
-      "                                                    'total': 25,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cites=3497017024792502078&as_sdt=5,33&sciodt=0,33&hl=en'},\n",
+      "                                                    'total': 2474,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cites=3497017024792502078&as_sdt=2005&sciodt=0,5&hl=en'},\n",
       "                                       'versions': {'cluster_id': '3497017024792502078',\n",
-      "                                                    'total': 3,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cluster=3497017024792502078&hl=en&as_sdt=0,33'}},\n",
+      "                                                    'total': 7,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cluster=3497017024792502078&hl=en&as_sdt=0,5'},\n",
+      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:Ph9AwHTmhzAJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5'},\n",
+      "                      'resource': {'name': 'google.com',\n",
+      "                                   'format': 'PDF',\n",
+      "                                   'link': 'https://drive.google.com/file/d/1FKEGsSZ9GYOeToeKpxB4m3atGRbC-TSm/view'},\n",
       "                      'authors': [{'name': 'AJ Thirunavukarasu',\n",
       "                                   'id': '3qb1AYwAAAAJ',\n",
       "                                   'link': 'https://scholar.google.com/citations?user=3qb1AYwAAAAJ&hl=en&oi=sra'},\n",
@@ -293,43 +408,132 @@
       "                                  {'name': 'K Elangovan',\n",
       "                                   'id': 'BE_lVTQAAAAJ',\n",
       "                                   'link': 'https://scholar.google.com/citations?user=BE_lVTQAAAAJ&hl=en&oi=sra'}]},\n",
-      "                     {'position': 3,\n",
-      "                      'title': 'Extracting training data from large language '\n",
-      "                               'models',\n",
-      "                      'data_cid': 'mEYsWK6bWKoJ',\n",
-      "                      'link': 'https://www.usenix.org/conference/usenixsecurity21/presentation/carlini-extracting',\n",
-      "                      'publication': 'N Carlini, F Tramer, E Wallace, M '\n",
-      "                                     'Jagielski… - 30th USENIX Security …, '\n",
-      "                                     '2021 - usenix.org',\n",
-      "                      'snippet': '… language model trained on scrapes of the '\n",
-      "                                 'public Internet, and are able to extract '\n",
-      "                                 'hundreds of verbatim text sequences from the '\n",
-      "                                 'model’… models are more vulnerable than '\n",
-      "                                 'smaller models. …',\n",
-      "                      'inline_links': {'cited_by': {'cites_id': '12274731957504198296',\n",
-      "                                                    'total': 742,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cites=12274731957504198296&as_sdt=5,33&sciodt=0,33&hl=en'},\n",
-      "                                       'versions': {'cluster_id': '12274731957504198296',\n",
-      "                                                    'total': 8,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cluster=12274731957504198296&hl=en&as_sdt=0,33'},\n",
-      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:mEYsWK6bWKoJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,33',\n",
-      "                                       'cached_page_link': 'https://scholar.googleusercontent.com/scholar?q=cache:mEYsWK6bWKoJ:scholar.google.com/+Large+Language+Models&hl=en&as_sdt=0,33'},\n",
-      "                      'resource': {'name': 'usenix.org',\n",
+      "                     {'position': 5,\n",
+      "                      'title': 'A watermark for large language models',\n",
+      "                      'data_cid': 'BlSyLHT4iiEJ',\n",
+      "                      'link': 'https://proceedings.mlr.press/v202/kirchenbauer23a.html',\n",
+      "                      'publication': 'J Kirchenbauer, J Geiping, Y Wen… - '\n",
+      "                                     'International …, 2023 - '\n",
+      "                                     'proceedings.mlr.press',\n",
+      "                      'snippet': '… We propose a watermarking framework for '\n",
+      "                                 'proprietary language models. The … in the '\n",
+      "                                 'language model just before it produces a '\n",
+      "                                 'probability vector. The last layer of the '\n",
+      "                                 'language model …',\n",
+      "                      'inline_links': {'cited_by': {'cites_id': '2417017327887471622',\n",
+      "                                                    'total': 774,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cites=2417017327887471622&as_sdt=2005&sciodt=0,5&hl=en'},\n",
+      "                                       'versions': {'cluster_id': '2417017327887471622',\n",
+      "                                                    'total': 13,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cluster=2417017327887471622&hl=en&as_sdt=0,5'},\n",
+      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:BlSyLHT4iiEJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5',\n",
+      "                                       'cached_page_link': 'https://scholar.googleusercontent.com/scholar?q=cache:BlSyLHT4iiEJ:scholar.google.com/+Large+Language+Models&hl=en&as_sdt=0,5'},\n",
+      "                      'resource': {'name': 'mlr.press',\n",
       "                                   'format': 'PDF',\n",
-      "                                   'link': 'https://www.usenix.org/system/files/sec21-carlini-extracting.pdf'},\n",
-      "                      'authors': [{'name': 'N Carlini',\n",
-      "                                   'id': 'q4qDvAoAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=q4qDvAoAAAAJ&hl=en&oi=sra'},\n",
-      "                                  {'name': 'F Tramer',\n",
-      "                                   'id': 'ijH0-a8AAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=ijH0-a8AAAAJ&hl=en&oi=sra'},\n",
-      "                                  {'name': 'E Wallace',\n",
-      "                                   'id': 'SgST3LkAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=SgST3LkAAAAJ&hl=en&oi=sra'},\n",
-      "                                  {'name': 'M Jagielski',\n",
-      "                                   'id': '_8rw_GMAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=_8rw_GMAAAAJ&hl=en&oi=sra'}]},\n",
-      "                     {'position': 4,\n",
+      "                                   'link': 'https://proceedings.mlr.press/v202/kirchenbauer23a/kirchenbauer23a.pdf'},\n",
+      "                      'authors': [{'name': 'J Kirchenbauer',\n",
+      "                                   'id': '48GJrbsAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=48GJrbsAAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'J Geiping',\n",
+      "                                   'id': '206vNCEAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=206vNCEAAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'Y Wen',\n",
+      "                                   'id': 'oUYfjg0AAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=oUYfjg0AAAAJ&hl=en&oi=sra'}]},\n",
+      "                     {'position': 6,\n",
+      "                      'title': 'Welcome to the era of chatgpt et al. the '\n",
+      "                               'prospects of large language models',\n",
+      "                      'data_cid': '3UrgC1BmpV8J',\n",
+      "                      'link': 'https://link.springer.com/article/10.1007/s12599-023-00795-x',\n",
+      "                      'publication': 'T Teubner, CM Flath, C Weinhardt… - '\n",
+      "                                     'Business & Information …, 2023 - '\n",
+      "                                     'Springer',\n",
+      "                      'snippet': 'The emergence of Large Language Models '\n",
+      "                                 '(LLMs) in combination with easy-to-use '\n",
+      "                                 'interfaces such as ChatGPT, Bing Chat, and '\n",
+      "                                 'Google’s Bard represent both a Herculean '\n",
+      "                                 'task and a …',\n",
+      "                      'inline_links': {'cited_by': {'cites_id': '6892027298743077597',\n",
+      "                                                    'total': 409,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cites=6892027298743077597&as_sdt=2005&sciodt=0,5&hl=en'},\n",
+      "                                       'versions': {'cluster_id': '6892027298743077597',\n",
+      "                                                    'total': 16,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cluster=6892027298743077597&hl=en&as_sdt=0,5'},\n",
+      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:3UrgC1BmpV8J:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5'},\n",
+      "                      'resource': {'name': 'springer.com',\n",
+      "                                   'format': 'PDF',\n",
+      "                                   'link': 'https://link.springer.com/content/pdf/10.1007/s12599-023-00795-x.pdf'},\n",
+      "                      'authors': [{'name': 'T Teubner',\n",
+      "                                   'id': 'ZeCM1k8AAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=ZeCM1k8AAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'CM Flath',\n",
+      "                                   'id': '5Iy85HsAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=5Iy85HsAAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'C Weinhardt',\n",
+      "                                   'id': 'lhfZxjAAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=lhfZxjAAAAAJ&hl=en&oi=sra'}]},\n",
+      "                     {'position': 7,\n",
+      "                      'title': 'Talking about large language models',\n",
+      "                      'data_cid': '3eYYI745r_0J',\n",
+      "                      'link': 'https://dl.acm.org/doi/abs/10.1145/3624724',\n",
+      "                      'publication': 'M Shanahan - Communications of the ACM, '\n",
+      "                                     '2024 - dl.acm.org',\n",
+      "                      'snippet': '… Recently, it has become commonplace to use '\n",
+      "                                 'the term “large language model” both for the '\n",
+      "                                 'generative models themselves and for the '\n",
+      "                                 'systems in which they are embedded, '\n",
+      "                                 'especially in …',\n",
+      "                      'inline_links': {'cited_by': {'cites_id': '18279892901315536605',\n",
+      "                                                    'total': 477,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cites=18279892901315536605&as_sdt=2005&sciodt=0,5&hl=en'},\n",
+      "                                       'versions': {'cluster_id': '18279892901315536605',\n",
+      "                                                    'total': 4,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cluster=18279892901315536605&hl=en&as_sdt=0,5'},\n",
+      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:3eYYI745r_0J:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5'},\n",
+      "                      'resource': {'name': 'acm.org',\n",
+      "                                   'format': 'PDF',\n",
+      "                                   'link': 'https://dl.acm.org/doi/pdf/10.1145/3624724'},\n",
+      "                      'authors': [{'name': 'M Shanahan',\n",
+      "                                   'id': '00bnGpAAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=00bnGpAAAAAJ&hl=en&oi=sra'}]},\n",
+      "                     {'position': 8,\n",
+      "                      'title': 'Explainability for large language models: A '\n",
+      "                               'survey',\n",
+      "                      'data_cid': '0AqRKEINMw4J',\n",
+      "                      'link': 'https://dl.acm.org/doi/abs/10.1145/3639372',\n",
+      "                      'publication': 'H Zhao, H Chen, F Yang, N Liu, H Deng, H '\n",
+      "                                     'Cai… - ACM Transactions on …, 2024 - '\n",
+      "                                     'dl.acm.org',\n",
+      "                      'snippet': '… Let us consider a scenario where we have a '\n",
+      "                                 'language model and we input a specific text '\n",
+      "                                 'into the model. The model then produces a '\n",
+      "                                 'classification output, such as sentiment …',\n",
+      "                      'inline_links': {'cited_by': {'cites_id': '1023176118142831312',\n",
+      "                                                    'total': 576,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cites=1023176118142831312&as_sdt=2005&sciodt=0,5&hl=en'},\n",
+      "                                       'versions': {'cluster_id': '1023176118142831312',\n",
+      "                                                    'total': 7,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cluster=1023176118142831312&hl=en&as_sdt=0,5'},\n",
+      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:0AqRKEINMw4J:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5'},\n",
+      "                      'resource': {'name': 'acm.org',\n",
+      "                                   'format': 'PDF',\n",
+      "                                   'link': 'https://dl.acm.org/doi/pdf/10.1145/3639372'},\n",
+      "                      'authors': [{'name': 'H Zhao',\n",
+      "                                   'id': '9FobigIAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=9FobigIAAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'H Chen',\n",
+      "                                   'id': 'DyYOgLwAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=DyYOgLwAAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'F Yang',\n",
+      "                                   'id': 'RXFeW-8AAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=RXFeW-8AAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'N Liu',\n",
+      "                                   'id': 'Nir-EDYAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=Nir-EDYAAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'H Cai',\n",
+      "                                   'id': 'Kz-r34UAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=Kz-r34UAAAAJ&hl=en&oi=sra'}]},\n",
+      "                     {'position': 9,\n",
       "                      'title': 'Emergent abilities of large language models',\n",
       "                      'data_cid': 'hG0iVOrOguoJ',\n",
       "                      'link': 'https://arxiv.org/abs/2206.07682',\n",
@@ -341,16 +545,16 @@
       "                                 'efficiency on a wide range of downstream '\n",
       "                                 'tasks. This paper instead discusses an …',\n",
       "                      'inline_links': {'cited_by': {'cites_id': '16898296257676733828',\n",
-      "                                                    'total': 621,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cites=16898296257676733828&as_sdt=5,33&sciodt=0,33&hl=en'},\n",
+      "                                                    'total': 3436,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cites=16898296257676733828&as_sdt=2005&sciodt=0,5&hl=en'},\n",
       "                                       'versions': {'cluster_id': '16898296257676733828',\n",
-      "                                                    'total': 12,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cluster=16898296257676733828&hl=en&as_sdt=0,33'},\n",
-      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:hG0iVOrOguoJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,33',\n",
-      "                                       'cached_page_link': 'https://scholar.googleusercontent.com/scholar?q=cache:hG0iVOrOguoJ:scholar.google.com/+Large+Language+Models&hl=en&as_sdt=0,33'},\n",
+      "                                                    'total': 11,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cluster=16898296257676733828&hl=en&as_sdt=0,5'},\n",
+      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:hG0iVOrOguoJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5',\n",
+      "                                       'cached_page_link': 'https://scholar.googleusercontent.com/scholar?q=cache:hG0iVOrOguoJ:scholar.google.com/+Large+Language+Models&hl=en&as_sdt=0,5'},\n",
       "                      'resource': {'name': 'arxiv.org',\n",
       "                                   'format': 'PDF',\n",
-      "                                   'link': 'https://arxiv.org/pdf/2206.07682.pdf?trk=cndc-detail'},\n",
+      "                                   'link': 'https://arxiv.org/pdf/2206.07682'},\n",
       "                      'authors': [{'name': 'J Wei',\n",
       "                                   'id': 'wA5TK_0AAAAJ',\n",
       "                                   'link': 'https://scholar.google.com/citations?user=wA5TK_0AAAAJ&hl=en&oi=sra'},\n",
@@ -362,232 +566,78 @@
       "                                   'link': 'https://scholar.google.com/citations?user=WMBXw1EAAAAJ&hl=en&oi=sra'},\n",
       "                                  {'name': 'C Raffel',\n",
       "                                   'id': 'I66ZBYwAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=I66ZBYwAAAAJ&hl=en&oi=sra'},\n",
-      "                                  {'name': 'B Zoph',\n",
-      "                                   'id': 'NL_7iTwAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=NL_7iTwAAAAJ&hl=en&oi=sra'}]},\n",
-      "                     {'position': 5,\n",
-      "                      'title': 'A survey on evaluation of large language '\n",
-      "                               'models',\n",
-      "                      'data_cid': 'ZYohnzOz-XgJ',\n",
-      "                      'link': 'https://arxiv.org/abs/2307.03109',\n",
-      "                      'publication': 'Y Chang, X Wang, J Wang, Y Wu, K Zhu… - '\n",
-      "                                     'arXiv preprint arXiv …, 2023 - arxiv.org',\n",
-      "                      'snippet': '… 3.1 Natural Language Processing Tasks … '\n",
-      "                                 'the development of language models, '\n",
-      "                                 'particularly large language models, was to '\n",
-      "                                 'enhance performance on natural language '\n",
-      "                                 'processing tasks, …',\n",
-      "                      'inline_links': {'cited_by': {'cites_id': '8717195588046785125',\n",
-      "                                                    'total': 31,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cites=8717195588046785125&as_sdt=5,33&sciodt=0,33&hl=en'},\n",
-      "                                       'versions': {'cluster_id': '8717195588046785125',\n",
-      "                                                    'total': 3,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cluster=8717195588046785125&hl=en&as_sdt=0,33'},\n",
-      "                                       'cached_page_link': 'https://scholar.googleusercontent.com/scholar?q=cache:ZYohnzOz-XgJ:scholar.google.com/+Large+Language+Models&hl=en&as_sdt=0,33'},\n",
-      "                      'resource': {'name': 'arxiv.org',\n",
-      "                                   'format': 'PDF',\n",
-      "                                   'link': 'https://arxiv.org/pdf/2307.03109'},\n",
-      "                      'authors': [{'name': 'X Wang',\n",
-      "                                   'id': 'Q7Ieos8AAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=Q7Ieos8AAAAJ&hl=en&oi=sra'},\n",
-      "                                  {'name': 'J Wang',\n",
-      "                                   'id': 'YomxTXQAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=YomxTXQAAAAJ&hl=en&oi=sra'},\n",
-      "                                  {'name': 'Y Wu',\n",
-      "                                   'id': 'KVeRu2QAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=KVeRu2QAAAAJ&hl=en&oi=sra'},\n",
-      "                                  {'name': 'K Zhu',\n",
-      "                                   'id': 'g75dFLYAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=g75dFLYAAAAJ&hl=en&oi=sra'}]},\n",
-      "                     {'position': 6,\n",
-      "                      'title': 'Evaluating large language models trained on '\n",
-      "                               'code',\n",
-      "                      'data_cid': '3tNvW3l5nU4J',\n",
-      "                      'link': 'https://arxiv.org/abs/2107.03374',\n",
-      "                      'publication': 'M Chen, J Tworek, H Jun, Q Yuan, HPO '\n",
-      "                                     'Pinto… - arXiv preprint arXiv …, 2021 - '\n",
-      "                                     'arxiv.org',\n",
-      "                      'snippet': '… We introduce Codex, a GPT language model '\n",
-      "                                 'finetuned on publicly available code from '\n",
-      "                                 'GitHub, and study its Python code-writing '\n",
-      "                                 'capabilities. A distinct production version '\n",
-      "                                 'of Codex …',\n",
-      "                      'inline_links': {'cited_by': {'cites_id': '5664817468434011102',\n",
-      "                                                    'total': 941,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cites=5664817468434011102&as_sdt=5,33&sciodt=0,33&hl=en'},\n",
-      "                                       'versions': {'cluster_id': '5664817468434011102',\n",
-      "                                                    'total': 2,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cluster=5664817468434011102&hl=en&as_sdt=0,33'},\n",
-      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:3tNvW3l5nU4J:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,33',\n",
-      "                                       'cached_page_link': 'https://scholar.googleusercontent.com/scholar?q=cache:3tNvW3l5nU4J:scholar.google.com/+Large+Language+Models&hl=en&as_sdt=0,33'},\n",
-      "                      'resource': {'name': 'arxiv.org',\n",
-      "                                   'format': 'PDF',\n",
-      "                                   'link': 'https://arxiv.org/pdf/2107.03374.pdf?trk=public_post_comment-text'},\n",
-      "                      'authors': [{'name': 'M Chen',\n",
-      "                                   'id': '5fU-QMwAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=5fU-QMwAAAAJ&hl=en&oi=sra'},\n",
-      "                                  {'name': 'J Tworek',\n",
-      "                                   'id': 'ZPuESCQAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=ZPuESCQAAAAJ&hl=en&oi=sra'},\n",
-      "                                  {'name': 'Q Yuan',\n",
-      "                                   'id': 'B059m2EAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=B059m2EAAAAJ&hl=en&oi=sra'}]},\n",
-      "                     {'position': 7,\n",
-      "                      'title': 'Large language models in machine translation',\n",
-      "                      'data_cid': 'sY5m_Y3-0Y4J',\n",
-      "                      'link': 'http://research.google/pubs/pub33278.pdf',\n",
-      "                      'publication': 'T Brants, AC Popat, P Xu, FJ Och, J Dean '\n",
-      "                                     '- 2007 - research.google',\n",
-      "                      'snippet': '… the benefits of largescale statistical '\n",
-      "                                 'language modeling in ma… trillion tokens, '\n",
-      "                                 'resulting in language models having up to '\n",
-      "                                 '300 … is inexpensive to train on large data '\n",
-      "                                 'sets and approaches the …',\n",
-      "                      'type': 'PDF',\n",
-      "                      'inline_links': {'cited_by': {'cites_id': '10291286509313494705',\n",
-      "                                                    'total': 737,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cites=10291286509313494705&as_sdt=5,33&sciodt=0,33&hl=en'},\n",
-      "                                       'versions': {'cluster_id': '10291286509313494705',\n",
-      "                                                    'total': 31,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cluster=10291286509313494705&hl=en&as_sdt=0,33'},\n",
-      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:sY5m_Y3-0Y4J:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,33',\n",
-      "                                       'cached_page_link': 'https://scholar.googleusercontent.com/scholar?q=cache:sY5m_Y3-0Y4J:scholar.google.com/+Large+Language+Models&hl=en&as_sdt=0,33'},\n",
-      "                      'resource': {'name': 'research.google',\n",
-      "                                   'format': 'PDF',\n",
-      "                                   'link': 'http://research.google/pubs/pub33278.pdf'},\n",
-      "                      'authors': [{'name': 'FJ Och',\n",
-      "                                   'id': 'ITGdg6oAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=ITGdg6oAAAAJ&hl=en&oi=sra'},\n",
-      "                                  {'name': 'J Dean',\n",
-      "                                   'id': 'NMS69lQAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=NMS69lQAAAAJ&hl=en&oi=sra'}]},\n",
-      "                     {'position': 8,\n",
-      "                      'title': 'A watermark for large language models',\n",
-      "                      'data_cid': 'BlSyLHT4iiEJ',\n",
-      "                      'link': 'https://arxiv.org/abs/2301.10226',\n",
-      "                      'publication': 'J Kirchenbauer, J Geiping, Y Wen, J '\n",
-      "                                     'Katz… - arXiv preprint arXiv …, 2023 - '\n",
-      "                                     'arxiv.org',\n",
-      "                      'snippet': '… To derive this watermark, we examine what '\n",
-      "                                 'happens in the language model just before it '\n",
-      "                                 'produces a probability vector. The last '\n",
-      "                                 'layer of the language model outputs a vector '\n",
-      "                                 'of logits l(t). …',\n",
-      "                      'inline_links': {'cited_by': {'cites_id': '2417017327887471622',\n",
-      "                                                    'total': 104,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cites=2417017327887471622&as_sdt=5,33&sciodt=0,33&hl=en'},\n",
-      "                                       'versions': {'cluster_id': '2417017327887471622',\n",
-      "                                                    'total': 4,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cluster=2417017327887471622&hl=en&as_sdt=0,33'},\n",
-      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:BlSyLHT4iiEJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,33',\n",
-      "                                       'cached_page_link': 'https://scholar.googleusercontent.com/scholar?q=cache:BlSyLHT4iiEJ:scholar.google.com/+Large+Language+Models&hl=en&as_sdt=0,33'},\n",
-      "                      'resource': {'name': 'arxiv.org',\n",
-      "                                   'format': 'PDF',\n",
-      "                                   'link': 'https://arxiv.org/pdf/2301.10226.pdf?curius=1419'},\n",
-      "                      'authors': [{'name': 'J Kirchenbauer',\n",
-      "                                   'id': '48GJrbsAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=48GJrbsAAAAJ&hl=en&oi=sra'},\n",
-      "                                  {'name': 'J Geiping',\n",
-      "                                   'id': '206vNCEAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=206vNCEAAAAJ&hl=en&oi=sra'},\n",
-      "                                  {'name': 'Y Wen',\n",
-      "                                   'id': 'oUYfjg0AAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=oUYfjg0AAAAJ&hl=en&oi=sra'},\n",
-      "                                  {'name': 'J Katz',\n",
-      "                                   'id': 'yPw4WjoAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=yPw4WjoAAAAJ&hl=en&oi=sra'}]},\n",
-      "                     {'position': 9,\n",
-      "                      'title': 'ChatGPT and other large language models are '\n",
-      "                               'double-edged swords',\n",
-      "                      'data_cid': 'So0q8TRvxhYJ',\n",
-      "                      'link': 'https://pubs.rsna.org/doi/full/10.1148/radiol.230163',\n",
-      "                      'publication': 'Y Shen, L Heacock, J Elias, KD Hentel, B '\n",
-      "                                     'Reig, G Shih… - Radiology, 2023 - '\n",
-      "                                     'pubs.rsna.org',\n",
-      "                      'snippet': '… Large Language Models (LLMs) are deep '\n",
-      "                                 'learning models trained to understand and '\n",
-      "                                 'generate natural language. Recent studies '\n",
-      "                                 'demonstrated that LLMs achieve great success '\n",
-      "                                 'in a …',\n",
-      "                      'inline_links': {'cited_by': {'cites_id': '1641121387398204746',\n",
-      "                                                    'total': 231,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cites=1641121387398204746&as_sdt=5,33&sciodt=0,33&hl=en'},\n",
-      "                                       'versions': {'cluster_id': '1641121387398204746',\n",
-      "                                                    'total': 3,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cluster=1641121387398204746&hl=en&as_sdt=0,33'},\n",
-      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:So0q8TRvxhYJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,33'},\n",
-      "                      'authors': [{'name': 'Y Shen',\n",
-      "                                   'id': 'XaeN2zgAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=XaeN2zgAAAAJ&hl=en&oi=sra'},\n",
-      "                                  {'name': 'L Heacock',\n",
-      "                                   'id': 'tYYM5IkAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=tYYM5IkAAAAJ&hl=en&oi=sra'}]},\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=I66ZBYwAAAAJ&hl=en&oi=sra'}]},\n",
       "                     {'position': 10,\n",
-      "                      'title': 'Pythia: A suite for analyzing large language '\n",
-      "                               'models across training and scaling',\n",
-      "                      'data_cid': 'aaIDvsMAD8QJ',\n",
-      "                      'link': 'https://proceedings.mlr.press/v202/biderman23a.html',\n",
-      "                      'publication': 'S Biderman, H Schoelkopf… - '\n",
-      "                                     'International …, 2023 - '\n",
-      "                                     'proceedings.mlr.press',\n",
-      "                      'snippet': '… large language models, we prioritize '\n",
-      "                                 'consistency in model … out the most '\n",
-      "                                 'performance from each model. For example, we '\n",
-      "                                 '… models, as it is becoming widely used for '\n",
-      "                                 'the largest models, …',\n",
-      "                      'inline_links': {'cited_by': {'cites_id': '14127511396791067241',\n",
-      "                                                    'total': 89,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cites=14127511396791067241&as_sdt=5,33&sciodt=0,33&hl=en'},\n",
-      "                                       'versions': {'cluster_id': '14127511396791067241',\n",
-      "                                                    'total': 3,\n",
-      "                                                    'link': 'https://scholar.google.com/scholar?cluster=14127511396791067241&hl=en&as_sdt=0,33'},\n",
-      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:aaIDvsMAD8QJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,33',\n",
-      "                                       'cached_page_link': 'https://scholar.googleusercontent.com/scholar?q=cache:aaIDvsMAD8QJ:scholar.google.com/+Large+Language+Models&hl=en&as_sdt=0,33'},\n",
-      "                      'resource': {'name': 'mlr.press',\n",
+      "                      'title': 'A systematic evaluation of large language '\n",
+      "                               'models of code',\n",
+      "                      'data_cid': '-iQSW0h72hYJ',\n",
+      "                      'link': 'https://dl.acm.org/doi/abs/10.1145/3520312.3534862',\n",
+      "                      'publication': 'FF Xu, U Alon, G Neubig, VJ Hellendoorn '\n",
+      "                                     '- Proceedings of the 6th ACM …, 2022 - '\n",
+      "                                     'dl.acm.org',\n",
+      "                      'snippet': '… largest language models for code. We also '\n",
+      "                                 'release PolyCoder, a large open-source '\n",
+      "                                 'language model for code, trained exclusively '\n",
+      "                                 'on code in 12 different programming '\n",
+      "                                 'languages. In the …',\n",
+      "                      'inline_links': {'cited_by': {'cites_id': '1646764164453115130',\n",
+      "                                                    'total': 764,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cites=1646764164453115130&as_sdt=2005&sciodt=0,5&hl=en'},\n",
+      "                                       'versions': {'cluster_id': '1646764164453115130',\n",
+      "                                                    'total': 6,\n",
+      "                                                    'link': 'https://scholar.google.com/scholar?cluster=1646764164453115130&hl=en&as_sdt=0,5'},\n",
+      "                                       'related_articles_link': 'https://scholar.google.com/scholar?q=related:-iQSW0h72hYJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5'},\n",
+      "                      'resource': {'name': 'acm.org',\n",
       "                                   'format': 'PDF',\n",
-      "                                   'link': 'https://proceedings.mlr.press/v202/biderman23a/biderman23a.pdf'},\n",
-      "                      'authors': [{'name': 'S Biderman',\n",
-      "                                   'id': 'bO7H0DAAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=bO7H0DAAAAAJ&hl=en&oi=sra'},\n",
-      "                                  {'name': 'H Schoelkopf',\n",
-      "                                   'id': 'XLahYIYAAAAJ',\n",
-      "                                   'link': 'https://scholar.google.com/citations?user=XLahYIYAAAAJ&hl=en&oi=sra'}]}],\n",
-      " 'related_searches': [{'query': 'large language models machine',\n",
-      "                       'highlighted': ['machine'],\n",
-      "                       'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,33&qsp=1&q=large+language+models+machine&qst=ib'},\n",
-      "                      {'query': 'large language models pruning',\n",
-      "                       'highlighted': ['pruning'],\n",
-      "                       'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,33&qsp=2&q=large+language+models+pruning&qst=ib'},\n",
-      "                      {'query': 'large language models multitask learners',\n",
-      "                       'highlighted': ['multitask learners'],\n",
-      "                       'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,33&qsp=3&q=large+language+models+multitask+learners&qst=ib'},\n",
-      "                      {'query': 'large language models speech recognition',\n",
-      "                       'highlighted': ['speech recognition'],\n",
-      "                       'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,33&qsp=4&q=large+language+models+speech+recognition&qst=ib'},\n",
+      "                                   'link': 'https://dl.acm.org/doi/pdf/10.1145/3520312.3534862'},\n",
+      "                      'authors': [{'name': 'FF Xu',\n",
+      "                                   'id': '1hXyfIkAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=1hXyfIkAAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'U Alon',\n",
+      "                                   'id': 'QBn7vq8AAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=QBn7vq8AAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'G Neubig',\n",
+      "                                   'id': 'wlosgkoAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=wlosgkoAAAAJ&hl=en&oi=sra'},\n",
+      "                                  {'name': 'VJ Hellendoorn',\n",
+      "                                   'id': 'PfYrc5kAAAAJ',\n",
+      "                                   'link': 'https://scholar.google.com/citations?user=PfYrc5kAAAAJ&hl=en&oi=sra'}]}],\n",
+      " 'related_searches': [{'query': 'emergent large language models',\n",
+      "                       'highlighted': ['emergent'],\n",
+      "                       'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=1&q=emergent+large+language+models&qst=ib'},\n",
+      "                      {'query': 'large language models abilities',\n",
+      "                       'highlighted': ['abilities'],\n",
+      "                       'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=2&q=large+language+models+abilities&qst=ib'},\n",
+      "                      {'query': 'prompt large language models',\n",
+      "                       'highlighted': ['prompt'],\n",
+      "                       'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=3&q=prompt+large+language+models&qst=ib'},\n",
+      "                      {'query': 'large language models training '\n",
+      "                                'compute-optimal',\n",
+      "                       'highlighted': ['training compute-optimal'],\n",
+      "                       'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=4&q=large+language+models+training+compute-optimal&qst=ib'},\n",
       "                      {'query': 'large language models machine translation',\n",
       "                       'highlighted': ['machine translation'],\n",
-      "                       'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,33&qsp=5&q=large+language+models+machine+translation&qst=ib'},\n",
-      "                      {'query': 'emergent abilities of large language models',\n",
-      "                       'highlighted': ['emergent abilities of'],\n",
-      "                       'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,33&qsp=6&q=emergent+abilities+of+large+language+models&qst=ir'},\n",
-      "                      {'query': 'language models privacy risks',\n",
-      "                       'highlighted': ['privacy risks'],\n",
-      "                       'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,33&qsp=7&q=language+models+privacy+risks&qst=ir'},\n",
-      "                      {'query': 'language model fine tuning',\n",
+      "                       'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=5&q=large+language+models+machine+translation&qst=ib'},\n",
+      "                      {'query': 'large language models zero shot',\n",
+      "                       'highlighted': ['zero shot'],\n",
+      "                       'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=6&q=large+language+models+zero+shot&qst=ib'},\n",
+      "                      {'query': 'large language models chatgpt',\n",
+      "                       'highlighted': ['chatgpt'],\n",
+      "                       'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=7&q=large+language+models+chatgpt&qst=ib'},\n",
+      "                      {'query': 'fine tuning large language models',\n",
       "                       'highlighted': ['fine tuning'],\n",
-      "                       'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,33&qsp=8&q=language+model+fine+tuning&qst=ir'}],\n",
+      "                       'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=8&q=fine+tuning+large+language+models&qst=ib'}],\n",
       " 'pagination': {'current': 1,\n",
-      "                'next': 'https://scholar.google.com/scholar?start=10&q=Large+Language+Models&hl=en&as_sdt=0,33',\n",
-      "                'other_pages': {'2': 'https://scholar.google.com/scholar?start=10&q=Large+Language+Models&hl=en&as_sdt=0,33',\n",
-      "                                '3': 'https://scholar.google.com/scholar?start=20&q=Large+Language+Models&hl=en&as_sdt=0,33',\n",
-      "                                '4': 'https://scholar.google.com/scholar?start=30&q=Large+Language+Models&hl=en&as_sdt=0,33',\n",
-      "                                '5': 'https://scholar.google.com/scholar?start=40&q=Large+Language+Models&hl=en&as_sdt=0,33',\n",
-      "                                '6': 'https://scholar.google.com/scholar?start=50&q=Large+Language+Models&hl=en&as_sdt=0,33',\n",
-      "                                '7': 'https://scholar.google.com/scholar?start=60&q=Large+Language+Models&hl=en&as_sdt=0,33',\n",
-      "                                '8': 'https://scholar.google.com/scholar?start=70&q=Large+Language+Models&hl=en&as_sdt=0,33',\n",
-      "                                '9': 'https://scholar.google.com/scholar?start=80&q=Large+Language+Models&hl=en&as_sdt=0,33',\n",
-      "                                '10': 'https://scholar.google.com/scholar?start=90&q=Large+Language+Models&hl=en&as_sdt=0,33'}}}\n"
+      "                'next': 'https://scholar.google.com/scholar?start=10&q=Large+Language+Models&hl=en&as_sdt=0,5',\n",
+      "                'other_pages': {'2': 'https://scholar.google.com/scholar?start=10&q=Large+Language+Models&hl=en&as_sdt=0,5',\n",
+      "                                '3': 'https://scholar.google.com/scholar?start=20&q=Large+Language+Models&hl=en&as_sdt=0,5',\n",
+      "                                '4': 'https://scholar.google.com/scholar?start=30&q=Large+Language+Models&hl=en&as_sdt=0,5',\n",
+      "                                '5': 'https://scholar.google.com/scholar?start=40&q=Large+Language+Models&hl=en&as_sdt=0,5',\n",
+      "                                '6': 'https://scholar.google.com/scholar?start=50&q=Large+Language+Models&hl=en&as_sdt=0,5',\n",
+      "                                '7': 'https://scholar.google.com/scholar?start=60&q=Large+Language+Models&hl=en&as_sdt=0,5',\n",
+      "                                '8': 'https://scholar.google.com/scholar?start=70&q=Large+Language+Models&hl=en&as_sdt=0,5',\n",
+      "                                '9': 'https://scholar.google.com/scholar?start=80&q=Large+Language+Models&hl=en&as_sdt=0,5',\n",
+      "                                '10': 'https://scholar.google.com/scholar?start=90&q=Large+Language+Models&hl=en&as_sdt=0,5'}}}\n"
      ]
     }
    ],
@@ -596,6 +646,14 @@
     "results = search.results(\"Large Language Models\")\n",
     "pprint.pp(results)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "11ab5938-e298-471d-96fc-50405ffad35c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -614,7 +672,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.12.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/vectorstores/aerospike.ipynb

@@ -11,8 +11,8 @@
     "datasets stored in Aerospike. This new service lives outside of Aerospike and\n",
     "builds an index to perform those searches.\n",
     "\n",
-    "This notebook showcases the functionality of the LangChain Aerospike VectorStore\n",
-    "integration.\n",
+    "This notebook showcases the functionality of the [LangChain Aerospike VectorStore\n",
+    "integration](https://github.com/aerospike/langchain-aerospike).\n",
     "\n",
     "## Install AVS\n",
     "\n",
@@ -25,11 +25,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
-    "AVS_HOST = \"<avs-ip>\"\n",
+    "AVS_HOST = \"<avs_ip>\"\n",
     "AVS_PORT = 5000"
    ]
   },
@@ -43,15 +43,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 5,
    "metadata": {
     "vscode": {
      "languageId": "shellscript"
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m25.0.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m25.1.1\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
+     ]
+    }
+   ],
    "source": [
-    "!pip install --upgrade --quiet aerospike-vector-search==3.0.1 langchain-community sentence-transformers langchain"
+    "!pip install --upgrade --quiet aerospike-vector-search==4.2.0 langchain-aerospike langchain-community sentence-transformers langchain"
    ]
   },
   {
@@ -65,28 +75,32 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "--2024-05-10 17:28:17--  https://github.com/aerospike/aerospike-vector-search-examples/raw/7dfab0fccca0852a511c6803aba46578729694b5/quote-semantic-search/container-volumes/quote-search/data/quotes.csv.tgz\n",
-      "Resolving github.com (github.com)... 140.82.116.4\n",
-      "Connecting to github.com (github.com)|140.82.116.4|:443... connected.\n",
+      "--2025-05-07 21:06:30--  https://github.com/aerospike/aerospike-vector-search-examples/raw/7dfab0fccca0852a511c6803aba46578729694b5/quote-semantic-search/container-volumes/quote-search/data/quotes.csv.tgz\n",
+      "Resolving github.com (github.com)... 140.82.116.3\n",
+      "Connecting to github.com (github.com)|140.82.116.3|:443... connected.\n",
+      "HTTP request sent, awaiting response... 301 Moved Permanently\n",
+      "Location: https://github.com/aerospike/aerospike-vector/raw/7dfab0fccca0852a511c6803aba46578729694b5/quote-semantic-search/container-volumes/quote-search/data/quotes.csv.tgz [following]\n",
+      "--2025-05-07 21:06:30--  https://github.com/aerospike/aerospike-vector/raw/7dfab0fccca0852a511c6803aba46578729694b5/quote-semantic-search/container-volumes/quote-search/data/quotes.csv.tgz\n",
+      "Reusing existing connection to github.com:443.\n",
       "HTTP request sent, awaiting response... 302 Found\n",
-      "Location: https://raw.githubusercontent.com/aerospike/aerospike-vector-search-examples/7dfab0fccca0852a511c6803aba46578729694b5/quote-semantic-search/container-volumes/quote-search/data/quotes.csv.tgz [following]\n",
-      "--2024-05-10 17:28:17--  https://raw.githubusercontent.com/aerospike/aerospike-vector-search-examples/7dfab0fccca0852a511c6803aba46578729694b5/quote-semantic-search/container-volumes/quote-search/data/quotes.csv.tgz\n",
-      "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.110.133, 185.199.109.133, 185.199.111.133, ...\n",
+      "Location: https://raw.githubusercontent.com/aerospike/aerospike-vector/7dfab0fccca0852a511c6803aba46578729694b5/quote-semantic-search/container-volumes/quote-search/data/quotes.csv.tgz [following]\n",
+      "--2025-05-07 21:06:30--  https://raw.githubusercontent.com/aerospike/aerospike-vector/7dfab0fccca0852a511c6803aba46578729694b5/quote-semantic-search/container-volumes/quote-search/data/quotes.csv.tgz\n",
+      "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.110.133, 185.199.111.133, 185.199.108.133, ...\n",
       "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.110.133|:443... connected.\n",
       "HTTP request sent, awaiting response... 200 OK\n",
       "Length: 11597643 (11M) [application/octet-stream]\n",
       "Saving to: ‘quotes.csv.tgz’\n",
       "\n",
-      "quotes.csv.tgz      100%[===================>]  11.06M  1.94MB/s    in 6.1s    \n",
+      "quotes.csv.tgz      100%[===================>]  11.06M  12.7MB/s    in 0.9s    \n",
       "\n",
-      "2024-05-10 17:28:23 (1.81 MB/s) - ‘quotes.csv.tgz’ saved [11597643/11597643]\n",
+      "2025-05-07 21:06:32 (12.7 MB/s) - ‘quotes.csv.tgz’ saved [11597643/11597643]\n",
       "\n"
      ]
     }
@@ -106,7 +120,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -132,14 +146,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "page_content=\"quote: I'm selfish, impatient and a little insecure. I make mistakes, I am out of control and at times hard to handle. But if you can't handle me at my worst, then you sure as hell don't deserve me at my best.\" metadata={'source': './quotes.csv', 'row': 0, 'author': 'Marilyn Monroe', 'category': 'attributed-no-source, best, life, love, mistakes, out-of-control, truth, worst'}\n"
+      "page_content='quote: I'm selfish, impatient and a little insecure. I make mistakes, I am out of control and at times hard to handle. But if you can't handle me at my worst, then you sure as hell don't deserve me at my best.' metadata={'source': './quotes.csv', 'row': 0, 'author': 'Marilyn Monroe', 'category': 'attributed-no-source, best, life, love, mistakes, out-of-control, truth, worst'}\n"
      ]
     }
    ],
@@ -158,178 +172,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "60662fc2676a46a2ac48fbf30d9c85fe",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "modules.json:   0%|          | 0.00/349 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "319412217d3944488f135c8bf8bca73b",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "config_sentence_transformers.json:   0%|          | 0.00/116 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "eb020ec2e2f4486294f85c490ef4a387",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "README.md:   0%|          | 0.00/10.7k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "65d248263e4049bea4f6b554640a6aae",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "sentence_bert_config.json:   0%|          | 0.00/53.0 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/opt/conda/lib/python3.11/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
-      "  warnings.warn(\n"
+      "/var/folders/h5/lm2_c1xs3s32kwp11prnpftw0000gp/T/ipykernel_84638/3255399720.py:6: LangChainDeprecationWarning: The class `HuggingFaceEmbeddings` was deprecated in LangChain 0.2.2 and will be removed in 1.0. An updated version of the class exists in the :class:`~langchain-huggingface package and should be used instead. To use it run `pip install -U :class:`~langchain-huggingface` and import as `from :class:`~langchain_huggingface import HuggingFaceEmbeddings``.\n",
+      "  embedder = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",
+      "/Users/dwelch/Desktop/everything/projects/langchain/myfork/langchain/.venv/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
      ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c6b09a49fbd84c799ea28ace296406e3",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "config.json:   0%|          | 0.00/612 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/opt/conda/lib/python3.11/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "7e649688c67544d5af6bdd883c47d315",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "model.safetensors:   0%|          | 0.00/90.9M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "de447c7e4df1485ead14efae1faf96d6",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "tokenizer_config.json:   0%|          | 0.00/350 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "83ad1f289cd04f73aafca01a8e68e63b",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "vocab.txt:   0%|          | 0.00/232k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "2b612221e29e433cb50a54a6b838f5af",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "tokenizer.json:   0%|          | 0.00/466k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "1f5f0c29c58642478cd665731728dad0",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "special_tokens_map.json:   0%|          | 0.00/112 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "dff1d16a5a6d4d20ac39adb5c9425cf6",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "1_Pooling/config.json:   0%|          | 0.00/190 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
     }
    ],
    "source": [
@@ -352,7 +206,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -364,9 +218,9 @@
     }
    ],
    "source": [
-    "from aerospike_vector_search import AdminClient, Client, HostPort\n",
+    "from aerospike_vector_search import Client, HostPort\n",
     "from aerospike_vector_search.types import VectorDistanceMetric\n",
-    "from langchain_community.vectorstores import Aerospike\n",
+    "from langchain_aerospike.vectorstores import Aerospike\n",
     "\n",
     "# Here we are using the AVS host and port you configured earlier\n",
     "seed = HostPort(host=AVS_HOST, port=AVS_PORT)\n",
@@ -381,13 +235,10 @@
     "VECTOR_KEY = \"vector\"\n",
     "\n",
     "client = Client(seeds=seed)\n",
-    "admin_client = AdminClient(\n",
-    "    seeds=seed,\n",
-    ")\n",
     "index_exists = False\n",
     "\n",
     "# Check if the index already exists. If not, create it\n",
-    "for index in admin_client.index_list():\n",
+    "for index in client.index_list():\n",
     "    if index[\"id\"][\"namespace\"] == NAMESPACE and index[\"id\"][\"name\"] == INDEX_NAME:\n",
     "        index_exists = True\n",
     "        print(f\"{INDEX_NAME} already exists. Skipping creation\")\n",
@@ -395,7 +246,7 @@
     "\n",
     "if not index_exists:\n",
     "    print(f\"{INDEX_NAME} does not exist. Creating index\")\n",
-    "    admin_client.index_create(\n",
+    "    client.index_create(\n",
     "        namespace=NAMESPACE,\n",
     "        name=INDEX_NAME,\n",
     "        vector_field=VECTOR_KEY,\n",
@@ -409,8 +260,6 @@
     "        },\n",
     "    )\n",
     "\n",
-    "admin_client.close()\n",
-    "\n",
     "docstore = Aerospike.from_documents(\n",
     "    documents,\n",
     "    embedder,\n",
@@ -432,7 +281,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
@@ -440,31 +289,31 @@
      "output_type": "stream",
      "text": [
       "~~~~ Document 0 ~~~~\n",
-      "auto-generated id: f53589dd-e3e0-4f55-8214-766ca8dc082f\n",
+      "auto-generated id: 4984b472-8a32-4552-b3eb-f03b31b68031\n",
       "author:  Carl Sagan, Cosmos\n",
       "quote: The Cosmos is all that is or was or ever will be. Our feeblest contemplations of the Cosmos stir us -- there is a tingling in the spine, a catch in the voice, a faint sensation, as if a distant memory, of falling from a height. We know we are approaching the greatest of mysteries.\n",
       "~~~~~~~~~~~~~~~~~~~~\n",
       "\n",
       "~~~~ Document 1 ~~~~\n",
-      "auto-generated id: dde3e5d1-30b7-47b4-aab7-e319d14e1810\n",
-      "author:  Elizabeth Gilbert\n",
-      "quote: The love that moves the sun and the other stars.\n",
-      "~~~~~~~~~~~~~~~~~~~~\n",
-      "\n",
-      "~~~~ Document 2 ~~~~\n",
-      "auto-generated id: fd56575b-2091-45e7-91c1-9efff2fe5359\n",
+      "auto-generated id: 486c8d87-8dd7-450d-9008-d7549e680ffb\n",
       "author:  Renee Ahdieh, The Rose & the Dagger\n",
       "quote: From the stars, to the stars.\n",
       "~~~~~~~~~~~~~~~~~~~~\n",
       "\n",
+      "~~~~ Document 2 ~~~~\n",
+      "auto-generated id: 4b43b309-ce51-498c-b225-5254383b5b4a\n",
+      "author:  Elizabeth Gilbert\n",
+      "quote: The love that moves the sun and the other stars.\n",
+      "~~~~~~~~~~~~~~~~~~~~\n",
+      "\n",
       "~~~~ Document 3 ~~~~\n",
-      "auto-generated id: 8567ed4e-885b-44a7-b993-e0caf422b3c9\n",
+      "auto-generated id: af784a10-f498-4570-bf81-2ffdca35440e\n",
       "author:  Dante Alighieri, Paradiso\n",
       "quote: Love, that moves the sun and the other stars\n",
       "~~~~~~~~~~~~~~~~~~~~\n",
       "\n",
       "~~~~ Document 4 ~~~~\n",
-      "auto-generated id: f868c25e-c54d-48cd-a5a8-14bf402f9ea8\n",
+      "auto-generated id: b45d5d5e-d818-4206-ae6b-b1d166ea3d43\n",
       "author:  Thich Nhat Hanh, Teachings on Love\n",
       "quote: Through my love for you, I want to express my love for the whole cosmos, the whole of humanity, and all beings. By living with you, I want to learn to love everyone and all species. If I succeed in loving you, I will be able to love everyone and all species on Earth... This is the real message of love.\n",
       "~~~~~~~~~~~~~~~~~~~~\n",
@@ -502,7 +351,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
@@ -510,7 +359,7 @@
      "output_type": "stream",
      "text": [
       "New IDs\n",
-      "['972846bd-87ae-493b-8ba3-a3d023c03948', '8171122e-cbda-4eb7-a711-6625b120893b', '53b54409-ac19-4d90-b518-d7c40bf5ee5d']\n"
+      "['adf8064e-9c0e-46e2-b193-169c36432f4c', 'cf65b5ed-a0f4-491a-86ad-dcacc23c2815', '2ef52efd-d9b7-4077-bc14-defdf0b7dd2f']\n"
      ]
     }
    ],
@@ -552,7 +401,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
@@ -560,25 +409,25 @@
      "output_type": "stream",
      "text": [
       "~~~~ Document 0 ~~~~\n",
-      "auto-generated id: 67d5b23f-b2d2-4872-80ad-5834ea08aa64\n",
+      "auto-generated id: 91e77b39-a528-40c6-a58a-486ae85f991a\n",
       "author:  John Grogan, Marley and Me: Life and Love With the World's Worst Dog\n",
       "quote: Such short little lives our pets have to spend with us, and they spend most of it waiting for us to come home each day. It is amazing how much love and laughter they bring into our lives and even how much closer we become with each other because of them.\n",
       "~~~~~~~~~~~~~~~~~~~~\n",
       "\n",
       "~~~~ Document 1 ~~~~\n",
-      "auto-generated id: a9b28eb0-a21c-45bf-9e60-ab2b80e988d8\n",
+      "auto-generated id: c585b4ec-92b5-4579-948c-0529373abc2a\n",
       "author:  John Grogan, Marley and Me: Life and Love With the World's Worst Dog\n",
       "quote: Dogs are great. Bad dogs, if you can really call them that, are perhaps the greatest of them all.\n",
       "~~~~~~~~~~~~~~~~~~~~\n",
       "\n",
       "~~~~ Document 2 ~~~~\n",
-      "auto-generated id: ee7434c8-2551-4651-8a22-58514980fb4a\n",
+      "auto-generated id: 5768b31c-fac4-4af7-84b4-fb11bbfcb590\n",
       "author:  Colleen Houck, Tiger's Curse\n",
       "quote: He then put both hands on the door on either side of my head and leaned in close, pinning me against it. I trembled like a downy rabbit caught in the clutches of a wolf. The wolf came closer. He bent his head and began nuzzling my cheek. The problem was…I wanted the wolf to devour me.\n",
       "~~~~~~~~~~~~~~~~~~~~\n",
       "\n",
       "~~~~ Document 3 ~~~~\n",
-      "auto-generated id: 9170804c-a155-473b-ab93-8a561dd48f91\n",
+      "auto-generated id: 94f1b9fb-ad57-4f65-b470-7f49dd6c274c\n",
       "author:  Ray Bradbury\n",
       "quote: Stuff your eyes with wonder,\" he said, \"live as if you'd drop dead in ten seconds. See the world. It's more fantastic than any dream made or paid for in factories. Ask no guarantees, ask for no security, there never was such an animal. And if there were, it would be related to the great sloth which hangs upside down in a tree all day every day, sleeping its life away. To hell with that,\" he said, \"shake the tree and knock the great sloth down on his ass.\n",
       "~~~~~~~~~~~~~~~~~~~~\n",
@@ -607,7 +456,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
@@ -615,25 +464,25 @@
      "output_type": "stream",
      "text": [
       "~~~~ Document 0 ~~~~\n",
-      "auto-generated id: 2c1d6ee1-b742-45ea-bed6-24a1f655c849\n",
+      "auto-generated id: 6d9e67a6-0427-41e6-9e24-050518120d74\n",
       "author:  Roy T. Bennett, The Light in the Heart\n",
       "quote: Never lose hope. Storms make people stronger and never last forever.\n",
       "~~~~~~~~~~~~~~~~~~~~\n",
       "\n",
       "~~~~ Document 1 ~~~~\n",
-      "auto-generated id: 5962c2cf-ffb5-4e03-9257-bdd630b5c7e9\n",
+      "auto-generated id: 7d426e59-7935-4bcf-a676-cbe8dd4860e7\n",
       "author:  Roy T. Bennett, The Light in the Heart\n",
       "quote: Difficulties and adversities viciously force all their might on us and cause us to fall apart, but they are necessary elements of individual growth and reveal our true potential. We have got to endure and overcome them, and move forward. Never lose hope. Storms make people stronger and never last forever.\n",
       "~~~~~~~~~~~~~~~~~~~~\n",
       "\n",
       "~~~~ Document 2 ~~~~\n",
-      "auto-generated id: 3bbcc4ca-de89-4196-9a46-190a50bf6c47\n",
+      "auto-generated id: 6ec05e48-d162-440d-8819-001d2f3712f9\n",
       "author:  Vincent van Gogh, The Letters of Vincent van Gogh\n",
       "quote: There is peace even in the storm\n",
       "~~~~~~~~~~~~~~~~~~~~\n",
       "\n",
       "~~~~ Document 3 ~~~~\n",
-      "auto-generated id: 37d8cf02-fc2f-429d-b2b6-260a05286108\n",
+      "auto-generated id: d3c3de59-4da4-4ae6-8f6d-83ed905dd320\n",
       "author:  Edwin Morgan, A Book of Lives\n",
       "quote: Valentine WeatherKiss me with rain on your eyelashes,come on, let us sway together,under the trees, and to hell with thunder.\n",
       "~~~~~~~~~~~~~~~~~~~~\n",
@@ -665,7 +514,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -684,7 +533,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": ".venv",
    "language": "python",
    "name": "python3"
   },
@@ -698,7 +547,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.6"
+   "version": "3.11.12"
   }
  },
  "nbformat": 4,

docs/docs/integrations/vectorstores/gel.ipynb

@@ -0,0 +1,450 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "7679dd7b-7ed4-4755-a499-824deadba708",
+   "metadata": {},
+   "source": [
+    "# Gel \n",
+    "\n",
+    "> An implementation of LangChain vectorstore abstraction using `gel` as the backend.\n",
+    "\n",
+    "[Gel](https://www.geldata.com/) is an open-source PostgreSQL data layer optimized for fast development to production cycle. It comes with a high-level strictly typed graph-like data model, composable hierarchical query language, full SQL support, migrations, Auth and AI modules.\n",
+    "\n",
+    "The code lives in an integration package called [langchain-gel](https://github.com/geldata/langchain-gel).\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "First install relevant packages:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "92df32f0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! pip install -qU gel langchain-gel "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "68ef6ebb",
+   "metadata": {},
+   "source": [
+    "## Initialization\n",
+    "\n",
+    "In order to use Gel as a backend for your `VectorStore`, you're going to need a working Gel instance.\n",
+    "Fortunately, it doesn't have to involve Docker containers or anything complicated, unless you want to!\n",
+    "\n",
+    "To set up a local instance, run:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b79938d3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! gel project init --non-interactive"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "08e79230",
+   "metadata": {},
+   "source": [
+    "If you are using [Gel Cloud](https://cloud.geldata.com/) (and you should!), add one more argument to that command:\n",
+    "\n",
+    "```bash\n",
+    "gel project init --server-instance <org-name>/<instance-name>\n",
+    "```\n",
+    "\n",
+    "For a comprehensive list of ways to run Gel, take a look at [Running Gel](https://docs.geldata.com/reference/running) section of the reference docs.\n",
+    "\n",
+    "### Set up the schema\n",
+    "\n",
+    "[Gel schema](https://docs.geldata.com/reference/datamodel) is an explicit high-level description of your application's data model. \n",
+    "Aside from enabling you to define exactly how your data is going to be laid out, it drives Gel's many powerful features such as links, access policies, functions, triggers, constraints, indexes, and more.\n",
+    "\n",
+    "The LangChain's `VectorStore` expects the following layout for the schema:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "9a7edd58",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "schema_content = \"\"\"\n",
+    "using extension pgvector;\n",
+    "                                    \n",
+    "module default {\n",
+    "    scalar type EmbeddingVector extending ext::pgvector::vector<1536>;\n",
+    "\n",
+    "    type Record {\n",
+    "        required collection: str;\n",
+    "        text: str;\n",
+    "        embedding: EmbeddingVector; \n",
+    "        external_id: str {\n",
+    "            constraint exclusive;\n",
+    "        };\n",
+    "        metadata: json;\n",
+    "\n",
+    "        index ext::pgvector::hnsw_cosine(m := 16, ef_construction := 128)\n",
+    "            on (.embedding)\n",
+    "    } \n",
+    "}\n",
+    "\"\"\".strip()\n",
+    "\n",
+    "with open(\"dbschema/default.gel\", \"w\") as f:\n",
+    "    f.write(schema_content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "90320ef1",
+   "metadata": {},
+   "source": [
+    "In order to apply schema changes to the database, run a migration using Gel's [migration mechanism](https://docs.geldata.com/reference/datamodel/migrations):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cdff483e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! gel migration create --non-interactive\n",
+    "! gel migrate"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b2290ef2",
+   "metadata": {},
+   "source": [
+    "From this point onward, `GelVectorStore` can be used as a drop-in replacement for any other vectorstore available in LangChain."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ec44dfcc",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "import EmbeddingTabs from \"@theme/EmbeddingTabs\";\n",
+    "\n",
+    "<EmbeddingTabs/>\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "94f5c129",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# | output: false\n",
+    "# | echo: false\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings(model=\"text-embedding-3-small\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "979a65bd-742f-4b0d-be1e-c0baae245ec6",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_gel import GelVectorStore\n",
+    "\n",
+    "vector_store = GelVectorStore(\n",
+    "    embeddings=embeddings,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "61a224a1-d70b-4daf-86ba-ab6e43c08b50",
+   "metadata": {},
+   "source": [
+    "## Manage vector store\n",
+    "\n",
+    "### Add items to vector store\n",
+    "\n",
+    "Note that adding documents by ID will over-write any existing documents that match that ID."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "88a288cc-ffd4-4800-b011-750c72b9fd10",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_core.documents import Document\n",
+    "\n",
+    "docs = [\n",
+    "    Document(\n",
+    "        page_content=\"there are cats in the pond\",\n",
+    "        metadata={\"id\": \"1\", \"location\": \"pond\", \"topic\": \"animals\"},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"ducks are also found in the pond\",\n",
+    "        metadata={\"id\": \"2\", \"location\": \"pond\", \"topic\": \"animals\"},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"fresh apples are available at the market\",\n",
+    "        metadata={\"id\": \"3\", \"location\": \"market\", \"topic\": \"food\"},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"the market also sells fresh oranges\",\n",
+    "        metadata={\"id\": \"4\", \"location\": \"market\", \"topic\": \"food\"},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"the new art exhibit is fascinating\",\n",
+    "        metadata={\"id\": \"5\", \"location\": \"museum\", \"topic\": \"art\"},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"a sculpture exhibit is also at the museum\",\n",
+    "        metadata={\"id\": \"6\", \"location\": \"museum\", \"topic\": \"art\"},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"a new coffee shop opened on Main Street\",\n",
+    "        metadata={\"id\": \"7\", \"location\": \"Main Street\", \"topic\": \"food\"},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"the book club meets at the library\",\n",
+    "        metadata={\"id\": \"8\", \"location\": \"library\", \"topic\": \"reading\"},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"the library hosts a weekly story time for kids\",\n",
+    "        metadata={\"id\": \"9\", \"location\": \"library\", \"topic\": \"reading\"},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"a cooking class for beginners is offered at the community center\",\n",
+    "        metadata={\"id\": \"10\", \"location\": \"community center\", \"topic\": \"classes\"},\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "vector_store.add_documents(docs, ids=[doc.metadata[\"id\"] for doc in docs])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0c712fa3",
+   "metadata": {},
+   "source": [
+    "### Delete items from vector store"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "a5b2b71f-49eb-407d-b03a-dea4c0a517d6",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "vector_store.delete(ids=[\"3\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "59f82250-7903-4279-8300-062542c83416",
+   "metadata": {},
+   "source": [
+    "## Query vector store\n",
+    "\n",
+    "Once your vector store has been created and the relevant documents have been added you will most likely wish to query it during the running of your chain or agent. \n",
+    "\n",
+    "### Filtering Support\n",
+    "\n",
+    "The vectorstore supports a set of filters that can be applied against the metadata fields of the documents.\n",
+    "\n",
+    "| Operator | Meaning/Category        |\n",
+    "|----------|-------------------------|\n",
+    "| \\$eq      | Equality (==)           |\n",
+    "| \\$ne      | Inequality (!=)         |\n",
+    "| \\$lt      | Less than (&lt;)           |\n",
+    "| \\$lte     | Less than or equal (&lt;=) |\n",
+    "| \\$gt      | Greater than (>)        |\n",
+    "| \\$gte     | Greater than or equal (>=) |\n",
+    "| \\$in      | Special Cased (in)      |\n",
+    "| \\$nin     | Special Cased (not in)  |\n",
+    "| \\$between | Special Cased (between) |\n",
+    "| \\$like    | Text (like)             |\n",
+    "| \\$ilike   | Text (case-insensitive like) |\n",
+    "| \\$and     | Logical (and)           |\n",
+    "| \\$or      | Logical (or)            |\n",
+    "\n",
+    "### Query directly\n",
+    "\n",
+    "Performing a simple similarity search can be done as follows:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f15a2359-6dc3-4099-8214-785f167a9ca4",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "results = vector_store.similarity_search(\n",
+    "    \"kitty\", k=10, filter={\"id\": {\"$in\": [\"1\", \"5\", \"2\", \"9\"]}}\n",
+    ")\n",
+    "for doc in results:\n",
+    "    print(f\"* {doc.page_content} [{doc.metadata}]\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d92ea049-1b1f-4ae9-9525-35750fe2e52e",
+   "metadata": {},
+   "source": [
+    "If you provide a dict with multiple fields, but no operators, the top level will be interpreted as a logical **AND** filter"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "88f919e4-e4b0-4b5f-99b3-24c675c26d33",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "vector_store.similarity_search(\n",
+    "    \"ducks\",\n",
+    "    k=10,\n",
+    "    filter={\n",
+    "        \"id\": {\"$in\": [\"1\", \"5\", \"2\", \"9\"]},\n",
+    "        \"location\": {\"$in\": [\"pond\", \"market\"]},\n",
+    "    },\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "88f423a4-6575-4fb8-9be2-a3da01106591",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "vector_store.similarity_search(\n",
+    "    \"ducks\",\n",
+    "    k=10,\n",
+    "    filter={\n",
+    "        \"$and\": [\n",
+    "            {\"id\": {\"$in\": [\"1\", \"5\", \"2\", \"9\"]}},\n",
+    "            {\"location\": {\"$in\": [\"pond\", \"market\"]}},\n",
+    "        ]\n",
+    "    },\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2e65adc1",
+   "metadata": {},
+   "source": [
+    "If you want to execute a similarity search and receive the corresponding scores you can run:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7d92e7b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "results = vector_store.similarity_search_with_score(query=\"cats\", k=1)\n",
+    "for doc, score in results:\n",
+    "    print(f\"* [SIM={score:3f}] {doc.page_content} [{doc.metadata}]\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8d40db8c",
+   "metadata": {},
+   "source": [
+    "### Query by turning into retriever\n",
+    "\n",
+    "You can also transform the vector store into a retriever for easier usage in your chains. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7cd1fb75",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = vector_store.as_retriever(search_kwargs={\"k\": 1})\n",
+    "retriever.invoke(\"kitty\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7ecd77a0",
+   "metadata": {},
+   "source": [
+    "## Usage for retrieval-augmented generation\n",
+    "\n",
+    "For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:\n",
+    "\n",
+    "- [Tutorials](/docs/tutorials/)\n",
+    "- [How-to: Question and answer with RAG](https://python.langchain.com/docs/how_to/#qa-with-rag)\n",
+    "- [Retrieval conceptual docs](https://python.langchain.com/docs/concepts/retrieval)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "33a5f0e6",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all GelVectorStore features and configurations head to the API reference: https://python.langchain.com/api_reference/"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/vectorstores/milvus.ipynb

@@ -553,7 +553,10 @@
    "cell_type": "markdown",
    "id": "8edb47106e1a46a883d545849b8ab81b",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "\n",
@@ -576,6 +579,9 @@
    "id": "10185d26023b46108eb7d9f57d49d2b3",
    "metadata": {
     "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    },
     "pycharm": {
      "name": "#%%\n"
     }
@@ -603,7 +609,10 @@
    "cell_type": "markdown",
    "id": "8763a12b2bbd4a93a75aff182afb95dc",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "> - When you use `BM25BuiltInFunction`, please note that the full-text search is available in Milvus Standalone and Milvus Distributed, but not in Milvus Lite, although it is on the roadmap for future inclusion. It will also be available in Zilliz Cloud (fully-managed Milvus) soon. Please reach out to support@zilliz.com for more information.\n",
@@ -617,7 +626,10 @@
    "cell_type": "markdown",
    "id": "7623eae2785240b9bd12b16a66d81610",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "### Rerank the candidates\n",
@@ -632,6 +644,9 @@
    "id": "7cdc8c89c7104fffa095e18ddfef8986",
    "metadata": {
     "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    },
     "pycharm": {
      "name": "#%%\n"
     }
@@ -645,14 +660,6 @@
     ")"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "b3965036",
-   "metadata": {},
-   "source": [
-    "For more information about Full-text search and Hybrid search, please refer to the [Using Full-Text Search with LangChain and Milvus](https://milvus.io/docs/full_text_search_with_langchain.md) and [Hybrid Retrieval with LangChain and Milvus](https://milvus.io/docs/milvus_hybrid_search_retriever.md)."
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "8ac953f1",
@@ -813,7 +820,7 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -827,7 +834,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.0"
+   "version": "3.13.2"
   }
  },
  "nbformat": 4,

docs/scripts/packages_yml_get_downloads.py

@@ -37,6 +37,7 @@ def _reorder_keys(p):
         "downloads",
         "downloads_updated_at",
         "disabled",
+        "include_in_api_ref",
     ]
     if set(keys) - set(key_order):
         raise ValueError(f"Unexpected keys: {set(keys) - set(key_order)}")

docs/src/theme/EmbeddingTabs.js

@@ -9,8 +9,10 @@ export default function EmbeddingTabs(props) {
       hideOpenai,
       azureOpenaiParams,
       hideAzureOpenai,
-      googleParams,
-      hideGoogle,
+      googleGenAIParams,
+      hideGoogleGenAI,
+      googleVertexAIParams,
+      hideGoogleVertexAI,
       awsParams,
       hideAws,
       huggingFaceParams,
@@ -38,7 +40,8 @@ export default function EmbeddingTabs(props) {
     const azureParamsOrDefault =
       azureOpenaiParams ??
       `\n    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],\n    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],\n    openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"],\n`;
-    const googleParamsOrDefault = googleParams ?? `model="text-embedding-004"`;
+    const googleGenAIParamsOrDefault = googleGenAIParams ?? `model="models/embedding-001"`;
+    const googleVertexAIParamsOrDefault = googleVertexAIParams ?? `model="text-embedding-004"`;
     const awsParamsOrDefault = awsParams ?? `model_id="amazon.titan-embed-text-v2:0"`;
     const huggingFaceParamsOrDefault = huggingFaceParams ?? `model_name="sentence-transformers/all-mpnet-base-v2"`;
     const ollamaParamsOrDefault = ollamaParams ?? `model="llama3"`;
@@ -73,13 +76,22 @@ export default function EmbeddingTabs(props) {
         shouldHide: hideAzureOpenai,
       },
       {
-        value: "Google",
-        label: "Google",
-        text: `from langchain_google_vertexai import VertexAIEmbeddings\n\n${embeddingVarName} = VertexAIEmbeddings(${googleParamsOrDefault})`,
+        value: "GoogleGenAI",
+        label: "Google Gemini",
+        text: `from langchain_google_genai import GoogleGenerativeAIEmbeddings\n\n${embeddingVarName} = GoogleGenerativeAIEmbeddings(${googleGenAIParamsOrDefault})`,
+        apiKeyName: "GOOGLE_API_KEY",
+        packageName: "langchain-google-genai",
+        default: false,
+        shouldHide: hideGoogleGenAI,
+      },
+      {
+        value: "GoogleVertexAI",
+        label: "Google Vertex",
+        text: `from langchain_google_vertexai import VertexAIEmbeddings\n\n${embeddingVarName} = VertexAIEmbeddings(${googleVertexAIParamsOrDefault})`,
         apiKeyName: undefined,
         packageName: "langchain-google-vertexai",
         default: false,
-        shouldHide: hideGoogle,
+        shouldHide: hideGoogleVertexAI,
       },
       {
         value: "AWS",

docs/src/theme/FeatureTables.js

@@ -461,14 +461,6 @@ const FEATURE_TABLES = {
                 apiLink: "https://python.langchain.com/api_reference/elasticsearch/retrievers/langchain_elasticsearch.retrievers.ElasticsearchRetriever.html",
                 package: "langchain_elasticsearch"
             },
-            {
-                name: "MilvusCollectionHybridSearchRetriever",
-                link: "milvus_hybrid_search",
-                selfHost: true,
-                cloudOffering: false,
-                apiLink: "https://python.langchain.com/api_reference/milvus/retrievers/langchain_milvus.retrievers.milvus_hybrid_search.MilvusCollectionHybridSearchRetriever.html",
-                package: "langchain_milvus"
-            },
             {
                 name: "VertexAISearchRetriever",
                 link: "google_vertex_ai_search",

docs/vercel.json

@@ -153,6 +153,10 @@
     {
       "source": "/api_reference/tests/:path(.*/?)*",
       "destination": "/api_reference/standard_tests/:path"
+    },
+    {
+      "source": "/docs/integrations/retrievers/milvus_hybrid_search(/?)",
+      "destination": "https://python.langchain.com/v0.2/docs/integrations/retrievers/milvus_hybrid_search/"
     }
   ]
 }

docs/vercel_overrides.txt

@@ -2,3 +2,5 @@ httpx
 grpcio
 aiohttp<3.11
 protobuf<3.21
+tenacity
+urllib3

libs/core/langchain_core/callbacks/manager.py

@@ -520,6 +520,8 @@ class RunManager(BaseRunManager):
         Returns:
             Any: The result of the callback.
         """
+        if not self.handlers:
+            return
         handle_event(
             self.handlers,
             "on_text",
@@ -542,6 +544,8 @@ class RunManager(BaseRunManager):
             retry_state (RetryCallState): The retry state.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         handle_event(
             self.handlers,
             "on_retry",
@@ -601,6 +605,8 @@ class AsyncRunManager(BaseRunManager, ABC):
         Returns:
             Any: The result of the callback.
         """
+        if not self.handlers:
+            return
         await ahandle_event(
             self.handlers,
             "on_text",
@@ -623,6 +629,8 @@ class AsyncRunManager(BaseRunManager, ABC):
             retry_state (RetryCallState): The retry state.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         await ahandle_event(
             self.handlers,
             "on_retry",
@@ -675,6 +683,8 @@ class CallbackManagerForLLMRun(RunManager, LLMManagerMixin):
                 The chunk. Defaults to None.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         handle_event(
             self.handlers,
             "on_llm_new_token",
@@ -694,6 +704,8 @@ class CallbackManagerForLLMRun(RunManager, LLMManagerMixin):
             response (LLMResult): The LLM result.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         handle_event(
             self.handlers,
             "on_llm_end",
@@ -718,6 +730,8 @@ class CallbackManagerForLLMRun(RunManager, LLMManagerMixin):
                 - response (LLMResult): The response which was generated before
                     the error occurred.
         """
+        if not self.handlers:
+            return
         handle_event(
             self.handlers,
             "on_llm_error",
@@ -750,7 +764,6 @@ class AsyncCallbackManagerForLLMRun(AsyncRunManager, LLMManagerMixin):
             inheritable_metadata=self.inheritable_metadata,
         )
 
-    @shielded
     async def on_llm_new_token(
         self,
         token: str,
@@ -766,6 +779,8 @@ class AsyncCallbackManagerForLLMRun(AsyncRunManager, LLMManagerMixin):
                 The chunk. Defaults to None.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         await ahandle_event(
             self.handlers,
             "on_llm_new_token",
@@ -786,6 +801,8 @@ class AsyncCallbackManagerForLLMRun(AsyncRunManager, LLMManagerMixin):
             response (LLMResult): The LLM result.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         await ahandle_event(
             self.handlers,
             "on_llm_end",
@@ -814,6 +831,8 @@ class AsyncCallbackManagerForLLMRun(AsyncRunManager, LLMManagerMixin):
 
 
         """
+        if not self.handlers:
+            return
         await ahandle_event(
             self.handlers,
             "on_llm_error",
@@ -836,6 +855,8 @@ class CallbackManagerForChainRun(ParentRunManager, ChainManagerMixin):
             outputs (Union[dict[str, Any], Any]): The outputs of the chain.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         handle_event(
             self.handlers,
             "on_chain_end",
@@ -858,6 +879,8 @@ class CallbackManagerForChainRun(ParentRunManager, ChainManagerMixin):
             error (Exception or KeyboardInterrupt): The error.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         handle_event(
             self.handlers,
             "on_chain_error",
@@ -879,6 +902,8 @@ class CallbackManagerForChainRun(ParentRunManager, ChainManagerMixin):
         Returns:
             Any: The result of the callback.
         """
+        if not self.handlers:
+            return
         handle_event(
             self.handlers,
             "on_agent_action",
@@ -900,6 +925,8 @@ class CallbackManagerForChainRun(ParentRunManager, ChainManagerMixin):
         Returns:
             Any: The result of the callback.
         """
+        if not self.handlers:
+            return
         handle_event(
             self.handlers,
             "on_agent_finish",
@@ -942,6 +969,8 @@ class AsyncCallbackManagerForChainRun(AsyncParentRunManager, ChainManagerMixin):
             outputs (Union[dict[str, Any], Any]): The outputs of the chain.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         await ahandle_event(
             self.handlers,
             "on_chain_end",
@@ -965,6 +994,8 @@ class AsyncCallbackManagerForChainRun(AsyncParentRunManager, ChainManagerMixin):
             error (Exception or KeyboardInterrupt): The error.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         await ahandle_event(
             self.handlers,
             "on_chain_error",
@@ -976,7 +1007,6 @@ class AsyncCallbackManagerForChainRun(AsyncParentRunManager, ChainManagerMixin):
             **kwargs,
         )
 
-    @shielded
     async def on_agent_action(self, action: AgentAction, **kwargs: Any) -> Any:
         """Run when agent action is received.
 
@@ -987,6 +1017,8 @@ class AsyncCallbackManagerForChainRun(AsyncParentRunManager, ChainManagerMixin):
         Returns:
             Any: The result of the callback.
         """
+        if not self.handlers:
+            return
         await ahandle_event(
             self.handlers,
             "on_agent_action",
@@ -998,7 +1030,6 @@ class AsyncCallbackManagerForChainRun(AsyncParentRunManager, ChainManagerMixin):
             **kwargs,
         )
 
-    @shielded
     async def on_agent_finish(self, finish: AgentFinish, **kwargs: Any) -> Any:
         """Run when agent finish is received.
 
@@ -1009,6 +1040,8 @@ class AsyncCallbackManagerForChainRun(AsyncParentRunManager, ChainManagerMixin):
         Returns:
             Any: The result of the callback.
         """
+        if not self.handlers:
+            return
         await ahandle_event(
             self.handlers,
             "on_agent_finish",
@@ -1035,6 +1068,8 @@ class CallbackManagerForToolRun(ParentRunManager, ToolManagerMixin):
             output (Any): The output of the tool.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         handle_event(
             self.handlers,
             "on_tool_end",
@@ -1057,6 +1092,8 @@ class CallbackManagerForToolRun(ParentRunManager, ToolManagerMixin):
             error (Exception or KeyboardInterrupt): The error.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         handle_event(
             self.handlers,
             "on_tool_error",
@@ -1089,7 +1126,6 @@ class AsyncCallbackManagerForToolRun(AsyncParentRunManager, ToolManagerMixin):
             inheritable_metadata=self.inheritable_metadata,
         )
 
-    @shielded
     async def on_tool_end(self, output: Any, **kwargs: Any) -> None:
         """Async run when the tool ends running.
 
@@ -1097,6 +1133,8 @@ class AsyncCallbackManagerForToolRun(AsyncParentRunManager, ToolManagerMixin):
             output (Any): The output of the tool.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         await ahandle_event(
             self.handlers,
             "on_tool_end",
@@ -1108,7 +1146,6 @@ class AsyncCallbackManagerForToolRun(AsyncParentRunManager, ToolManagerMixin):
             **kwargs,
         )
 
-    @shielded
     async def on_tool_error(
         self,
         error: BaseException,
@@ -1120,6 +1157,8 @@ class AsyncCallbackManagerForToolRun(AsyncParentRunManager, ToolManagerMixin):
             error (Exception or KeyboardInterrupt): The error.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         await ahandle_event(
             self.handlers,
             "on_tool_error",
@@ -1146,6 +1185,8 @@ class CallbackManagerForRetrieverRun(ParentRunManager, RetrieverManagerMixin):
             documents (Sequence[Document]): The retrieved documents.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         handle_event(
             self.handlers,
             "on_retriever_end",
@@ -1168,6 +1209,8 @@ class CallbackManagerForRetrieverRun(ParentRunManager, RetrieverManagerMixin):
             error (BaseException): The error.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         handle_event(
             self.handlers,
             "on_retriever_error",
@@ -1213,6 +1256,8 @@ class AsyncCallbackManagerForRetrieverRun(
             documents (Sequence[Document]): The retrieved documents.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         await ahandle_event(
             self.handlers,
             "on_retriever_end",
@@ -1236,6 +1281,8 @@ class AsyncCallbackManagerForRetrieverRun(
             error (BaseException): The error.
             **kwargs (Any): Additional keyword arguments.
         """
+        if not self.handlers:
+            return
         await ahandle_event(
             self.handlers,
             "on_retriever_error",
@@ -1521,6 +1568,8 @@ class CallbackManager(BaseCallbackManager):
 
         .. versionadded:: 0.2.14
         """
+        if not self.handlers:
+            return
         if kwargs:
             msg = (
                 "The dispatcher API does not accept additional keyword arguments."
@@ -1998,6 +2047,8 @@ class AsyncCallbackManager(BaseCallbackManager):
 
         .. versionadded:: 0.2.14
         """
+        if not self.handlers:
+            return
         if run_id is None:
             run_id = uuid.uuid4()
 

libs/core/langchain_core/documents/base.py

@@ -8,7 +8,7 @@ from io import BufferedReader, BytesIO
 from pathlib import Path, PurePath
 from typing import TYPE_CHECKING, Any, Literal, Optional, Union, cast
 
-from pydantic import ConfigDict, Field, field_validator, model_validator
+from pydantic import ConfigDict, Field, model_validator
 
 from langchain_core.load.serializable import Serializable
 
@@ -33,7 +33,7 @@ class BaseMedia(Serializable):
     # The ID field is optional at the moment.
     # It will likely become required in a future major release after
     # it has been adopted by enough vectorstore implementations.
-    id: Optional[str] = None
+    id: Optional[str] = Field(default=None, coerce_numbers_to_str=True)
     """An optional identifier for the document.
 
     Ideally this should be unique across the document collection and formatted
@@ -45,17 +45,6 @@ class BaseMedia(Serializable):
     metadata: dict = Field(default_factory=dict)
     """Arbitrary metadata associated with the content."""
 
-    @field_validator("id", mode="before")
-    def cast_id_to_str(cls, id_value: Any) -> Optional[str]:
-        """Coerce the id field to a string.
-
-        Args:
-            id_value: The id value to coerce.
-        """
-        if id_value is not None:
-            return str(id_value)
-        return id_value
-
 
 class Blob(BaseMedia):
     """Blob represents raw data by either reference or value.

libs/core/langchain_core/indexing/api.py

@@ -466,10 +466,9 @@ def index(
 
             _source_ids = cast("Sequence[str]", source_ids)
 
-            uids_to_delete = record_manager.list_keys(
-                group_ids=_source_ids, before=index_start_dt
-            )
-            if uids_to_delete:
+            while uids_to_delete := record_manager.list_keys(
+                group_ids=_source_ids, before=index_start_dt, limit=cleanup_batch_size
+            ):
                 # Then delete from vector store.
                 _delete(destination, uids_to_delete)
                 # First delete from record store.
@@ -780,10 +779,9 @@ async def aindex(
 
             _source_ids = cast("Sequence[str]", source_ids)
 
-            uids_to_delete = await record_manager.alist_keys(
-                group_ids=_source_ids, before=index_start_dt
-            )
-            if uids_to_delete:
+            while uids_to_delete := await record_manager.alist_keys(
+                group_ids=_source_ids, before=index_start_dt, limit=cleanup_batch_size
+            ):
                 # Then delete from vector store.
                 await _adelete(destination, uids_to_delete)
                 # First delete from record store.

libs/core/langchain_core/language_models/chat_models.py

@@ -66,6 +66,7 @@ from langchain_core.outputs import (
     LLMResult,
     RunInfo,
 )
+from langchain_core.outputs.chat_generation import merge_chat_generation_chunks
 from langchain_core.prompt_values import ChatPromptValue, PromptValue, StringPromptValue
 from langchain_core.rate_limiters import BaseRateLimiter
 from langchain_core.runnables import RunnableMap, RunnablePassthrough
@@ -411,8 +412,8 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
         **kwargs: Any,
     ) -> bool:
         """Determine if a given model call should hit the streaming API."""
-        sync_not_implemented = type(self)._stream == BaseChatModel._stream
-        async_not_implemented = type(self)._astream == BaseChatModel._astream
+        sync_not_implemented = type(self)._stream == BaseChatModel._stream  # noqa: SLF001
+        async_not_implemented = type(self)._astream == BaseChatModel._astream  # noqa: SLF001
 
         # Check if streaming is implemented.
         if (not async_api) and sync_not_implemented:
@@ -485,34 +486,41 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
                 run_id=config.pop("run_id", None),
                 batch_size=1,
             )
-            generation: Optional[ChatGenerationChunk] = None
+
+            chunks: list[ChatGenerationChunk] = []
 
             if self.rate_limiter:
                 self.rate_limiter.acquire(blocking=True)
 
             try:
                 input_messages = _normalize_messages(messages)
+                run_id = "-".join((_LC_ID_PREFIX, str(run_manager.run_id)))
                 for chunk in self._stream(input_messages, stop=stop, **kwargs):
                     if chunk.message.id is None:
-                        chunk.message.id = f"{_LC_ID_PREFIX}-{run_manager.run_id}"
+                        chunk.message.id = run_id
                     chunk.message.response_metadata = _gen_info_and_msg_metadata(chunk)
                     run_manager.on_llm_new_token(
                         cast("str", chunk.message.content), chunk=chunk
                     )
+                    chunks.append(chunk)
                     yield chunk.message
-                    if generation is None:
-                        generation = chunk
-                    else:
-                        generation += chunk
             except BaseException as e:
                 generations_with_error_metadata = _generate_response_from_error(e)
-                if generation:
-                    generations = [[generation], generations_with_error_metadata]
+                chat_generation_chunk = merge_chat_generation_chunks(chunks)
+                if chat_generation_chunk:
+                    generations = [
+                        [chat_generation_chunk],
+                        generations_with_error_metadata,
+                    ]
                 else:
                     generations = [generations_with_error_metadata]
-                run_manager.on_llm_error(e, response=LLMResult(generations=generations))  # type: ignore[arg-type]
+                run_manager.on_llm_error(
+                    e,
+                    response=LLMResult(generations=generations),  # type: ignore[arg-type]
+                )
                 raise
 
+            generation = merge_chat_generation_chunks(chunks)
             if generation is None:
                 err = ValueError("No generation chunks were returned")
                 run_manager.on_llm_error(err, response=LLMResult(generations=[]))
@@ -575,29 +583,29 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
         if self.rate_limiter:
             await self.rate_limiter.aacquire(blocking=True)
 
-        generation: Optional[ChatGenerationChunk] = None
+        chunks: list[ChatGenerationChunk] = []
+
         try:
             input_messages = _normalize_messages(messages)
+            run_id = "-".join((_LC_ID_PREFIX, str(run_manager.run_id)))
             async for chunk in self._astream(
                 input_messages,
                 stop=stop,
                 **kwargs,
             ):
                 if chunk.message.id is None:
-                    chunk.message.id = f"{_LC_ID_PREFIX}-{run_manager.run_id}"
+                    chunk.message.id = run_id
                 chunk.message.response_metadata = _gen_info_and_msg_metadata(chunk)
                 await run_manager.on_llm_new_token(
                     cast("str", chunk.message.content), chunk=chunk
                 )
+                chunks.append(chunk)
                 yield chunk.message
-                if generation is None:
-                    generation = chunk
-                else:
-                    generation += chunk
         except BaseException as e:
             generations_with_error_metadata = _generate_response_from_error(e)
-            if generation:
-                generations = [[generation], generations_with_error_metadata]
+            chat_generation_chunk = merge_chat_generation_chunks(chunks)
+            if chat_generation_chunk:
+                generations = [[chat_generation_chunk], generations_with_error_metadata]
             else:
                 generations = [generations_with_error_metadata]
             await run_manager.on_llm_error(
@@ -606,7 +614,8 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
             )
             raise
 
-        if generation is None:
+        generation = merge_chat_generation_chunks(chunks)
+        if not generation:
             err = ValueError("No generation chunks were returned")
             await run_manager.on_llm_error(err, response=LLMResult(generations=[]))
             raise err

libs/core/langchain_core/language_models/llms.py

@@ -522,7 +522,7 @@ class BaseLLM(BaseLanguageModel[str], ABC):
         stop: Optional[list[str]] = None,
         **kwargs: Any,
     ) -> Iterator[str]:
-        if type(self)._stream == BaseLLM._stream:
+        if type(self)._stream == BaseLLM._stream:  # noqa: SLF001
             # model doesn't implement streaming, so use default implementation
             yield self.invoke(input, config=config, stop=stop, **kwargs)
         else:
@@ -590,8 +590,8 @@ class BaseLLM(BaseLanguageModel[str], ABC):
         **kwargs: Any,
     ) -> AsyncIterator[str]:
         if (
-            type(self)._astream is BaseLLM._astream
-            and type(self)._stream is BaseLLM._stream
+            type(self)._astream is BaseLLM._astream  # noqa: SLF001
+            and type(self)._stream is BaseLLM._stream  # noqa: SLF001
         ):
             yield await self.ainvoke(input, config=config, stop=stop, **kwargs)
             return

libs/core/langchain_core/messages/ai.py

@@ -194,6 +194,7 @@ class AIMessage(BaseMessage):
             "invalid_tool_calls": self.invalid_tool_calls,
         }
 
+    # TODO: remove this logic if possible, reducing breaking nature of changes
     @model_validator(mode="before")
     @classmethod
     def _backwards_compat_tool_calls(cls, values: dict) -> Any:

libs/core/langchain_core/messages/base.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 
 from typing import TYPE_CHECKING, Any, Optional, Union, cast
 
-from pydantic import ConfigDict, Field, field_validator
+from pydantic import ConfigDict, Field
 
 from langchain_core.load.serializable import Serializable
 from langchain_core.utils import get_bolded_text
@@ -52,7 +52,7 @@ class BaseMessage(Serializable):
     model implementation.
     """
 
-    id: Optional[str] = None
+    id: Optional[str] = Field(default=None, coerce_numbers_to_str=True)
     """An optional unique identifier for the message. This should ideally be
     provided by the provider/model which created the message."""
 
@@ -60,13 +60,6 @@ class BaseMessage(Serializable):
         extra="allow",
     )
 
-    @field_validator("id", mode="before")
-    def cast_id_to_str(cls, id_value: Any) -> Optional[str]:
-        """Coerce the id field to a string."""
-        if id_value is not None:
-            return str(id_value)
-        return id_value
-
     def __init__(
         self, content: Union[str, list[Union[str, dict]]], **kwargs: Any
     ) -> None:

libs/core/langchain_core/outputs/chat_generation.py

@@ -2,17 +2,14 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Literal, Union
+from typing import Literal, Union
 
-from pydantic import model_validator
+from pydantic import computed_field
 
 from langchain_core.messages import BaseMessage, BaseMessageChunk
 from langchain_core.outputs.generation import Generation
 from langchain_core.utils._merge import merge_dicts
 
-if TYPE_CHECKING:
-    from typing_extensions import Self
-
 
 class ChatGeneration(Generation):
     """A single chat generation output.
@@ -28,48 +25,30 @@ class ChatGeneration(Generation):
     via callbacks).
     """
 
-    text: str = ""
-    """*SHOULD NOT BE SET DIRECTLY* The text contents of the output message."""
     message: BaseMessage
     """The message output by the chat model."""
-    # Override type to be ChatGeneration, ignore mypy error as this is intentional
+
     type: Literal["ChatGeneration"] = "ChatGeneration"  # type: ignore[assignment]
     """Type is used exclusively for serialization purposes."""
 
-    @model_validator(mode="after")
-    def set_text(self) -> Self:
-        """Set the text attribute to be the contents of the message.
-
-        Args:
-            values: The values of the object.
-
-        Returns:
-            The values of the object with the text attribute set.
-
-        Raises:
-            ValueError: If the message is not a string or a list.
-        """
-        try:
-            text = ""
-            if isinstance(self.message.content, str):
-                text = self.message.content
-            # Assumes text in content blocks in OpenAI format.
-            # Uses first text block.
-            elif isinstance(self.message.content, list):
-                for block in self.message.content:
-                    if isinstance(block, str):
-                        text = block
-                        break
-                    if isinstance(block, dict) and "text" in block:
-                        text = block["text"]
-                        break
-            else:
-                pass
-            self.text = text
-        except (KeyError, AttributeError) as e:
-            msg = "Error while initializing ChatGeneration"
-            raise ValueError(msg) from e
-        return self
+    @computed_field  # type: ignore[prop-decorator]
+    @property
+    def text(self) -> str:
+        """Set the text attribute to be the contents of the message."""
+        text_ = ""
+        if isinstance(self.message.content, str):
+            text_ = self.message.content
+        # Assumes text in content blocks in OpenAI format.
+        # Uses first text block.
+        elif isinstance(self.message.content, list):
+            for block in self.message.content:
+                if isinstance(block, str):
+                    text_ = block
+                    break
+                if isinstance(block, dict) and "text" in block:
+                    text_ = block["text"]
+                    break
+        return text_
 
 
 class ChatGenerationChunk(ChatGeneration):
@@ -80,7 +59,7 @@ class ChatGenerationChunk(ChatGeneration):
 
     message: BaseMessageChunk
     """The message chunk output by the chat model."""
-    # Override type to be ChatGeneration, ignore mypy error as this is intentional
+
     type: Literal["ChatGenerationChunk"] = "ChatGenerationChunk"  # type: ignore[assignment]
     """Type is used exclusively for serialization purposes."""
 
@@ -115,3 +94,16 @@ class ChatGenerationChunk(ChatGeneration):
             )
         msg = f"unsupported operand type(s) for +: '{type(self)}' and '{type(other)}'"
         raise TypeError(msg)
+
+
+def merge_chat_generation_chunks(
+    chunks: list[ChatGenerationChunk],
+) -> Union[ChatGenerationChunk, None]:
+    """Merge a list of ChatGenerationChunks into a single ChatGenerationChunk."""
+    if not chunks:
+        return None
+
+    if len(chunks) == 1:
+        return chunks[0]
+
+    return chunks[0] + chunks[1:]

libs/core/langchain_core/outputs/generation.py

@@ -4,6 +4,8 @@ from __future__ import annotations
 
 from typing import Any, Literal, Optional
 
+from pydantic import computed_field
+
 from langchain_core.load import Serializable
 from langchain_core.utils._merge import merge_dicts
 
@@ -24,14 +26,30 @@ class Generation(Serializable):
     for more information.
     """
 
-    text: str
-    """Generated text output."""
+    def __init__(
+        self,
+        text: str = "",
+        generation_info: Optional[dict[str, Any]] = None,
+        **kwargs: Any,
+    ):
+        """Initialize a Generation."""
+        super().__init__(generation_info=generation_info, **kwargs)
+        self._text = text
+
+    # workaround for ChatGeneration so that we can use a computed field to populate
+    # the text field from the message content (parent class needs to have a property)
+    @computed_field  # type: ignore[prop-decorator]
+    @property
+    def text(self) -> str:
+        """The text contents of the output."""
+        return self._text
 
     generation_info: Optional[dict[str, Any]] = None
     """Raw response from the provider.
 
     May include things like the reason for finishing or token log probabilities.
     """
+
     type: Literal["Generation"] = "Generation"
     """Type is used exclusively for serialization purposes.
     Set to "Generation" for this class."""
@@ -53,6 +71,16 @@ class Generation(Serializable):
 class GenerationChunk(Generation):
     """Generation chunk, which can be concatenated with other Generation chunks."""
 
+    def __init__(
+        self,
+        text: str = "",
+        generation_info: Optional[dict[str, Any]] = None,
+        **kwargs: Any,
+    ):
+        """Initialize a GenerationChunk."""
+        super().__init__(text=text, generation_info=generation_info, **kwargs)
+        self._text = text
+
     def __add__(self, other: GenerationChunk) -> GenerationChunk:
         """Concatenate two GenerationChunks."""
         if isinstance(other, GenerationChunk):

libs/core/langchain_core/runnables/configurable.py

@@ -131,7 +131,7 @@ class DynamicRunnable(RunnableSerializable[Input, Output]):
         """
         runnable: Runnable[Input, Output] = self
         while isinstance(runnable, DynamicRunnable):
-            runnable, config = runnable._prepare(merge_configs(runnable.config, config))
+            runnable, config = runnable._prepare(merge_configs(runnable.config, config))  # noqa: SLF001
         return runnable, cast("RunnableConfig", config)
 
     @abstractmethod

libs/core/langchain_core/runnables/graph_ascii.py

@@ -163,16 +163,21 @@ class AsciiCanvas:
         self.point(x0 + width, y0 + height, "+")
 
 
+class _EdgeViewer:
+    def __init__(self) -> None:
+        self.pts: list[tuple[float]] = []
+
+    def setpath(self, pts: list[tuple[float]]) -> None:
+        self.pts = pts
+
+
 def _build_sugiyama_layout(
     vertices: Mapping[str, str], edges: Sequence[LangEdge]
 ) -> Any:
     try:
         from grandalf.graphs import Edge, Graph, Vertex  # type: ignore[import-untyped]
         from grandalf.layouts import SugiyamaLayout  # type: ignore[import-untyped]
-        from grandalf.routing import (  # type: ignore[import-untyped]
-            EdgeViewer,
-            route_with_lines,
-        )
+        from grandalf.routing import route_with_lines  # type: ignore[import-untyped]
     except ImportError as exc:
         msg = "Install grandalf to draw graphs: `pip install grandalf`."
         raise ImportError(msg) from exc
@@ -199,7 +204,7 @@ def _build_sugiyama_layout(
     minw = min(v.view.w for v in vertices_list)
 
     for edge in edges_:
-        edge.view = EdgeViewer()
+        edge.view = _EdgeViewer()
 
     sug = SugiyamaLayout(graph.C[0])
     graph = graph.C[0]
@@ -277,7 +282,7 @@ def draw_ascii(vertices: Mapping[str, str], edges: Sequence[LangEdge]) -> str:
         ylist.extend((vertex.view.xy[1], vertex.view.xy[1] + vertex.view.h))
 
     for edge in sug.g.sE:
-        for x, y in edge.view._pts:
+        for x, y in edge.view.pts:
             xlist.append(x)
             ylist.append(y)
 
@@ -293,12 +298,12 @@ def draw_ascii(vertices: Mapping[str, str], edges: Sequence[LangEdge]) -> str:
 
     # NOTE: first draw edges so that node boxes could overwrite them
     for edge in sug.g.sE:
-        if len(edge.view._pts) <= 1:
+        if len(edge.view.pts) <= 1:
             msg = "Not enough points to draw an edge"
             raise ValueError(msg)
-        for index in range(1, len(edge.view._pts)):
-            start = edge.view._pts[index - 1]
-            end = edge.view._pts[index]
+        for index in range(1, len(edge.view.pts)):
+            start = edge.view.pts[index - 1]
+            end = edge.view.pts[index]
 
             start_x = int(round(start[0] - minx))
             start_y = int(round(start[1] - miny))

libs/core/langchain_core/tools/base.py

@@ -845,7 +845,7 @@ class ChildTool(BaseTool):
             child_config = patch_config(config, callbacks=run_manager.get_child())
             with set_config_context(child_config) as context:
                 func_to_check = (
-                    self._run if self.__class__._arun is BaseTool._arun else self._arun
+                    self._run if self.__class__._arun is BaseTool._arun else self._arun  # noqa: SLF001
                 )
                 if signature(func_to_check).parameters.get("run_manager"):
                     tool_kwargs["run_manager"] = run_manager
@@ -1077,16 +1077,18 @@ def get_all_basemodel_annotations(
     """
     # cls has no subscript: cls = FooBar
     if isinstance(cls, type):
+        # Gather pydantic field objects (v2: model_fields / v1: __fields__)
+        fields = getattr(cls, "model_fields", {}) or getattr(cls, "__fields__", {})
+        alias_map = {field.alias: name for name, field in fields.items() if field.alias}
+
         annotations: dict[str, type] = {}
         for name, param in inspect.signature(cls).parameters.items():
             # Exclude hidden init args added by pydantic Config. For example if
             # BaseModel(extra="allow") then "extra_data" will part of init sig.
-            if (
-                fields := getattr(cls, "model_fields", {})  # pydantic v2+
-                or getattr(cls, "__fields__", {})  # pydantic v1
-            ) and name not in fields:
+            if fields and name not in fields and name not in alias_map:
                 continue
-            annotations[name] = param.annotation
+            field_name = alias_map.get(name, name)
+            annotations[field_name] = param.annotation
         orig_bases: tuple = getattr(cls, "__orig_bases__", ())
     # cls has subscript: cls = FooBar[int]
     else:

libs/core/langchain_core/tracers/langchain.py

@@ -50,8 +50,8 @@ def log_error_once(method: str, exception: Exception) -> None:
 
 def wait_for_all_tracers() -> None:
     """Wait for all tracers to finish."""
-    if rt._CLIENT is not None:
-        rt._CLIENT.flush()
+    if rt._CLIENT is not None:  # noqa: SLF001
+        rt._CLIENT.flush()  # noqa: SLF001
 
 
 def get_client() -> Client:
@@ -123,8 +123,8 @@ class LangChainTracer(BaseTracer):
                 run.tags = self.tags.copy()
 
         super()._start_trace(run)
-        if run._client is None:
-            run._client = self.client  # type: ignore[misc]
+        if run.ls_client is None:
+            run.ls_client = self.client
 
     def on_chat_model_start(
         self,

libs/core/langchain_core/utils/mustache.py

@@ -379,7 +379,7 @@ def _get_key(
             try:
                 # This allows for custom falsy data types
                 # https://github.com/noahmorrison/chevron/issues/35
-                if resolved_scope._CHEVRON_return_scope_when_falsy:  # type: ignore[union-attr]
+                if resolved_scope._CHEVRON_return_scope_when_falsy:  # type: ignore[union-attr] # noqa: SLF001
                     return resolved_scope
             except AttributeError:
                 if resolved_scope in (0, False):

libs/core/langchain_core/version.py

@@ -1,3 +1,3 @@
 """langchain-core version information and utilities."""
 
-VERSION = "0.3.59"
+VERSION = "0.3.60"

libs/core/pyproject.toml

@@ -7,17 +7,16 @@ authors = []
 license = {text = "MIT"}
 requires-python = ">=3.9"
 dependencies = [
-    "langsmith<0.4,>=0.1.125",
+    "langsmith<0.4,>=0.1.126",
     "tenacity!=8.4.0,<10.0.0,>=8.1.0",
     "jsonpatch<2.0,>=1.33",
     "PyYAML>=5.3",
     "packaging<25,>=23.2",
     "typing-extensions>=4.7",
-    "pydantic<3.0.0,>=2.5.2; python_full_version < \"3.12.4\"",
-    "pydantic<3.0.0,>=2.7.4; python_full_version >= \"3.12.4\"",
+    "pydantic>=2.7.4",
 ]
 name = "langchain-core"
-version = "0.3.59"
+version = "0.3.60"
 description = "Building applications with LLMs through composability"
 readme = "README.md"
 
@@ -106,7 +105,6 @@ ignore = [
     "ERA",
     "PLR2004",
     "RUF",
-    "SLF",
 ]
 flake8-type-checking.runtime-evaluated-base-classes = ["pydantic.BaseModel","langchain_core.load.serializable.Serializable","langchain_core.runnables.base.RunnableSerializable"]
 flake8-annotations.allow-star-arg-any = true
@@ -133,5 +131,5 @@ classmethod-decorators = [ "classmethod", "langchain_core.utils.pydantic.pre_ini
 "tests/unit_tests/runnables/test_runnable.py" = [ "E501",]
 "tests/unit_tests/runnables/test_graph.py" = [ "E501",]
 "tests/unit_tests/test_tools.py" = [ "ARG",]
-"tests/**" = [ "D", "S",]
+"tests/**" = [ "D", "S", "SLF",]
 "scripts/**" = [ "INP", "S",]

libs/core/tests/unit_tests/indexing/test_indexing.py

@@ -1882,7 +1882,7 @@ async def test_adeduplication(
     }
 
 
-def test_cleanup_with_different_batchsize(
+def test_full_cleanup_with_different_batchsize(
     record_manager: InMemoryRecordManager, vector_store: VectorStore
 ) -> None:
     """Check that we can clean up with different batch size."""
@@ -1919,7 +1919,56 @@ def test_cleanup_with_different_batchsize(
     }
 
 
-async def test_async_cleanup_with_different_batchsize(
+def test_incremental_cleanup_with_different_batchsize(
+    record_manager: InMemoryRecordManager, vector_store: VectorStore
+) -> None:
+    """Check that we can clean up with different batch size."""
+
+    docs = [
+        Document(
+            page_content="This is a test document.",
+            metadata={"source": str(d)},
+        )
+        for d in range(1000)
+    ]
+
+    assert index(
+        docs,
+        record_manager,
+        vector_store,
+        source_id_key="source",
+        cleanup="incremental",
+    ) == {
+        "num_added": 1000,
+        "num_deleted": 0,
+        "num_skipped": 0,
+        "num_updated": 0,
+    }
+
+    docs = [
+        Document(
+            page_content="Different doc",
+            metadata={"source": str(d)},
+        )
+        for d in range(1001)
+    ]
+
+    assert index(
+        docs,
+        record_manager,
+        vector_store,
+        source_id_key="source",
+        cleanup="incremental",
+        cleanup_batch_size=17,
+    ) == {
+        "num_added": 1001,
+        "num_deleted": 1000,
+        "num_skipped": 0,
+        "num_updated": 0,
+    }
+
+
+async def test_afull_cleanup_with_different_batchsize(
     arecord_manager: InMemoryRecordManager, vector_store: InMemoryVectorStore
 ) -> None:
     """Check that we can clean up with different batch size."""
@@ -1956,6 +2005,54 @@ async def test_async_cleanup_with_different_batchsize(
     }
 
 
+async def test_aincremental_cleanup_with_different_batchsize(
+    arecord_manager: InMemoryRecordManager, vector_store: InMemoryVectorStore
+) -> None:
+    """Check that we can clean up with different batch size."""
+    docs = [
+        Document(
+            page_content="This is a test document.",
+            metadata={"source": str(d)},
+        )
+        for d in range(1000)
+    ]
+
+    assert await aindex(
+        docs,
+        arecord_manager,
+        vector_store,
+        source_id_key="source",
+        cleanup="incremental",
+    ) == {
+        "num_added": 1000,
+        "num_deleted": 0,
+        "num_skipped": 0,
+        "num_updated": 0,
+    }
+
+    docs = [
+        Document(
+            page_content="Different doc",
+            metadata={"source": str(d)},
+        )
+        for d in range(1001)
+    ]
+
+    assert await aindex(
+        docs,
+        arecord_manager,
+        vector_store,
+        cleanup="incremental",
+        source_id_key="source",
+        cleanup_batch_size=17,
+    ) == {
+        "num_added": 1001,
+        "num_deleted": 1000,
+        "num_skipped": 0,
+        "num_updated": 0,
+    }
+
+
 def test_deduplication_v2(
     record_manager: InMemoryRecordManager, vector_store: VectorStore
 ) -> None:

libs/core/tests/unit_tests/test_tools.py

@@ -2146,6 +2146,15 @@ def test__get_all_basemodel_annotations_v1() -> None:
     assert actual == expected
 
 
+def test_get_all_basemodel_annotations_aliases() -> None:
+    class CalculatorInput(BaseModel):
+        a: int = Field(description="first number", alias="A")
+        b: int = Field(description="second number")
+
+    actual = get_all_basemodel_annotations(CalculatorInput)
+    assert actual == {"a": int, "b": int}
+
+
 def test_tool_annotations_preserved() -> None:
     """Test that annotations are preserved when creating a tool."""
 

libs/core/uv.lock

@@ -935,7 +935,7 @@ wheels = [
 
 [[package]]
 name = "langchain-core"
-version = "0.3.59"
+version = "0.3.60"
 source = { editable = "." }
 dependencies = [
     { name = "jsonpatch" },
@@ -984,10 +984,9 @@ typing = [
 [package.metadata]
 requires-dist = [
     { name = "jsonpatch", specifier = ">=1.33,<2.0" },
-    { name = "langsmith", specifier = ">=0.1.125,<0.4" },
+    { name = "langsmith", specifier = ">=0.1.126,<0.4" },
     { name = "packaging", specifier = ">=23.2,<25" },
-    { name = "pydantic", marker = "python_full_version < '3.12.4'", specifier = ">=2.5.2,<3.0.0" },
-    { name = "pydantic", marker = "python_full_version >= '3.12.4'", specifier = ">=2.7.4,<3.0.0" },
+    { name = "pydantic", specifier = ">=2.7.4" },
     { name = "pyyaml", specifier = ">=5.3" },
     { name = "tenacity", specifier = ">=8.1.0,!=8.4.0,<10.0.0" },
     { name = "typing-extensions", specifier = ">=4.7" },
@@ -1718,7 +1717,7 @@ wheels = [
 
 [[package]]
 name = "pydantic"
-version = "2.11.1"
+version = "2.11.4"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "annotated-types" },
@@ -1726,118 +1725,118 @@ dependencies = [
     { name = "typing-extensions" },
     { name = "typing-inspection" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/93/a3/698b87a4d4d303d7c5f62ea5fbf7a79cab236ccfbd0a17847b7f77f8163e/pydantic-2.11.1.tar.gz", hash = "sha256:442557d2910e75c991c39f4b4ab18963d57b9b55122c8b2a9cd176d8c29ce968", size = 782817 }
+sdist = { url = "https://files.pythonhosted.org/packages/77/ab/5250d56ad03884ab5efd07f734203943c8a8ab40d551e208af81d0257bf2/pydantic-2.11.4.tar.gz", hash = "sha256:32738d19d63a226a52eed76645a98ee07c1f410ee41d93b4afbfa85ed8111c2d", size = 786540 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/cc/12/f9221a949f2419e2e23847303c002476c26fbcfd62dc7f3d25d0bec5ca99/pydantic-2.11.1-py3-none-any.whl", hash = "sha256:5b6c415eee9f8123a14d859be0c84363fec6b1feb6b688d6435801230b56e0b8", size = 442648 },
+    { url = "https://files.pythonhosted.org/packages/e7/12/46b65f3534d099349e38ef6ec98b1a5a81f42536d17e0ba382c28c67ba67/pydantic-2.11.4-py3-none-any.whl", hash = "sha256:d9615eaa9ac5a063471da949c8fc16376a84afb5024688b3ff885693506764eb", size = 443900 },
 ]
 
 [[package]]
 name = "pydantic-core"
-version = "2.33.0"
+version = "2.33.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/b9/05/91ce14dfd5a3a99555fce436318cc0fd1f08c4daa32b3248ad63669ea8b4/pydantic_core-2.33.0.tar.gz", hash = "sha256:40eb8af662ba409c3cbf4a8150ad32ae73514cd7cb1f1a2113af39763dd616b3", size = 434080 }
+sdist = { url = "https://files.pythonhosted.org/packages/ad/88/5f2260bdfae97aabf98f1778d43f69574390ad787afb646292a638c923d4/pydantic_core-2.33.2.tar.gz", hash = "sha256:7cb8bc3605c29176e1b105350d2e6474142d7c1bd1d9327c4a9bdb46bf827acc", size = 435195 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/29/43/0649ad07e66b36a3fb21442b425bd0348ac162c5e686b36471f363201535/pydantic_core-2.33.0-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:71dffba8fe9ddff628c68f3abd845e91b028361d43c5f8e7b3f8b91d7d85413e", size = 2042968 },
-    { url = "https://files.pythonhosted.org/packages/a0/a6/975fea4774a459e495cb4be288efd8b041ac756a0a763f0b976d0861334b/pydantic_core-2.33.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:abaeec1be6ed535a5d7ffc2e6c390083c425832b20efd621562fbb5bff6dc518", size = 1860347 },
-    { url = "https://files.pythonhosted.org/packages/aa/49/7858dadad305101a077ec4d0c606b6425a2b134ea8d858458a6d287fd871/pydantic_core-2.33.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:759871f00e26ad3709efc773ac37b4d571de065f9dfb1778012908bcc36b3a73", size = 1910060 },
-    { url = "https://files.pythonhosted.org/packages/8d/4f/6522527911d9c5fe6d76b084d8b388d5c84b09d113247b39f91937500b34/pydantic_core-2.33.0-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:dcfebee69cd5e1c0b76a17e17e347c84b00acebb8dd8edb22d4a03e88e82a207", size = 1997129 },
-    { url = "https://files.pythonhosted.org/packages/75/d0/06f396da053e3d73001ea4787e56b4d7132a87c0b5e2e15a041e808c35cd/pydantic_core-2.33.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1b1262b912435a501fa04cd213720609e2cefa723a07c92017d18693e69bf00b", size = 2140389 },
-    { url = "https://files.pythonhosted.org/packages/f5/6b/b9ff5b69cd4ef007cf665463f3be2e481dc7eb26c4a55b2f57a94308c31a/pydantic_core-2.33.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4726f1f3f42d6a25678c67da3f0b10f148f5655813c5aca54b0d1742ba821b8f", size = 2754237 },
-    { url = "https://files.pythonhosted.org/packages/53/80/b4879de375cdf3718d05fcb60c9aa1f119d28e261dafa51b6a69c78f7178/pydantic_core-2.33.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e790954b5093dff1e3a9a2523fddc4e79722d6f07993b4cd5547825c3cbf97b5", size = 2007433 },
-    { url = "https://files.pythonhosted.org/packages/46/24/54054713dc0af98a94eab37e0f4294dfd5cd8f70b2ca9dcdccd15709fd7e/pydantic_core-2.33.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:34e7fb3abe375b5c4e64fab75733d605dda0f59827752debc99c17cb2d5f3276", size = 2123980 },
-    { url = "https://files.pythonhosted.org/packages/3a/4c/257c1cb89e14cfa6e95ebcb91b308eb1dd2b348340ff76a6e6fcfa9969e1/pydantic_core-2.33.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:ecb158fb9b9091b515213bed3061eb7deb1d3b4e02327c27a0ea714ff46b0760", size = 2087433 },
-    { url = "https://files.pythonhosted.org/packages/0c/62/927df8a39ad78ef7b82c5446e01dec9bb0043e1ad71d8f426062f5f014db/pydantic_core-2.33.0-cp310-cp310-musllinux_1_1_armv7l.whl", hash = "sha256:4d9149e7528af8bbd76cc055967e6e04617dcb2a2afdaa3dea899406c5521faa", size = 2260242 },
-    { url = "https://files.pythonhosted.org/packages/74/f2/389414f7c77a100954e84d6f52a82bd1788ae69db72364376d8a73b38765/pydantic_core-2.33.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:e81a295adccf73477220e15ff79235ca9dcbcee4be459eb9d4ce9a2763b8386c", size = 2258227 },
-    { url = "https://files.pythonhosted.org/packages/53/99/94516313e15d906a1264bb40faf24a01a4af4e2ca8a7c10dd173b6513c5a/pydantic_core-2.33.0-cp310-cp310-win32.whl", hash = "sha256:f22dab23cdbce2005f26a8f0c71698457861f97fc6318c75814a50c75e87d025", size = 1925523 },
-    { url = "https://files.pythonhosted.org/packages/7d/67/cc789611c6035a0b71305a1ec6ba196256ced76eba8375f316f840a70456/pydantic_core-2.33.0-cp310-cp310-win_amd64.whl", hash = "sha256:9cb2390355ba084c1ad49485d18449b4242da344dea3e0fe10babd1f0db7dcfc", size = 1951872 },
-    { url = "https://files.pythonhosted.org/packages/f0/93/9e97af2619b4026596487a79133e425c7d3c374f0a7f100f3d76bcdf9c83/pydantic_core-2.33.0-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:a608a75846804271cf9c83e40bbb4dab2ac614d33c6fd5b0c6187f53f5c593ef", size = 2042784 },
-    { url = "https://files.pythonhosted.org/packages/42/b4/0bba8412fd242729feeb80e7152e24f0e1a1c19f4121ca3d4a307f4e6222/pydantic_core-2.33.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e1c69aa459f5609dec2fa0652d495353accf3eda5bdb18782bc5a2ae45c9273a", size = 1858179 },
-    { url = "https://files.pythonhosted.org/packages/69/1f/c1c40305d929bd08af863df64b0a26203b70b352a1962d86f3bcd52950fe/pydantic_core-2.33.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b9ec80eb5a5f45a2211793f1c4aeddff0c3761d1c70d684965c1807e923a588b", size = 1909396 },
-    { url = "https://files.pythonhosted.org/packages/0f/99/d2e727375c329c1e652b5d450fbb9d56e8c3933a397e4bd46e67c68c2cd5/pydantic_core-2.33.0-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e925819a98318d17251776bd3d6aa9f3ff77b965762155bdad15d1a9265c4cfd", size = 1998264 },
-    { url = "https://files.pythonhosted.org/packages/9c/2e/3119a33931278d96ecc2e9e1b9d50c240636cfeb0c49951746ae34e4de74/pydantic_core-2.33.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5bf68bb859799e9cec3d9dd8323c40c00a254aabb56fe08f907e437005932f2b", size = 2140588 },
-    { url = "https://files.pythonhosted.org/packages/35/bd/9267bd1ba55f17c80ef6cb7e07b3890b4acbe8eb6014f3102092d53d9300/pydantic_core-2.33.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1b2ea72dea0825949a045fa4071f6d5b3d7620d2a208335207793cf29c5a182d", size = 2746296 },
-    { url = "https://files.pythonhosted.org/packages/6f/ed/ef37de6478a412ee627cbebd73e7b72a680f45bfacce9ff1199de6e17e88/pydantic_core-2.33.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1583539533160186ac546b49f5cde9ffc928062c96920f58bd95de32ffd7bffd", size = 2005555 },
-    { url = "https://files.pythonhosted.org/packages/dd/84/72c8d1439585d8ee7bc35eb8f88a04a4d302ee4018871f1f85ae1b0c6625/pydantic_core-2.33.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:23c3e77bf8a7317612e5c26a3b084c7edeb9552d645742a54a5867635b4f2453", size = 2124452 },
-    { url = "https://files.pythonhosted.org/packages/a7/8f/cb13de30c6a3e303423751a529a3d1271c2effee4b98cf3e397a66ae8498/pydantic_core-2.33.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:a7a7f2a3f628d2f7ef11cb6188bcf0b9e1558151d511b974dfea10a49afe192b", size = 2087001 },
-    { url = "https://files.pythonhosted.org/packages/83/d0/e93dc8884bf288a63fedeb8040ac8f29cb71ca52e755f48e5170bb63e55b/pydantic_core-2.33.0-cp311-cp311-musllinux_1_1_armv7l.whl", hash = "sha256:f1fb026c575e16f673c61c7b86144517705865173f3d0907040ac30c4f9f5915", size = 2261663 },
-    { url = "https://files.pythonhosted.org/packages/4c/ba/4b7739c95efa0b542ee45fd872c8f6b1884ab808cf04ce7ac6621b6df76e/pydantic_core-2.33.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:635702b2fed997e0ac256b2cfbdb4dd0bf7c56b5d8fba8ef03489c03b3eb40e2", size = 2257786 },
-    { url = "https://files.pythonhosted.org/packages/cc/98/73cbca1d2360c27752cfa2fcdcf14d96230e92d7d48ecd50499865c56bf7/pydantic_core-2.33.0-cp311-cp311-win32.whl", hash = "sha256:07b4ced28fccae3f00626eaa0c4001aa9ec140a29501770a88dbbb0966019a86", size = 1925697 },
-    { url = "https://files.pythonhosted.org/packages/9a/26/d85a40edeca5d8830ffc33667d6fef329fd0f4bc0c5181b8b0e206cfe488/pydantic_core-2.33.0-cp311-cp311-win_amd64.whl", hash = "sha256:4927564be53239a87770a5f86bdc272b8d1fbb87ab7783ad70255b4ab01aa25b", size = 1949859 },
-    { url = "https://files.pythonhosted.org/packages/7e/0b/5a381605f0b9870465b805f2c86c06b0a7c191668ebe4117777306c2c1e5/pydantic_core-2.33.0-cp311-cp311-win_arm64.whl", hash = "sha256:69297418ad644d521ea3e1aa2e14a2a422726167e9ad22b89e8f1130d68e1e9a", size = 1907978 },
-    { url = "https://files.pythonhosted.org/packages/a9/c4/c9381323cbdc1bb26d352bc184422ce77c4bc2f2312b782761093a59fafc/pydantic_core-2.33.0-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:6c32a40712e3662bebe524abe8abb757f2fa2000028d64cc5a1006016c06af43", size = 2025127 },
-    { url = "https://files.pythonhosted.org/packages/6f/bd/af35278080716ecab8f57e84515c7dc535ed95d1c7f52c1c6f7b313a9dab/pydantic_core-2.33.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8ec86b5baa36f0a0bfb37db86c7d52652f8e8aa076ab745ef7725784183c3fdd", size = 1851687 },
-    { url = "https://files.pythonhosted.org/packages/12/e4/a01461225809c3533c23bd1916b1e8c2e21727f0fea60ab1acbffc4e2fca/pydantic_core-2.33.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4deac83a8cc1d09e40683be0bc6d1fa4cde8df0a9bf0cda5693f9b0569ac01b6", size = 1892232 },
-    { url = "https://files.pythonhosted.org/packages/51/17/3d53d62a328fb0a49911c2962036b9e7a4f781b7d15e9093c26299e5f76d/pydantic_core-2.33.0-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:175ab598fb457a9aee63206a1993874badf3ed9a456e0654273e56f00747bbd6", size = 1977896 },
-    { url = "https://files.pythonhosted.org/packages/30/98/01f9d86e02ec4a38f4b02086acf067f2c776b845d43f901bd1ee1c21bc4b/pydantic_core-2.33.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5f36afd0d56a6c42cf4e8465b6441cf546ed69d3a4ec92724cc9c8c61bd6ecf4", size = 2127717 },
-    { url = "https://files.pythonhosted.org/packages/3c/43/6f381575c61b7c58b0fd0b92134c5a1897deea4cdfc3d47567b3ff460a4e/pydantic_core-2.33.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0a98257451164666afafc7cbf5fb00d613e33f7e7ebb322fbcd99345695a9a61", size = 2680287 },
-    { url = "https://files.pythonhosted.org/packages/01/42/c0d10d1451d161a9a0da9bbef023b8005aa26e9993a8cc24dc9e3aa96c93/pydantic_core-2.33.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ecc6d02d69b54a2eb83ebcc6f29df04957f734bcf309d346b4f83354d8376862", size = 2008276 },
-    { url = "https://files.pythonhosted.org/packages/20/ca/e08df9dba546905c70bae44ced9f3bea25432e34448d95618d41968f40b7/pydantic_core-2.33.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:1a69b7596c6603afd049ce7f3835bcf57dd3892fc7279f0ddf987bebed8caa5a", size = 2115305 },
-    { url = "https://files.pythonhosted.org/packages/03/1f/9b01d990730a98833113581a78e595fd40ed4c20f9693f5a658fb5f91eff/pydantic_core-2.33.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:ea30239c148b6ef41364c6f51d103c2988965b643d62e10b233b5efdca8c0099", size = 2068999 },
-    { url = "https://files.pythonhosted.org/packages/20/18/fe752476a709191148e8b1e1139147841ea5d2b22adcde6ee6abb6c8e7cf/pydantic_core-2.33.0-cp312-cp312-musllinux_1_1_armv7l.whl", hash = "sha256:abfa44cf2f7f7d7a199be6c6ec141c9024063205545aa09304349781b9a125e6", size = 2241488 },
-    { url = "https://files.pythonhosted.org/packages/81/22/14738ad0a0bf484b928c9e52004f5e0b81dd8dabbdf23b843717b37a71d1/pydantic_core-2.33.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:20d4275f3c4659d92048c70797e5fdc396c6e4446caf517ba5cad2db60cd39d3", size = 2248430 },
-    { url = "https://files.pythonhosted.org/packages/e8/27/be7571e215ac8d321712f2433c445b03dbcd645366a18f67b334df8912bc/pydantic_core-2.33.0-cp312-cp312-win32.whl", hash = "sha256:918f2013d7eadea1d88d1a35fd4a1e16aaf90343eb446f91cb091ce7f9b431a2", size = 1908353 },
-    { url = "https://files.pythonhosted.org/packages/be/3a/be78f28732f93128bd0e3944bdd4b3970b389a1fbd44907c97291c8dcdec/pydantic_core-2.33.0-cp312-cp312-win_amd64.whl", hash = "sha256:aec79acc183865bad120b0190afac467c20b15289050648b876b07777e67ea48", size = 1955956 },
-    { url = "https://files.pythonhosted.org/packages/21/26/b8911ac74faa994694b76ee6a22875cc7a4abea3c381fdba4edc6c6bef84/pydantic_core-2.33.0-cp312-cp312-win_arm64.whl", hash = "sha256:5461934e895968655225dfa8b3be79e7e927e95d4bd6c2d40edd2fa7052e71b6", size = 1903259 },
-    { url = "https://files.pythonhosted.org/packages/79/20/de2ad03ce8f5b3accf2196ea9b44f31b0cd16ac6e8cfc6b21976ed45ec35/pydantic_core-2.33.0-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:f00e8b59e1fc8f09d05594aa7d2b726f1b277ca6155fc84c0396db1b373c4555", size = 2032214 },
-    { url = "https://files.pythonhosted.org/packages/f9/af/6817dfda9aac4958d8b516cbb94af507eb171c997ea66453d4d162ae8948/pydantic_core-2.33.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:1a73be93ecef45786d7d95b0c5e9b294faf35629d03d5b145b09b81258c7cd6d", size = 1852338 },
-    { url = "https://files.pythonhosted.org/packages/44/f3/49193a312d9c49314f2b953fb55740b7c530710977cabe7183b8ef111b7f/pydantic_core-2.33.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ff48a55be9da6930254565ff5238d71d5e9cd8c5487a191cb85df3bdb8c77365", size = 1896913 },
-    { url = "https://files.pythonhosted.org/packages/06/e0/c746677825b2e29a2fa02122a8991c83cdd5b4c5f638f0664d4e35edd4b2/pydantic_core-2.33.0-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:26a4ea04195638dcd8c53dadb545d70badba51735b1594810e9768c2c0b4a5da", size = 1986046 },
-    { url = "https://files.pythonhosted.org/packages/11/ec/44914e7ff78cef16afb5e5273d480c136725acd73d894affdbe2a1bbaad5/pydantic_core-2.33.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:41d698dcbe12b60661f0632b543dbb119e6ba088103b364ff65e951610cb7ce0", size = 2128097 },
-    { url = "https://files.pythonhosted.org/packages/fe/f5/c6247d424d01f605ed2e3802f338691cae17137cee6484dce9f1ac0b872b/pydantic_core-2.33.0-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ae62032ef513fe6281ef0009e30838a01057b832dc265da32c10469622613885", size = 2681062 },
-    { url = "https://files.pythonhosted.org/packages/f0/85/114a2113b126fdd7cf9a9443b1b1fe1b572e5bd259d50ba9d5d3e1927fa9/pydantic_core-2.33.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f225f3a3995dbbc26affc191d0443c6c4aa71b83358fd4c2b7d63e2f6f0336f9", size = 2007487 },
-    { url = "https://files.pythonhosted.org/packages/e6/40/3c05ed28d225c7a9acd2b34c5c8010c279683a870219b97e9f164a5a8af0/pydantic_core-2.33.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:5bdd36b362f419c78d09630cbaebc64913f66f62bda6d42d5fbb08da8cc4f181", size = 2121382 },
-    { url = "https://files.pythonhosted.org/packages/8a/22/e70c086f41eebd323e6baa92cc906c3f38ddce7486007eb2bdb3b11c8f64/pydantic_core-2.33.0-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:2a0147c0bef783fd9abc9f016d66edb6cac466dc54a17ec5f5ada08ff65caf5d", size = 2072473 },
-    { url = "https://files.pythonhosted.org/packages/3e/84/d1614dedd8fe5114f6a0e348bcd1535f97d76c038d6102f271433cd1361d/pydantic_core-2.33.0-cp313-cp313-musllinux_1_1_armv7l.whl", hash = "sha256:c860773a0f205926172c6644c394e02c25421dc9a456deff16f64c0e299487d3", size = 2249468 },
-    { url = "https://files.pythonhosted.org/packages/b0/c0/787061eef44135e00fddb4b56b387a06c303bfd3884a6df9bea5cb730230/pydantic_core-2.33.0-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:138d31e3f90087f42aa6286fb640f3c7a8eb7bdae829418265e7e7474bd2574b", size = 2254716 },
-    { url = "https://files.pythonhosted.org/packages/ae/e2/27262eb04963201e89f9c280f1e10c493a7a37bc877e023f31aa72d2f911/pydantic_core-2.33.0-cp313-cp313-win32.whl", hash = "sha256:d20cbb9d3e95114325780f3cfe990f3ecae24de7a2d75f978783878cce2ad585", size = 1916450 },
-    { url = "https://files.pythonhosted.org/packages/13/8d/25ff96f1e89b19e0b70b3cd607c9ea7ca27e1dcb810a9cd4255ed6abf869/pydantic_core-2.33.0-cp313-cp313-win_amd64.whl", hash = "sha256:ca1103d70306489e3d006b0f79db8ca5dd3c977f6f13b2c59ff745249431a606", size = 1956092 },
-    { url = "https://files.pythonhosted.org/packages/1b/64/66a2efeff657b04323ffcd7b898cb0354d36dae3a561049e092134a83e9c/pydantic_core-2.33.0-cp313-cp313-win_arm64.whl", hash = "sha256:6291797cad239285275558e0a27872da735b05c75d5237bbade8736f80e4c225", size = 1908367 },
-    { url = "https://files.pythonhosted.org/packages/52/54/295e38769133363d7ec4a5863a4d579f331728c71a6644ff1024ee529315/pydantic_core-2.33.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:7b79af799630af263eca9ec87db519426d8c9b3be35016eddad1832bac812d87", size = 1813331 },
-    { url = "https://files.pythonhosted.org/packages/4c/9c/0c8ea02db8d682aa1ef48938abae833c1d69bdfa6e5ec13b21734b01ae70/pydantic_core-2.33.0-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:eabf946a4739b5237f4f56d77fa6668263bc466d06a8036c055587c130a46f7b", size = 1986653 },
-    { url = "https://files.pythonhosted.org/packages/8e/4f/3fb47d6cbc08c7e00f92300e64ba655428c05c56b8ab6723bd290bae6458/pydantic_core-2.33.0-cp313-cp313t-win_amd64.whl", hash = "sha256:8a1d581e8cdbb857b0e0e81df98603376c1a5c34dc5e54039dcc00f043df81e7", size = 1931234 },
-    { url = "https://files.pythonhosted.org/packages/32/b1/933e907c395a17c2ffa551112da2e6e725a200f951a91f61ae0b595a437d/pydantic_core-2.33.0-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:7c9c84749f5787781c1c45bb99f433402e484e515b40675a5d121ea14711cf61", size = 2043225 },
-    { url = "https://files.pythonhosted.org/packages/05/92/86daeceaa2cf5e054fcc73e0fa17fe210aa004baf3d0530e4e0b4a0f08ce/pydantic_core-2.33.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:64672fa888595a959cfeff957a654e947e65bbe1d7d82f550417cbd6898a1d6b", size = 1877319 },
-    { url = "https://files.pythonhosted.org/packages/20/c0/fab069cff6986c596a28af96f720ff84ec3ee5de6487f274e2b2f2d79c55/pydantic_core-2.33.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:26bc7367c0961dec292244ef2549afa396e72e28cc24706210bd44d947582c59", size = 1910568 },
-    { url = "https://files.pythonhosted.org/packages/6d/b5/c02cba6e0c661eb62eb1588a5775ba3e14d80f04071d684a8bd8ae1ca75b/pydantic_core-2.33.0-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:ce72d46eb201ca43994303025bd54d8a35a3fc2a3495fac653d6eb7205ce04f4", size = 1997899 },
-    { url = "https://files.pythonhosted.org/packages/cc/dc/96a4bb1ea6777e0329d609ade93cc3dca9bc71fd9cbe3f044c8ac39e7c24/pydantic_core-2.33.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:14229c1504287533dbf6b1fc56f752ce2b4e9694022ae7509631ce346158de11", size = 2140646 },
-    { url = "https://files.pythonhosted.org/packages/88/3d/9c8ce0dc418fa9b10bc994449ca6d251493525a6debc5f73b07a367b3ced/pydantic_core-2.33.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:085d8985b1c1e48ef271e98a658f562f29d89bda98bf120502283efbc87313eb", size = 2753924 },
-    { url = "https://files.pythonhosted.org/packages/17/d6/a9cee7d4689d51bfd01107c2ec8de394f56e974ea4ae7e2d624712bed67a/pydantic_core-2.33.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:31860fbda80d8f6828e84b4a4d129fd9c4535996b8249cfb8c720dc2a1a00bb8", size = 2008316 },
-    { url = "https://files.pythonhosted.org/packages/d5/ea/c2578b67b28f3e51323841632e217a5fdd0a8f3fce852bb16782e637cda7/pydantic_core-2.33.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:f200b2f20856b5a6c3a35f0d4e344019f805e363416e609e9b47c552d35fd5ea", size = 2124634 },
-    { url = "https://files.pythonhosted.org/packages/1f/ae/236dbc8085a88aec1fd8369c6062fff3b40463918af90d20a2058b967f0e/pydantic_core-2.33.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:5f72914cfd1d0176e58ddc05c7a47674ef4222c8253bf70322923e73e14a4ac3", size = 2087826 },
-    { url = "https://files.pythonhosted.org/packages/12/ad/8292aebcd787b03167a62df5221e613b76b263b5a05c2310217e88772b75/pydantic_core-2.33.0-cp39-cp39-musllinux_1_1_armv7l.whl", hash = "sha256:91301a0980a1d4530d4ba7e6a739ca1a6b31341252cb709948e0aca0860ce0ae", size = 2260866 },
-    { url = "https://files.pythonhosted.org/packages/83/f9/d89c9e306f69395fb5b0d6e83e99980046c2b3a7cc2839a43b869838bf60/pydantic_core-2.33.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:7419241e17c7fbe5074ba79143d5523270e04f86f1b3a0dff8df490f84c8273a", size = 2259118 },
-    { url = "https://files.pythonhosted.org/packages/30/f1/4da918dcd75898006a6b4da848f231306a2d8b2fda35c7679df76a4ae3d7/pydantic_core-2.33.0-cp39-cp39-win32.whl", hash = "sha256:7a25493320203005d2a4dac76d1b7d953cb49bce6d459d9ae38e30dd9f29bc9c", size = 1925241 },
-    { url = "https://files.pythonhosted.org/packages/4f/53/a31aaa220ac133f05e4e3622f65ad9b02e6cbd89723d8d035f5effac8701/pydantic_core-2.33.0-cp39-cp39-win_amd64.whl", hash = "sha256:82a4eba92b7ca8af1b7d5ef5f3d9647eee94d1f74d21ca7c21e3a2b92e008358", size = 1953427 },
-    { url = "https://files.pythonhosted.org/packages/44/77/85e173b715e1a277ce934f28d877d82492df13e564fa68a01c96f36a47ad/pydantic_core-2.33.0-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:e2762c568596332fdab56b07060c8ab8362c56cf2a339ee54e491cd503612c50", size = 2040129 },
-    { url = "https://files.pythonhosted.org/packages/33/e7/33da5f8a94bbe2191cfcd15bd6d16ecd113e67da1b8c78d3cc3478112dab/pydantic_core-2.33.0-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:5bf637300ff35d4f59c006fff201c510b2b5e745b07125458a5389af3c0dff8c", size = 1872656 },
-    { url = "https://files.pythonhosted.org/packages/b4/7a/9600f222bea840e5b9ba1f17c0acc79b669b24542a78c42c6a10712c0aae/pydantic_core-2.33.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:62c151ce3d59ed56ebd7ce9ce5986a409a85db697d25fc232f8e81f195aa39a1", size = 1903731 },
-    { url = "https://files.pythonhosted.org/packages/81/d2/94c7ca4e24c5dcfb74df92e0836c189e9eb6814cf62d2f26a75ea0a906db/pydantic_core-2.33.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9ee65f0cc652261744fd07f2c6e6901c914aa6c5ff4dcfaf1136bc394d0dd26b", size = 2083966 },
-    { url = "https://files.pythonhosted.org/packages/b8/74/a0259989d220e8865ed6866a6d40539e40fa8f507e587e35d2414cc081f8/pydantic_core-2.33.0-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:024d136ae44d233e6322027bbf356712b3940bee816e6c948ce4b90f18471b3d", size = 2118951 },
-    { url = "https://files.pythonhosted.org/packages/13/4c/87405ed04d6d07597920b657f082a8e8e58bf3034178bb9044b4d57a91e2/pydantic_core-2.33.0-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:e37f10f6d4bc67c58fbd727108ae1d8b92b397355e68519f1e4a7babb1473442", size = 2079632 },
-    { url = "https://files.pythonhosted.org/packages/5a/4c/bcb02970ef91d4cd6de7c6893101302637da456bc8b52c18ea0d047b55ce/pydantic_core-2.33.0-pp310-pypy310_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:502ed542e0d958bd12e7c3e9a015bce57deaf50eaa8c2e1c439b512cb9db1e3a", size = 2250541 },
-    { url = "https://files.pythonhosted.org/packages/a3/2b/dbe5450c4cd904be5da736dcc7f2357b828199e29e38de19fc81f988b288/pydantic_core-2.33.0-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:715c62af74c236bf386825c0fdfa08d092ab0f191eb5b4580d11c3189af9d330", size = 2255685 },
-    { url = "https://files.pythonhosted.org/packages/ca/a6/ca1d35f695d81f639c5617fc9efb44caad21a9463383fa45364b3044175a/pydantic_core-2.33.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:bccc06fa0372151f37f6b69834181aa9eb57cf8665ed36405fb45fbf6cac3bae", size = 2082395 },
-    { url = "https://files.pythonhosted.org/packages/2b/b2/553e42762e7b08771fca41c0230c1ac276f9e79e78f57628e1b7d328551d/pydantic_core-2.33.0-pp311-pypy311_pp73-macosx_10_12_x86_64.whl", hash = "sha256:5d8dc9f63a26f7259b57f46a7aab5af86b2ad6fbe48487500bb1f4b27e051e4c", size = 2041207 },
-    { url = "https://files.pythonhosted.org/packages/85/81/a91a57bbf3efe53525ab75f65944b8950e6ef84fe3b9a26c1ec173363263/pydantic_core-2.33.0-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:30369e54d6d0113d2aa5aee7a90d17f225c13d87902ace8fcd7bbf99b19124db", size = 1873736 },
-    { url = "https://files.pythonhosted.org/packages/9c/d2/5ab52e9f551cdcbc1ee99a0b3ef595f56d031f66f88e5ca6726c49f9ce65/pydantic_core-2.33.0-pp311-pypy311_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f3eb479354c62067afa62f53bb387827bee2f75c9c79ef25eef6ab84d4b1ae3b", size = 1903794 },
-    { url = "https://files.pythonhosted.org/packages/2f/5f/a81742d3f3821b16f1265f057d6e0b68a3ab13a814fe4bffac536a1f26fd/pydantic_core-2.33.0-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0310524c833d91403c960b8a3cf9f46c282eadd6afd276c8c5edc617bd705dc9", size = 2083457 },
-    { url = "https://files.pythonhosted.org/packages/b5/2f/e872005bc0fc47f9c036b67b12349a8522d32e3bda928e82d676e2a594d1/pydantic_core-2.33.0-pp311-pypy311_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:eddb18a00bbb855325db27b4c2a89a4ba491cd6a0bd6d852b225172a1f54b36c", size = 2119537 },
-    { url = "https://files.pythonhosted.org/packages/d3/13/183f13ce647202eaf3dada9e42cdfc59cbb95faedd44d25f22b931115c7f/pydantic_core-2.33.0-pp311-pypy311_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:ade5dbcf8d9ef8f4b28e682d0b29f3008df9842bb5ac48ac2c17bc55771cc976", size = 2080069 },
-    { url = "https://files.pythonhosted.org/packages/23/8b/b6be91243da44a26558d9c3a9007043b3750334136c6550551e8092d6d96/pydantic_core-2.33.0-pp311-pypy311_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:2c0afd34f928383e3fd25740f2050dbac9d077e7ba5adbaa2227f4d4f3c8da5c", size = 2251618 },
-    { url = "https://files.pythonhosted.org/packages/aa/c5/fbcf1977035b834f63eb542e74cd6c807177f383386175b468f0865bcac4/pydantic_core-2.33.0-pp311-pypy311_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:7da333f21cd9df51d5731513a6d39319892947604924ddf2e24a4612975fb936", size = 2255374 },
-    { url = "https://files.pythonhosted.org/packages/2f/f8/66f328e411f1c9574b13c2c28ab01f308b53688bbbe6ca8fb981e6cabc42/pydantic_core-2.33.0-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:4b6d77c75a57f041c5ee915ff0b0bb58eabb78728b69ed967bc5b780e8f701b8", size = 2082099 },
-    { url = "https://files.pythonhosted.org/packages/a7/b2/7d0182cb46cfa1e003a5a52b6a15d50ad3c191a34ca5e6f5726a56ac016f/pydantic_core-2.33.0-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:ba95691cf25f63df53c1d342413b41bd7762d9acb425df8858d7efa616c0870e", size = 2040349 },
-    { url = "https://files.pythonhosted.org/packages/58/9f/dc18700d82cd4e053ff02155d40cff89b08d8583668a0b54ca1b223d3132/pydantic_core-2.33.0-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:4f1ab031feb8676f6bd7c85abec86e2935850bf19b84432c64e3e239bffeb1ec", size = 1873052 },
-    { url = "https://files.pythonhosted.org/packages/06/a9/a30a2603121b5841dc2b8dea4e18db74fa83c8c9d4804401dec23bcd3bb0/pydantic_core-2.33.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:58c1151827eef98b83d49b6ca6065575876a02d2211f259fb1a6b7757bd24dd8", size = 1904205 },
-    { url = "https://files.pythonhosted.org/packages/53/b7/cc7638fd83ad8bb19cab297e3f0a669bd9633830833865c064a74ff5a1c1/pydantic_core-2.33.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a66d931ea2c1464b738ace44b7334ab32a2fd50be023d863935eb00f42be1778", size = 2084567 },
-    { url = "https://files.pythonhosted.org/packages/c4/f0/37ba8bdc15d2c233b2a3675160cc1b205e30dd9ef4cd6d3dfe069799e160/pydantic_core-2.33.0-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:0bcf0bab28995d483f6c8d7db25e0d05c3efa5cebfd7f56474359e7137f39856", size = 2119072 },
-    { url = "https://files.pythonhosted.org/packages/eb/29/e553e2e9c16e5ad9370e947f15585db4f7438ab4b52c53f93695c99831cd/pydantic_core-2.33.0-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:89670d7a0045acb52be0566df5bc8b114ac967c662c06cf5e0c606e4aadc964b", size = 2080432 },
-    { url = "https://files.pythonhosted.org/packages/65/ca/268cae039ea91366ba88b9a848977b7189cb7675cb2cd9ee273464a20d91/pydantic_core-2.33.0-pp39-pypy39_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:b716294e721d8060908dbebe32639b01bfe61b15f9f57bcc18ca9a0e00d9520b", size = 2251007 },
-    { url = "https://files.pythonhosted.org/packages/3c/a4/5ca3a14b5d992e63a766b8883d4ba8b4d353ef6a2d9f59ee5d60e728998a/pydantic_core-2.33.0-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:fc53e05c16697ff0c1c7c2b98e45e131d4bfb78068fffff92a82d169cbb4c7b7", size = 2256435 },
-    { url = "https://files.pythonhosted.org/packages/da/a2/2670964d7046025b96f8c6d35c38e5310ec6aa1681e4158ef31ab21a4727/pydantic_core-2.33.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:68504959253303d3ae9406b634997a2123a0b0c1da86459abbd0ffc921695eac", size = 2082790 },
+    { url = "https://files.pythonhosted.org/packages/e5/92/b31726561b5dae176c2d2c2dc43a9c5bfba5d32f96f8b4c0a600dd492447/pydantic_core-2.33.2-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:2b3d326aaef0c0399d9afffeb6367d5e26ddc24d351dbc9c636840ac355dc5d8", size = 2028817 },
+    { url = "https://files.pythonhosted.org/packages/a3/44/3f0b95fafdaca04a483c4e685fe437c6891001bf3ce8b2fded82b9ea3aa1/pydantic_core-2.33.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:0e5b2671f05ba48b94cb90ce55d8bdcaaedb8ba00cc5359f6810fc918713983d", size = 1861357 },
+    { url = "https://files.pythonhosted.org/packages/30/97/e8f13b55766234caae05372826e8e4b3b96e7b248be3157f53237682e43c/pydantic_core-2.33.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0069c9acc3f3981b9ff4cdfaf088e98d83440a4c7ea1bc07460af3d4dc22e72d", size = 1898011 },
+    { url = "https://files.pythonhosted.org/packages/9b/a3/99c48cf7bafc991cc3ee66fd544c0aae8dc907b752f1dad2d79b1b5a471f/pydantic_core-2.33.2-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d53b22f2032c42eaaf025f7c40c2e3b94568ae077a606f006d206a463bc69572", size = 1982730 },
+    { url = "https://files.pythonhosted.org/packages/de/8e/a5b882ec4307010a840fb8b58bd9bf65d1840c92eae7534c7441709bf54b/pydantic_core-2.33.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0405262705a123b7ce9f0b92f123334d67b70fd1f20a9372b907ce1080c7ba02", size = 2136178 },
+    { url = "https://files.pythonhosted.org/packages/e4/bb/71e35fc3ed05af6834e890edb75968e2802fe98778971ab5cba20a162315/pydantic_core-2.33.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4b25d91e288e2c4e0662b8038a28c6a07eaac3e196cfc4ff69de4ea3db992a1b", size = 2736462 },
+    { url = "https://files.pythonhosted.org/packages/31/0d/c8f7593e6bc7066289bbc366f2235701dcbebcd1ff0ef8e64f6f239fb47d/pydantic_core-2.33.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6bdfe4b3789761f3bcb4b1ddf33355a71079858958e3a552f16d5af19768fef2", size = 2005652 },
+    { url = "https://files.pythonhosted.org/packages/d2/7a/996d8bd75f3eda405e3dd219ff5ff0a283cd8e34add39d8ef9157e722867/pydantic_core-2.33.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:efec8db3266b76ef9607c2c4c419bdb06bf335ae433b80816089ea7585816f6a", size = 2113306 },
+    { url = "https://files.pythonhosted.org/packages/ff/84/daf2a6fb2db40ffda6578a7e8c5a6e9c8affb251a05c233ae37098118788/pydantic_core-2.33.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:031c57d67ca86902726e0fae2214ce6770bbe2f710dc33063187a68744a5ecac", size = 2073720 },
+    { url = "https://files.pythonhosted.org/packages/77/fb/2258da019f4825128445ae79456a5499c032b55849dbd5bed78c95ccf163/pydantic_core-2.33.2-cp310-cp310-musllinux_1_1_armv7l.whl", hash = "sha256:f8de619080e944347f5f20de29a975c2d815d9ddd8be9b9b7268e2e3ef68605a", size = 2244915 },
+    { url = "https://files.pythonhosted.org/packages/d8/7a/925ff73756031289468326e355b6fa8316960d0d65f8b5d6b3a3e7866de7/pydantic_core-2.33.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:73662edf539e72a9440129f231ed3757faab89630d291b784ca99237fb94db2b", size = 2241884 },
+    { url = "https://files.pythonhosted.org/packages/0b/b0/249ee6d2646f1cdadcb813805fe76265745c4010cf20a8eba7b0e639d9b2/pydantic_core-2.33.2-cp310-cp310-win32.whl", hash = "sha256:0a39979dcbb70998b0e505fb1556a1d550a0781463ce84ebf915ba293ccb7e22", size = 1910496 },
+    { url = "https://files.pythonhosted.org/packages/66/ff/172ba8f12a42d4b552917aa65d1f2328990d3ccfc01d5b7c943ec084299f/pydantic_core-2.33.2-cp310-cp310-win_amd64.whl", hash = "sha256:b0379a2b24882fef529ec3b4987cb5d003b9cda32256024e6fe1586ac45fc640", size = 1955019 },
+    { url = "https://files.pythonhosted.org/packages/3f/8d/71db63483d518cbbf290261a1fc2839d17ff89fce7089e08cad07ccfce67/pydantic_core-2.33.2-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:4c5b0a576fb381edd6d27f0a85915c6daf2f8138dc5c267a57c08a62900758c7", size = 2028584 },
+    { url = "https://files.pythonhosted.org/packages/24/2f/3cfa7244ae292dd850989f328722d2aef313f74ffc471184dc509e1e4e5a/pydantic_core-2.33.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e799c050df38a639db758c617ec771fd8fb7a5f8eaaa4b27b101f266b216a246", size = 1855071 },
+    { url = "https://files.pythonhosted.org/packages/b3/d3/4ae42d33f5e3f50dd467761304be2fa0a9417fbf09735bc2cce003480f2a/pydantic_core-2.33.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dc46a01bf8d62f227d5ecee74178ffc448ff4e5197c756331f71efcc66dc980f", size = 1897823 },
+    { url = "https://files.pythonhosted.org/packages/f4/f3/aa5976e8352b7695ff808599794b1fba2a9ae2ee954a3426855935799488/pydantic_core-2.33.2-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:a144d4f717285c6d9234a66778059f33a89096dfb9b39117663fd8413d582dcc", size = 1983792 },
+    { url = "https://files.pythonhosted.org/packages/d5/7a/cda9b5a23c552037717f2b2a5257e9b2bfe45e687386df9591eff7b46d28/pydantic_core-2.33.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:73cf6373c21bc80b2e0dc88444f41ae60b2f070ed02095754eb5a01df12256de", size = 2136338 },
+    { url = "https://files.pythonhosted.org/packages/2b/9f/b8f9ec8dd1417eb9da784e91e1667d58a2a4a7b7b34cf4af765ef663a7e5/pydantic_core-2.33.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3dc625f4aa79713512d1976fe9f0bc99f706a9dee21dfd1810b4bbbf228d0e8a", size = 2730998 },
+    { url = "https://files.pythonhosted.org/packages/47/bc/cd720e078576bdb8255d5032c5d63ee5c0bf4b7173dd955185a1d658c456/pydantic_core-2.33.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:881b21b5549499972441da4758d662aeea93f1923f953e9cbaff14b8b9565aef", size = 2003200 },
+    { url = "https://files.pythonhosted.org/packages/ca/22/3602b895ee2cd29d11a2b349372446ae9727c32e78a94b3d588a40fdf187/pydantic_core-2.33.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:bdc25f3681f7b78572699569514036afe3c243bc3059d3942624e936ec93450e", size = 2113890 },
+    { url = "https://files.pythonhosted.org/packages/ff/e6/e3c5908c03cf00d629eb38393a98fccc38ee0ce8ecce32f69fc7d7b558a7/pydantic_core-2.33.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:fe5b32187cbc0c862ee201ad66c30cf218e5ed468ec8dc1cf49dec66e160cc4d", size = 2073359 },
+    { url = "https://files.pythonhosted.org/packages/12/e7/6a36a07c59ebefc8777d1ffdaf5ae71b06b21952582e4b07eba88a421c79/pydantic_core-2.33.2-cp311-cp311-musllinux_1_1_armv7l.whl", hash = "sha256:bc7aee6f634a6f4a95676fcb5d6559a2c2a390330098dba5e5a5f28a2e4ada30", size = 2245883 },
+    { url = "https://files.pythonhosted.org/packages/16/3f/59b3187aaa6cc0c1e6616e8045b284de2b6a87b027cce2ffcea073adf1d2/pydantic_core-2.33.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:235f45e5dbcccf6bd99f9f472858849f73d11120d76ea8707115415f8e5ebebf", size = 2241074 },
+    { url = "https://files.pythonhosted.org/packages/e0/ed/55532bb88f674d5d8f67ab121a2a13c385df382de2a1677f30ad385f7438/pydantic_core-2.33.2-cp311-cp311-win32.whl", hash = "sha256:6368900c2d3ef09b69cb0b913f9f8263b03786e5b2a387706c5afb66800efd51", size = 1910538 },
+    { url = "https://files.pythonhosted.org/packages/fe/1b/25b7cccd4519c0b23c2dd636ad39d381abf113085ce4f7bec2b0dc755eb1/pydantic_core-2.33.2-cp311-cp311-win_amd64.whl", hash = "sha256:1e063337ef9e9820c77acc768546325ebe04ee38b08703244c1309cccc4f1bab", size = 1952909 },
+    { url = "https://files.pythonhosted.org/packages/49/a9/d809358e49126438055884c4366a1f6227f0f84f635a9014e2deb9b9de54/pydantic_core-2.33.2-cp311-cp311-win_arm64.whl", hash = "sha256:6b99022f1d19bc32a4c2a0d544fc9a76e3be90f0b3f4af413f87d38749300e65", size = 1897786 },
+    { url = "https://files.pythonhosted.org/packages/18/8a/2b41c97f554ec8c71f2a8a5f85cb56a8b0956addfe8b0efb5b3d77e8bdc3/pydantic_core-2.33.2-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:a7ec89dc587667f22b6a0b6579c249fca9026ce7c333fc142ba42411fa243cdc", size = 2009000 },
+    { url = "https://files.pythonhosted.org/packages/a1/02/6224312aacb3c8ecbaa959897af57181fb6cf3a3d7917fd44d0f2917e6f2/pydantic_core-2.33.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:3c6db6e52c6d70aa0d00d45cdb9b40f0433b96380071ea80b09277dba021ddf7", size = 1847996 },
+    { url = "https://files.pythonhosted.org/packages/d6/46/6dcdf084a523dbe0a0be59d054734b86a981726f221f4562aed313dbcb49/pydantic_core-2.33.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4e61206137cbc65e6d5256e1166f88331d3b6238e082d9f74613b9b765fb9025", size = 1880957 },
+    { url = "https://files.pythonhosted.org/packages/ec/6b/1ec2c03837ac00886ba8160ce041ce4e325b41d06a034adbef11339ae422/pydantic_core-2.33.2-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:eb8c529b2819c37140eb51b914153063d27ed88e3bdc31b71198a198e921e011", size = 1964199 },
+    { url = "https://files.pythonhosted.org/packages/2d/1d/6bf34d6adb9debd9136bd197ca72642203ce9aaaa85cfcbfcf20f9696e83/pydantic_core-2.33.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c52b02ad8b4e2cf14ca7b3d918f3eb0ee91e63b3167c32591e57c4317e134f8f", size = 2120296 },
+    { url = "https://files.pythonhosted.org/packages/e0/94/2bd0aaf5a591e974b32a9f7123f16637776c304471a0ab33cf263cf5591a/pydantic_core-2.33.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:96081f1605125ba0855dfda83f6f3df5ec90c61195421ba72223de35ccfb2f88", size = 2676109 },
+    { url = "https://files.pythonhosted.org/packages/f9/41/4b043778cf9c4285d59742281a769eac371b9e47e35f98ad321349cc5d61/pydantic_core-2.33.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8f57a69461af2a5fa6e6bbd7a5f60d3b7e6cebb687f55106933188e79ad155c1", size = 2002028 },
+    { url = "https://files.pythonhosted.org/packages/cb/d5/7bb781bf2748ce3d03af04d5c969fa1308880e1dca35a9bd94e1a96a922e/pydantic_core-2.33.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:572c7e6c8bb4774d2ac88929e3d1f12bc45714ae5ee6d9a788a9fb35e60bb04b", size = 2100044 },
+    { url = "https://files.pythonhosted.org/packages/fe/36/def5e53e1eb0ad896785702a5bbfd25eed546cdcf4087ad285021a90ed53/pydantic_core-2.33.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:db4b41f9bd95fbe5acd76d89920336ba96f03e149097365afe1cb092fceb89a1", size = 2058881 },
+    { url = "https://files.pythonhosted.org/packages/01/6c/57f8d70b2ee57fc3dc8b9610315949837fa8c11d86927b9bb044f8705419/pydantic_core-2.33.2-cp312-cp312-musllinux_1_1_armv7l.whl", hash = "sha256:fa854f5cf7e33842a892e5c73f45327760bc7bc516339fda888c75ae60edaeb6", size = 2227034 },
+    { url = "https://files.pythonhosted.org/packages/27/b9/9c17f0396a82b3d5cbea4c24d742083422639e7bb1d5bf600e12cb176a13/pydantic_core-2.33.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:5f483cfb75ff703095c59e365360cb73e00185e01aaea067cd19acffd2ab20ea", size = 2234187 },
+    { url = "https://files.pythonhosted.org/packages/b0/6a/adf5734ffd52bf86d865093ad70b2ce543415e0e356f6cacabbc0d9ad910/pydantic_core-2.33.2-cp312-cp312-win32.whl", hash = "sha256:9cb1da0f5a471435a7bc7e439b8a728e8b61e59784b2af70d7c169f8dd8ae290", size = 1892628 },
+    { url = "https://files.pythonhosted.org/packages/43/e4/5479fecb3606c1368d496a825d8411e126133c41224c1e7238be58b87d7e/pydantic_core-2.33.2-cp312-cp312-win_amd64.whl", hash = "sha256:f941635f2a3d96b2973e867144fde513665c87f13fe0e193c158ac51bfaaa7b2", size = 1955866 },
+    { url = "https://files.pythonhosted.org/packages/0d/24/8b11e8b3e2be9dd82df4b11408a67c61bb4dc4f8e11b5b0fc888b38118b5/pydantic_core-2.33.2-cp312-cp312-win_arm64.whl", hash = "sha256:cca3868ddfaccfbc4bfb1d608e2ccaaebe0ae628e1416aeb9c4d88c001bb45ab", size = 1888894 },
+    { url = "https://files.pythonhosted.org/packages/46/8c/99040727b41f56616573a28771b1bfa08a3d3fe74d3d513f01251f79f172/pydantic_core-2.33.2-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:1082dd3e2d7109ad8b7da48e1d4710c8d06c253cbc4a27c1cff4fbcaa97a9e3f", size = 2015688 },
+    { url = "https://files.pythonhosted.org/packages/3a/cc/5999d1eb705a6cefc31f0b4a90e9f7fc400539b1a1030529700cc1b51838/pydantic_core-2.33.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:f517ca031dfc037a9c07e748cefd8d96235088b83b4f4ba8939105d20fa1dcd6", size = 1844808 },
+    { url = "https://files.pythonhosted.org/packages/6f/5e/a0a7b8885c98889a18b6e376f344da1ef323d270b44edf8174d6bce4d622/pydantic_core-2.33.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0a9f2c9dd19656823cb8250b0724ee9c60a82f3cdf68a080979d13092a3b0fef", size = 1885580 },
+    { url = "https://files.pythonhosted.org/packages/3b/2a/953581f343c7d11a304581156618c3f592435523dd9d79865903272c256a/pydantic_core-2.33.2-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:2b0a451c263b01acebe51895bfb0e1cc842a5c666efe06cdf13846c7418caa9a", size = 1973859 },
+    { url = "https://files.pythonhosted.org/packages/e6/55/f1a813904771c03a3f97f676c62cca0c0a4138654107c1b61f19c644868b/pydantic_core-2.33.2-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1ea40a64d23faa25e62a70ad163571c0b342b8bf66d5fa612ac0dec4f069d916", size = 2120810 },
+    { url = "https://files.pythonhosted.org/packages/aa/c3/053389835a996e18853ba107a63caae0b9deb4a276c6b472931ea9ae6e48/pydantic_core-2.33.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0fb2d542b4d66f9470e8065c5469ec676978d625a8b7a363f07d9a501a9cb36a", size = 2676498 },
+    { url = "https://files.pythonhosted.org/packages/eb/3c/f4abd740877a35abade05e437245b192f9d0ffb48bbbbd708df33d3cda37/pydantic_core-2.33.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9fdac5d6ffa1b5a83bca06ffe7583f5576555e6c8b3a91fbd25ea7780f825f7d", size = 2000611 },
+    { url = "https://files.pythonhosted.org/packages/59/a7/63ef2fed1837d1121a894d0ce88439fe3e3b3e48c7543b2a4479eb99c2bd/pydantic_core-2.33.2-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:04a1a413977ab517154eebb2d326da71638271477d6ad87a769102f7c2488c56", size = 2107924 },
+    { url = "https://files.pythonhosted.org/packages/04/8f/2551964ef045669801675f1cfc3b0d74147f4901c3ffa42be2ddb1f0efc4/pydantic_core-2.33.2-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:c8e7af2f4e0194c22b5b37205bfb293d166a7344a5b0d0eaccebc376546d77d5", size = 2063196 },
+    { url = "https://files.pythonhosted.org/packages/26/bd/d9602777e77fc6dbb0c7db9ad356e9a985825547dce5ad1d30ee04903918/pydantic_core-2.33.2-cp313-cp313-musllinux_1_1_armv7l.whl", hash = "sha256:5c92edd15cd58b3c2d34873597a1e20f13094f59cf88068adb18947df5455b4e", size = 2236389 },
+    { url = "https://files.pythonhosted.org/packages/42/db/0e950daa7e2230423ab342ae918a794964b053bec24ba8af013fc7c94846/pydantic_core-2.33.2-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:65132b7b4a1c0beded5e057324b7e16e10910c106d43675d9bd87d4f38dde162", size = 2239223 },
+    { url = "https://files.pythonhosted.org/packages/58/4d/4f937099c545a8a17eb52cb67fe0447fd9a373b348ccfa9a87f141eeb00f/pydantic_core-2.33.2-cp313-cp313-win32.whl", hash = "sha256:52fb90784e0a242bb96ec53f42196a17278855b0f31ac7c3cc6f5c1ec4811849", size = 1900473 },
+    { url = "https://files.pythonhosted.org/packages/a0/75/4a0a9bac998d78d889def5e4ef2b065acba8cae8c93696906c3a91f310ca/pydantic_core-2.33.2-cp313-cp313-win_amd64.whl", hash = "sha256:c083a3bdd5a93dfe480f1125926afcdbf2917ae714bdb80b36d34318b2bec5d9", size = 1955269 },
+    { url = "https://files.pythonhosted.org/packages/f9/86/1beda0576969592f1497b4ce8e7bc8cbdf614c352426271b1b10d5f0aa64/pydantic_core-2.33.2-cp313-cp313-win_arm64.whl", hash = "sha256:e80b087132752f6b3d714f041ccf74403799d3b23a72722ea2e6ba2e892555b9", size = 1893921 },
+    { url = "https://files.pythonhosted.org/packages/a4/7d/e09391c2eebeab681df2b74bfe6c43422fffede8dc74187b2b0bf6fd7571/pydantic_core-2.33.2-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:61c18fba8e5e9db3ab908620af374db0ac1baa69f0f32df4f61ae23f15e586ac", size = 1806162 },
+    { url = "https://files.pythonhosted.org/packages/f1/3d/847b6b1fed9f8ed3bb95a9ad04fbd0b212e832d4f0f50ff4d9ee5a9f15cf/pydantic_core-2.33.2-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95237e53bb015f67b63c91af7518a62a8660376a6a0db19b89acc77a4d6199f5", size = 1981560 },
+    { url = "https://files.pythonhosted.org/packages/6f/9a/e73262f6c6656262b5fdd723ad90f518f579b7bc8622e43a942eec53c938/pydantic_core-2.33.2-cp313-cp313t-win_amd64.whl", hash = "sha256:c2fc0a768ef76c15ab9238afa6da7f69895bb5d1ee83aeea2e3509af4472d0b9", size = 1935777 },
+    { url = "https://files.pythonhosted.org/packages/53/ea/bbe9095cdd771987d13c82d104a9c8559ae9aec1e29f139e286fd2e9256e/pydantic_core-2.33.2-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:a2b911a5b90e0374d03813674bf0a5fbbb7741570dcd4b4e85a2e48d17def29d", size = 2028677 },
+    { url = "https://files.pythonhosted.org/packages/49/1d/4ac5ed228078737d457a609013e8f7edc64adc37b91d619ea965758369e5/pydantic_core-2.33.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:6fa6dfc3e4d1f734a34710f391ae822e0a8eb8559a85c6979e14e65ee6ba2954", size = 1864735 },
+    { url = "https://files.pythonhosted.org/packages/23/9a/2e70d6388d7cda488ae38f57bc2f7b03ee442fbcf0d75d848304ac7e405b/pydantic_core-2.33.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c54c939ee22dc8e2d545da79fc5381f1c020d6d3141d3bd747eab59164dc89fb", size = 1898467 },
+    { url = "https://files.pythonhosted.org/packages/ff/2e/1568934feb43370c1ffb78a77f0baaa5a8b6897513e7a91051af707ffdc4/pydantic_core-2.33.2-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:53a57d2ed685940a504248187d5685e49eb5eef0f696853647bf37c418c538f7", size = 1983041 },
+    { url = "https://files.pythonhosted.org/packages/01/1a/1a1118f38ab64eac2f6269eb8c120ab915be30e387bb561e3af904b12499/pydantic_core-2.33.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:09fb9dd6571aacd023fe6aaca316bd01cf60ab27240d7eb39ebd66a3a15293b4", size = 2136503 },
+    { url = "https://files.pythonhosted.org/packages/5c/da/44754d1d7ae0f22d6d3ce6c6b1486fc07ac2c524ed8f6eca636e2e1ee49b/pydantic_core-2.33.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0e6116757f7959a712db11f3e9c0a99ade00a5bbedae83cb801985aa154f071b", size = 2736079 },
+    { url = "https://files.pythonhosted.org/packages/4d/98/f43cd89172220ec5aa86654967b22d862146bc4d736b1350b4c41e7c9c03/pydantic_core-2.33.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8d55ab81c57b8ff8548c3e4947f119551253f4e3787a7bbc0b6b3ca47498a9d3", size = 2006508 },
+    { url = "https://files.pythonhosted.org/packages/2b/cc/f77e8e242171d2158309f830f7d5d07e0531b756106f36bc18712dc439df/pydantic_core-2.33.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:c20c462aa4434b33a2661701b861604913f912254e441ab8d78d30485736115a", size = 2113693 },
+    { url = "https://files.pythonhosted.org/packages/54/7a/7be6a7bd43e0a47c147ba7fbf124fe8aaf1200bc587da925509641113b2d/pydantic_core-2.33.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:44857c3227d3fb5e753d5fe4a3420d6376fa594b07b621e220cd93703fe21782", size = 2074224 },
+    { url = "https://files.pythonhosted.org/packages/2a/07/31cf8fadffbb03be1cb520850e00a8490c0927ec456e8293cafda0726184/pydantic_core-2.33.2-cp39-cp39-musllinux_1_1_armv7l.whl", hash = "sha256:eb9b459ca4df0e5c87deb59d37377461a538852765293f9e6ee834f0435a93b9", size = 2245403 },
+    { url = "https://files.pythonhosted.org/packages/b6/8d/bbaf4c6721b668d44f01861f297eb01c9b35f612f6b8e14173cb204e6240/pydantic_core-2.33.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:9fcd347d2cc5c23b06de6d3b7b8275be558a0c90549495c699e379a80bf8379e", size = 2242331 },
+    { url = "https://files.pythonhosted.org/packages/bb/93/3cc157026bca8f5006250e74515119fcaa6d6858aceee8f67ab6dc548c16/pydantic_core-2.33.2-cp39-cp39-win32.whl", hash = "sha256:83aa99b1285bc8f038941ddf598501a86f1536789740991d7d8756e34f1e74d9", size = 1910571 },
+    { url = "https://files.pythonhosted.org/packages/5b/90/7edc3b2a0d9f0dda8806c04e511a67b0b7a41d2187e2003673a996fb4310/pydantic_core-2.33.2-cp39-cp39-win_amd64.whl", hash = "sha256:f481959862f57f29601ccced557cc2e817bce7533ab8e01a797a48b49c9692b3", size = 1956504 },
+    { url = "https://files.pythonhosted.org/packages/30/68/373d55e58b7e83ce371691f6eaa7175e3a24b956c44628eb25d7da007917/pydantic_core-2.33.2-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:5c4aa4e82353f65e548c476b37e64189783aa5384903bfea4f41580f255fddfa", size = 2023982 },
+    { url = "https://files.pythonhosted.org/packages/a4/16/145f54ac08c96a63d8ed6442f9dec17b2773d19920b627b18d4f10a061ea/pydantic_core-2.33.2-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:d946c8bf0d5c24bf4fe333af284c59a19358aa3ec18cb3dc4370080da1e8ad29", size = 1858412 },
+    { url = "https://files.pythonhosted.org/packages/41/b1/c6dc6c3e2de4516c0bb2c46f6a373b91b5660312342a0cf5826e38ad82fa/pydantic_core-2.33.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:87b31b6846e361ef83fedb187bb5b4372d0da3f7e28d85415efa92d6125d6e6d", size = 1892749 },
+    { url = "https://files.pythonhosted.org/packages/12/73/8cd57e20afba760b21b742106f9dbdfa6697f1570b189c7457a1af4cd8a0/pydantic_core-2.33.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aa9d91b338f2df0508606f7009fde642391425189bba6d8c653afd80fd6bb64e", size = 2067527 },
+    { url = "https://files.pythonhosted.org/packages/e3/d5/0bb5d988cc019b3cba4a78f2d4b3854427fc47ee8ec8e9eaabf787da239c/pydantic_core-2.33.2-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:2058a32994f1fde4ca0480ab9d1e75a0e8c87c22b53a3ae66554f9af78f2fe8c", size = 2108225 },
+    { url = "https://files.pythonhosted.org/packages/f1/c5/00c02d1571913d496aabf146106ad8239dc132485ee22efe08085084ff7c/pydantic_core-2.33.2-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:0e03262ab796d986f978f79c943fc5f620381be7287148b8010b4097f79a39ec", size = 2069490 },
+    { url = "https://files.pythonhosted.org/packages/22/a8/dccc38768274d3ed3a59b5d06f59ccb845778687652daa71df0cab4040d7/pydantic_core-2.33.2-pp310-pypy310_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:1a8695a8d00c73e50bff9dfda4d540b7dee29ff9b8053e38380426a85ef10052", size = 2237525 },
+    { url = "https://files.pythonhosted.org/packages/d4/e7/4f98c0b125dda7cf7ccd14ba936218397b44f50a56dd8c16a3091df116c3/pydantic_core-2.33.2-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:fa754d1850735a0b0e03bcffd9d4b4343eb417e47196e4485d9cca326073a42c", size = 2238446 },
+    { url = "https://files.pythonhosted.org/packages/ce/91/2ec36480fdb0b783cd9ef6795753c1dea13882f2e68e73bce76ae8c21e6a/pydantic_core-2.33.2-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:a11c8d26a50bfab49002947d3d237abe4d9e4b5bdc8846a63537b6488e197808", size = 2066678 },
+    { url = "https://files.pythonhosted.org/packages/7b/27/d4ae6487d73948d6f20dddcd94be4ea43e74349b56eba82e9bdee2d7494c/pydantic_core-2.33.2-pp311-pypy311_pp73-macosx_10_12_x86_64.whl", hash = "sha256:dd14041875d09cc0f9308e37a6f8b65f5585cf2598a53aa0123df8b129d481f8", size = 2025200 },
+    { url = "https://files.pythonhosted.org/packages/f1/b8/b3cb95375f05d33801024079b9392a5ab45267a63400bf1866e7ce0f0de4/pydantic_core-2.33.2-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:d87c561733f66531dced0da6e864f44ebf89a8fba55f31407b00c2f7f9449593", size = 1859123 },
+    { url = "https://files.pythonhosted.org/packages/05/bc/0d0b5adeda59a261cd30a1235a445bf55c7e46ae44aea28f7bd6ed46e091/pydantic_core-2.33.2-pp311-pypy311_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2f82865531efd18d6e07a04a17331af02cb7a651583c418df8266f17a63c6612", size = 1892852 },
+    { url = "https://files.pythonhosted.org/packages/3e/11/d37bdebbda2e449cb3f519f6ce950927b56d62f0b84fd9cb9e372a26a3d5/pydantic_core-2.33.2-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2bfb5112df54209d820d7bf9317c7a6c9025ea52e49f46b6a2060104bba37de7", size = 2067484 },
+    { url = "https://files.pythonhosted.org/packages/8c/55/1f95f0a05ce72ecb02a8a8a1c3be0579bbc29b1d5ab68f1378b7bebc5057/pydantic_core-2.33.2-pp311-pypy311_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:64632ff9d614e5eecfb495796ad51b0ed98c453e447a76bcbeeb69615079fc7e", size = 2108896 },
+    { url = "https://files.pythonhosted.org/packages/53/89/2b2de6c81fa131f423246a9109d7b2a375e83968ad0800d6e57d0574629b/pydantic_core-2.33.2-pp311-pypy311_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:f889f7a40498cc077332c7ab6b4608d296d852182211787d4f3ee377aaae66e8", size = 2069475 },
+    { url = "https://files.pythonhosted.org/packages/b8/e9/1f7efbe20d0b2b10f6718944b5d8ece9152390904f29a78e68d4e7961159/pydantic_core-2.33.2-pp311-pypy311_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:de4b83bb311557e439b9e186f733f6c645b9417c84e2eb8203f3f820a4b988bf", size = 2239013 },
+    { url = "https://files.pythonhosted.org/packages/3c/b2/5309c905a93811524a49b4e031e9851a6b00ff0fb668794472ea7746b448/pydantic_core-2.33.2-pp311-pypy311_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:82f68293f055f51b51ea42fafc74b6aad03e70e191799430b90c13d643059ebb", size = 2238715 },
+    { url = "https://files.pythonhosted.org/packages/32/56/8a7ca5d2cd2cda1d245d34b1c9a942920a718082ae8e54e5f3e5a58b7add/pydantic_core-2.33.2-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:329467cecfb529c925cf2bbd4d60d2c509bc2fb52a20c1045bf09bb70971a9c1", size = 2066757 },
+    { url = "https://files.pythonhosted.org/packages/08/98/dbf3fdfabaf81cda5622154fda78ea9965ac467e3239078e0dcd6df159e7/pydantic_core-2.33.2-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:87acbfcf8e90ca885206e98359d7dca4bcbb35abdc0ff66672a293e1d7a19101", size = 2024034 },
+    { url = "https://files.pythonhosted.org/packages/8d/99/7810aa9256e7f2ccd492590f86b79d370df1e9292f1f80b000b6a75bd2fb/pydantic_core-2.33.2-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:7f92c15cd1e97d4b12acd1cc9004fa092578acfa57b67ad5e43a197175d01a64", size = 1858578 },
+    { url = "https://files.pythonhosted.org/packages/d8/60/bc06fa9027c7006cc6dd21e48dbf39076dc39d9abbaf718a1604973a9670/pydantic_core-2.33.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d3f26877a748dc4251cfcfda9dfb5f13fcb034f5308388066bcfe9031b63ae7d", size = 1892858 },
+    { url = "https://files.pythonhosted.org/packages/f2/40/9d03997d9518816c68b4dfccb88969756b9146031b61cd37f781c74c9b6a/pydantic_core-2.33.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dac89aea9af8cd672fa7b510e7b8c33b0bba9a43186680550ccf23020f32d535", size = 2068498 },
+    { url = "https://files.pythonhosted.org/packages/d8/62/d490198d05d2d86672dc269f52579cad7261ced64c2df213d5c16e0aecb1/pydantic_core-2.33.2-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:970919794d126ba8645f3837ab6046fb4e72bbc057b3709144066204c19a455d", size = 2108428 },
+    { url = "https://files.pythonhosted.org/packages/9a/ec/4cd215534fd10b8549015f12ea650a1a973da20ce46430b68fc3185573e8/pydantic_core-2.33.2-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:3eb3fe62804e8f859c49ed20a8451342de53ed764150cb14ca71357c765dc2a6", size = 2069854 },
+    { url = "https://files.pythonhosted.org/packages/1a/1a/abbd63d47e1d9b0d632fee6bb15785d0889c8a6e0a6c3b5a8e28ac1ec5d2/pydantic_core-2.33.2-pp39-pypy39_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:3abcd9392a36025e3bd55f9bd38d908bd17962cc49bc6da8e7e96285336e2bca", size = 2237859 },
+    { url = "https://files.pythonhosted.org/packages/80/1c/fa883643429908b1c90598fd2642af8839efd1d835b65af1f75fba4d94fe/pydantic_core-2.33.2-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:3a1c81334778f9e3af2f8aeb7a960736e5cab1dfebfb26aabca09afd2906c039", size = 2239059 },
+    { url = "https://files.pythonhosted.org/packages/d4/29/3cade8a924a61f60ccfa10842f75eb12787e1440e2b8660ceffeb26685e7/pydantic_core-2.33.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:2807668ba86cb38c6817ad9bc66215ab8584d1d304030ce4f0887336f28a5e27", size = 2066661 },
 ]
 
 [[package]]

libs/packages.yml

@@ -5,650 +5,660 @@ packages:
 - name: langchain-core
   path: libs/core
   repo: langchain-ai/langchain
-  downloads: 51178135
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 52153634
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-text-splitters
   path: libs/text-splitters
   repo: langchain-ai/langchain
-  downloads: 18371499
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 18674701
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain
   path: libs/langchain
   repo: langchain-ai/langchain
-  downloads: 68611637
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 71877707
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-community
   path: libs/community
   repo: langchain-ai/langchain-community
-  downloads: 20961009
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 21531980
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-experimental
   path: libs/experimental
   repo: langchain-ai/langchain-experimental
-  downloads: 1651817
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 1640028
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-cli
   path: libs/cli
   repo: langchain-ai/langchain
-  downloads: 55074
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 52924
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-ai21
   path: libs/ai21
   repo: langchain-ai/langchain-ai21
-  downloads: 4684
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 4360
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-anthropic
   path: libs/partners/anthropic
   repo: langchain-ai/langchain
   js: '@langchain/anthropic'
-  downloads: 2205980
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 2260743
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-chroma
   path: libs/partners/chroma
   repo: langchain-ai/langchain
-  downloads: 934777
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 952160
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-exa
   path: libs/partners/exa
   repo: langchain-ai/langchain
   provider_page: exa_search
   js: '@langchain/exa'
-  downloads: 5949
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 6843
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-fireworks
   path: libs/partners/fireworks
   repo: langchain-ai/langchain
-  downloads: 253744
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 302517
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-groq
   path: libs/partners/groq
   repo: langchain-ai/langchain
   js: '@langchain/groq'
-  downloads: 713166
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 711682
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-huggingface
   path: libs/partners/huggingface
   repo: langchain-ai/langchain
-  downloads: 565389
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 568294
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-ibm
   path: libs/ibm
   repo: langchain-ai/langchain-ibm
   js: '@langchain/ibm'
-  downloads: 193195
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 217224
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-localai
   path: libs/localai
   repo: mkhludnev/langchain-localai
-  downloads: 811
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 762
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-milvus
   path: libs/milvus
   repo: langchain-ai/langchain-milvus
-  downloads: 207750
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 195215
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-mistralai
   path: libs/partners/mistralai
   repo: langchain-ai/langchain
   js: '@langchain/mistralai'
-  downloads: 333887
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 317214
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-mongodb
   path: libs/langchain-mongodb
   repo: langchain-ai/langchain-mongodb
   provider_page: mongodb_atlas
   js: '@langchain/mongodb'
-  downloads: 229323
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 213285
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-nomic
   path: libs/partners/nomic
   repo: langchain-ai/langchain
   js: '@langchain/nomic'
-  downloads: 13453
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 11886
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-openai
   path: libs/partners/openai
   repo: langchain-ai/langchain
   js: '@langchain/openai'
-  downloads: 12632953
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 13665726
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-pinecone
   path: libs/pinecone
   repo: langchain-ai/langchain-pinecone
   js: '@langchain/pinecone'
-  downloads: 731139
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 729476
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-prompty
   path: libs/partners/prompty
   repo: langchain-ai/langchain
   provider_page: microsoft
-  downloads: 2215
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 2138
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-qdrant
   path: libs/partners/qdrant
   repo: langchain-ai/langchain
   js: '@langchain/qdrant'
-  downloads: 156264
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 159329
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-scrapegraph
   path: .
   repo: ScrapeGraphAI/langchain-scrapegraph
-  downloads: 1338
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 1177
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-sema4
   path: libs/sema4
   repo: langchain-ai/langchain-sema4
   provider_page: robocorp
-  downloads: 1864
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 1609
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-together
   path: libs/together
   repo: langchain-ai/langchain-together
-  downloads: 84925
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 82472
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-upstage
   path: libs/upstage
   repo: langchain-ai/langchain-upstage
-  downloads: 20074
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 20558
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-voyageai
   path: libs/partners/voyageai
   repo: langchain-ai/langchain
-  downloads: 31164
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 27698
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-aws
   name_title: AWS
   path: libs/aws
   repo: langchain-ai/langchain-aws
   js: '@langchain/aws'
-  downloads: 2756214
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 2946295
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-astradb
   name_title: DataStax Astra DB
   path: libs/astradb
   repo: langchain-ai/langchain-datastax
-  downloads: 100973
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 100092
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-google-genai
   name_title: Google Generative AI
   path: libs/genai
   repo: langchain-ai/langchain-google
   provider_page: google
   js: '@langchain/google-genai'
-  downloads: 1860492
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 1951902
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-google-vertexai
   path: libs/vertexai
   repo: langchain-ai/langchain-google
   provider_page: google
   js: '@langchain/google-vertexai'
-  downloads: 14375847
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 15219755
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-google-community
   path: libs/community
   repo: langchain-ai/langchain-google
   provider_page: google
-  downloads: 4565784
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 4529167
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-weaviate
   path: libs/weaviate
   repo: langchain-ai/langchain-weaviate
   js: '@langchain/weaviate'
-  downloads: 42280
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 41265
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-cohere
   path: libs/cohere
   repo: langchain-ai/langchain-cohere
   js: '@langchain/cohere'
-  downloads: 816207
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 859764
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-elasticsearch
   path: libs/elasticsearch
   repo: langchain-ai/langchain-elastic
-  downloads: 182874
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 169912
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-nvidia-ai-endpoints
   path: libs/ai-endpoints
   repo: langchain-ai/langchain-nvidia
   provider_page: nvidia
-  downloads: 178772
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 171961
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-postgres
   path: .
   repo: langchain-ai/langchain-postgres
   provider_page: pgvector
-  downloads: 751590
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 720037
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-redis
   path: libs/redis
   repo: langchain-ai/langchain-redis
   js: '@langchain/redis'
-  downloads: 43514
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 41653
+  downloads_updated_at: '2025-05-08T20:26:05.985970+00:00'
 - name: langchain-unstructured
   path: libs/unstructured
   repo: langchain-ai/langchain-unstructured
-  downloads: 152489
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 139927
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: langchain-azure-ai
   path: libs/azure-ai
   repo: langchain-ai/langchain-azure
   provider_page: azure_ai
   js: '@langchain/openai'
-  downloads: 29862
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 27904
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: langchain-azure-dynamic-sessions
   path: libs/azure-dynamic-sessions
   repo: langchain-ai/langchain-azure
   provider_page: microsoft
   js: '@langchain/azure-dynamic-sessions'
-  downloads: 9328
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 8945
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: langchain-sqlserver
   path: libs/sqlserver
   repo: langchain-ai/langchain-azure
   provider_page: microsoft
-  downloads: 2519
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 2370
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: langchain-cerebras
   path: libs/cerebras
   repo: langchain-ai/langchain-cerebras
-  downloads: 66301
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 41520
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: langchain-snowflake
   path: libs/snowflake
   repo: langchain-ai/langchain-snowflake
-  downloads: 2235
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 2037
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: databricks-langchain
   name_title: Databricks
   path: integrations/langchain
   repo: databricks/databricks-ai-bridge
   provider_page: databricks
-  downloads: 112136
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 126587
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: langchain-couchbase
   path: .
   repo: Couchbase-Ecosystem/langchain-couchbase
-  downloads: 1251
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 1350
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: langchain-ollama
   path: libs/partners/ollama
   repo: langchain-ai/langchain
   js: '@langchain/ollama'
-  downloads: 924780
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 948591
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: langchain-box
   path: libs/box
   repo: box-community/langchain-box
-  downloads: 703
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 654
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: langchain-tests
   path: libs/standard-tests
   repo: langchain-ai/langchain
-  downloads: 267152
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 262480
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: langchain-neo4j
   path: libs/neo4j
   repo: langchain-ai/langchain-neo4j
-  downloads: 55071
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 52537
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: langchain-linkup
   path: .
   repo: LinkupPlatform/langchain-linkup
-  downloads: 782
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 616
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: langchain-yt-dlp
   path: .
   repo: aqib0770/langchain-yt-dlp
-  downloads: 2369
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 2276
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: langchain-oceanbase
   path: .
   repo: oceanbase/langchain-oceanbase
-  downloads: 73
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 68
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: langchain-predictionguard
   path: .
   repo: predictionguard/langchain-predictionguard
-  downloads: 4063
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 4351
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: langchain-cratedb
   path: .
   repo: crate/langchain-cratedb
-  downloads: 216
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 198
+  downloads_updated_at: '2025-05-08T20:26:13.914570+00:00'
 - name: langchain-modelscope
   path: .
   repo: modelscope/langchain-modelscope
-  downloads: 141
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 110
+  downloads_updated_at: '2025-05-08T20:26:23.196172+00:00'
 - name: langchain-falkordb
   path: .
   repo: kingtroga/langchain-falkordb
-  downloads: 129
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 99
+  downloads_updated_at: '2025-05-08T20:26:23.196172+00:00'
 - name: langchain-dappier
   path: .
   repo: DappierAI/langchain-dappier
-  downloads: 343
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 300
+  downloads_updated_at: '2025-05-08T20:26:23.196172+00:00'
 - name: langchain-pull-md
   path: .
   repo: chigwell/langchain-pull-md
-  downloads: 135
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 115
+  downloads_updated_at: '2025-05-08T20:26:23.196172+00:00'
 - name: langchain-kuzu
   path: .
   repo: kuzudb/langchain-kuzu
-  downloads: 760
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 777
+  downloads_updated_at: '2025-05-08T20:26:23.196172+00:00'
 - name: langchain-docling
   path: .
   repo: DS4SD/docling-langchain
-  downloads: 18845
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 19927
+  downloads_updated_at: '2025-05-08T20:26:23.196172+00:00'
 - name: langchain-lindorm-integration
   path: .
   repo: AlwaysBluer/langchain-lindorm-integration
   provider_page: lindorm
-  downloads: 69
-  downloads_updated_at: '2025-04-22T15:24:39.289813+00:00'
+  downloads: 53
+  downloads_updated_at: '2025-05-08T20:26:23.196172+00:00'
 - name: langchain-hyperbrowser
   path: .
   repo: hyperbrowserai/langchain-hyperbrowser
-  downloads: 523
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 448
+  downloads_updated_at: '2025-05-08T20:26:23.196172+00:00'
 - name: langchain-fmp-data
   path: .
   repo: MehdiZare/langchain-fmp-data
-  downloads: 108
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 122
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: tilores-langchain
   name_title: Tilores
   path: .
   repo: tilotech/tilores-langchain
   provider_page: tilores
-  downloads: 124
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 133
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-pipeshift
   path: .
   repo: pipeshift-org/langchain-pipeshift
-  downloads: 119
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 93
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-payman-tool
   path: .
   repo: paymanai/langchain-payman-tool
-  downloads: 226
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 172
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-sambanova
   path: .
   repo: sambanova/langchain-sambanova
-  downloads: 53108
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 52905
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-deepseek
   path: libs/partners/deepseek
   repo: langchain-ai/langchain
   provider_page: deepseek
   js: '@langchain/deepseek'
-  downloads: 100570
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 200311
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-jenkins
   path: .
   repo: Amitgb14/langchain_jenkins
-  downloads: 200
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 172
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-goodfire
   path: .
   repo: keenanpepper/langchain-goodfire
-  downloads: 314
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 256
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-nimble
   path: .
   repo: Nimbleway/langchain-nimble
-  downloads: 214
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 191
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-apify
   path: .
   repo: apify/langchain-apify
-  downloads: 886
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 1062
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langfair
   name_title: LangFair
   path: .
   repo: cvs-health/langfair
-  downloads: 1692
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 1663
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-abso
   path: .
   repo: lunary-ai/langchain-abso
-  downloads: 233
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 203
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-graph-retriever
   name_title: Graph RAG
   path: packages/langchain-graph-retriever
   repo: datastax/graph-rag
   provider_page: graph_rag
-  downloads: 47297
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 52322
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-xai
   path: libs/partners/xai
   repo: langchain-ai/langchain
-  downloads: 44422
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 48297
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-salesforce
   path: .
   repo: colesmcintosh/langchain-salesforce
-  downloads: 455
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 982
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-discord-shikenso
   path: .
   repo: Shikenso-Analytics/langchain-discord
-  downloads: 137
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 109
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-vdms
   name_title: VDMS
   path: .
   repo: IntelLabs/langchain-vdms
-  downloads: 11847
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 11916
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-deeplake
   path: .
   repo: activeloopai/langchain-deeplake
-  downloads: 117
-  downloads_updated_at: '2025-04-22T15:25:01.432566+00:00'
+  downloads: 63
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-cognee
   path: .
   repo: topoteretes/langchain-cognee
-  downloads: 114
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 90
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-prolog
   path: .
   repo: apisani1/langchain-prolog
-  downloads: 175
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 153
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-permit
   path: .
   repo: permitio/langchain-permit
-  downloads: 266
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 176
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-pymupdf4llm
   path: .
   repo: lakinduboteju/langchain-pymupdf4llm
-  downloads: 5324
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 6332
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-writer
   path: .
   repo: writer/langchain-writer
-  downloads: 728
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 745
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-taiga
   name_title: Taiga
   path: .
   repo: Shikenso-Analytics/langchain-taiga
-  downloads: 439
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 444
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-tableau
   name_title: Tableau
   path: .
   repo: Tab-SE/tableau_langchain
-  downloads: 551
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 543
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: ads4gpts-langchain
   name_title: ADS4GPTs
   path: libs/python-sdk/ads4gpts-langchain
   repo: ADS4GPTs/ads4gpts
   provider_page: ads4gpts
-  downloads: 626
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 521
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-contextual
   name_title: Contextual AI
   path: langchain-contextual
   repo: ContextualAI//langchain-contextual
-  downloads: 365
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 502
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-valthera
   name_title: Valthera
   path: .
   repo: valthera/langchain-valthera
-  downloads: 213
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 173
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-opengradient
   path: .
   repo: OpenGradient/og-langchain
-  downloads: 263
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 135
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: goat-sdk-adapter-langchain
   name_title: GOAT SDK
   path: python/src/adapters/langchain
   repo: goat-sdk/goat
   provider_page: goat
-  downloads: 418
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 395
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-netmind
   path: .
   repo: protagolabs/langchain-netmind
-  downloads: 65
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 47
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-agentql
   path: langchain
   repo: tinyfish-io/agentql-integrations
-  downloads: 227
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 337
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-xinference
   path: .
   repo: TheSongg/langchain-xinference
-  downloads: 132
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 103
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: powerscale-rag-connector
   name_title: PowerScale RAG Connector
   path: .
   repo: dell/powerscale-rag-connector
   provider_page: dell
-  downloads: 89
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 74
+  downloads_updated_at: '2025-05-08T20:26:32.333380+00:00'
 - name: langchain-tavily
   path: .
   repo: tavily-ai/langchain-tavily
-  include_in_api_ref: true
   js: '@langchain/tavily'
-  downloads: 13796
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 28335
+  downloads_updated_at: '2025-05-08T20:26:54.465130+00:00'
+  include_in_api_ref: true
 - name: langchain-zotero-retriever
   name_title: Zotero
   path: .
   repo: TimBMK/langchain-zotero-retriever
   provider_page: zotero
-  downloads: 72
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 60
+  downloads_updated_at: '2025-05-08T20:26:54.465130+00:00'
 - name: langchain-naver
   name_title: Naver
   path: .
   repo: NaverCloudPlatform/langchain-naver
   provider_page: naver
-  downloads: 239
-  downloads_updated_at: '2025-04-22T15:43:47.979572+00:00'
+  downloads: 682
+  downloads_updated_at: '2025-05-08T20:26:54.465130+00:00'
 - name: langchain-naver-community
   name_title: Naver (community-maintained)
   path: .
   repo: e7217/langchain-naver-community
   provider_page: naver
-  downloads: 119
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 147
+  downloads_updated_at: '2025-05-08T20:26:54.465130+00:00'
 - name: langchain-memgraph
   path: .
   repo: memgraph/langchain-memgraph
-  downloads: 222
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 929
+  downloads_updated_at: '2025-05-08T20:26:54.465130+00:00'
 - name: langchain-vectara
   path: libs/vectara
   repo: vectara/langchain-vectara
-  downloads: 284
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 265
+  downloads_updated_at: '2025-05-08T20:26:54.465130+00:00'
 - name: langchain-oxylabs
   path: .
   repo: oxylabs/langchain-oxylabs
-  downloads: 141
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 60
+  downloads_updated_at: '2025-05-08T20:26:54.465130+00:00'
 - name: langchain-perplexity
   path: libs/partners/perplexity
   repo: langchain-ai/langchain
-  downloads: 3297
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 7587
+  downloads_updated_at: '2025-05-08T20:26:54.465130+00:00'
 - name: langchain-runpod
   name_title: RunPod
   path: .
   repo: runpod/langchain-runpod
   provider_page: runpod
-  downloads: 283
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 272
+  downloads_updated_at: '2025-05-08T20:26:54.465130+00:00'
 - name: langchain-mariadb
   path: .
   repo: mariadb-corporation/langchain-mariadb
-  downloads: 428
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 497
+  downloads_updated_at: '2025-05-08T20:27:05.631733+00:00'
 - name: langchain-qwq
   path: .
   repo: yigit353/langchain-qwq
   provider_page: alibaba_cloud
-  downloads: 1062
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 794
+  downloads_updated_at: '2025-05-08T20:27:18.592135+00:00'
 - name: langchain-litellm
   path: .
   repo: akshay-dongare/langchain-litellm
-  downloads: 2114
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 4379
+  downloads_updated_at: '2025-05-08T20:27:18.592135+00:00'
 - name: langchain-cloudflare
   path: libs/langchain-cloudflare
   repo: cloudflare/langchain-cloudflare
-  downloads: 766
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 943
+  downloads_updated_at: '2025-05-08T20:27:18.592135+00:00'
 - name: langchain-ydb
   path: .
   repo: ydb-platform/langchain-ydb
-  downloads: 231
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 181
+  downloads_updated_at: '2025-05-08T20:27:18.592135+00:00'
 - name: langchain-singlestore
   name_title: SingleStore
   path: .
   repo: singlestore-labs/langchain-singlestore
-  downloads: 116
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 131
+  downloads_updated_at: '2025-05-08T20:27:18.592135+00:00'
 - name: langchain-galaxia-retriever
   path: .
   repo: rrozanski-smabbler/galaxia-langchain
   provider_page: galaxia
-  downloads: 319
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 374
+  downloads_updated_at: '2025-05-08T20:27:18.592135+00:00'
 - name: langchain-valyu
   path: .
   repo: valyu-network/langchain-valyu
-  downloads: 120
-  downloads_updated_at: '2025-04-22T15:25:24.644345+00:00'
+  downloads: 141
+  downloads_updated_at: '2025-05-08T20:27:18.592135+00:00'
 - name: langchain-hana
+  name_title: SAP HANA Cloud
   path: .
   repo: SAP/langchain-integration-for-sap-hana-cloud
-  name_title: SAP HANA Cloud
   provider_page: sap
-  downloads: 315
-  downloads_updated_at: '2025-04-27T19:45:43.938924+00:00'
+  downloads: 350
+  downloads_updated_at: '2025-05-08T20:27:18.592135+00:00'
+- name: langchain-gel
+  path: .
+  repo: geldata/langchain-gel
+  provider_page: gel
+- name: langchain-aerospike
+  path: .
+  repo: aerospike/langchain-aerospike
+- name: langchain-brightdata
+  repo: luminati-io/langchain-brightdata
+  path: .

libs/partners/anthropic/langchain_anthropic/chat_models.py

@@ -866,29 +866,46 @@ class ChatAnthropic(BaseChatModel):
         See LangChain `docs <https://python.langchain.com/docs/integrations/chat/anthropic/>`_
         for more detail.
 
-        .. code-block:: python
+        Web search:
 
-            from langchain_anthropic import ChatAnthropic
+            .. code-block:: python
 
-            llm = ChatAnthropic(model="claude-3-7-sonnet-20250219")
+                from langchain_anthropic import ChatAnthropic
 
-            tool = {"type": "text_editor_20250124", "name": "str_replace_editor"}
-            llm_with_tools = llm.bind_tools([tool])
+                llm = ChatAnthropic(model="claude-3-5-sonnet-latest")
 
-            response = llm_with_tools.invoke(
-                "There's a syntax error in my primes.py file. Can you help me fix it?"
-            )
-            print(response.text())
-            response.tool_calls
+                tool = {"type": "web_search_20250305", "name": "web_search", "max_uses": 3}
+                llm_with_tools = llm.bind_tools([tool])
 
-        .. code-block:: none
+                response = llm_with_tools.invoke(
+                    "How do I update a web app to TypeScript 5.5?"
+                )
 
-            I'd be happy to help you fix the syntax error in your primes.py file. First, let's look at the current content of the file to identify the error.
+        Text editor:
 
-            [{'name': 'str_replace_editor',
-            'args': {'command': 'view', 'path': '/repo/primes.py'},
-            'id': 'toolu_01VdNgt1YV7kGfj9LFLm6HyQ',
-            'type': 'tool_call'}]
+            .. code-block:: python
+
+                from langchain_anthropic import ChatAnthropic
+
+                llm = ChatAnthropic(model="claude-3-7-sonnet-20250219")
+
+                tool = {"type": "text_editor_20250124", "name": "str_replace_editor"}
+                llm_with_tools = llm.bind_tools([tool])
+
+                response = llm_with_tools.invoke(
+                    "There's a syntax error in my primes.py file. Can you help me fix it?"
+                )
+                print(response.text())
+                response.tool_calls
+
+            .. code-block:: none
+
+                I'd be happy to help you fix the syntax error in your primes.py file. First, let's look at the current content of the file to identify the error.
+
+                [{'name': 'str_replace_editor',
+                'args': {'command': 'view', 'path': '/repo/primes.py'},
+                'id': 'toolu_01VdNgt1YV7kGfj9LFLm6HyQ',
+                'type': 'tool_call'}]
 
     Response metadata
         .. code-block:: python
@@ -1744,6 +1761,12 @@ def _make_message_chunk_from_anthropic_event(
     # See https://github.com/anthropics/anthropic-sdk-python/blob/main/src/anthropic/lib/streaming/_messages.py  # noqa: E501
     if event.type == "message_start" and stream_usage:
         usage_metadata = _create_usage_metadata(event.message.usage)
+        # We pick up a cumulative count of output_tokens at the end of the stream,
+        # so here we zero out to avoid double counting.
+        usage_metadata["total_tokens"] = (
+            usage_metadata["total_tokens"] - usage_metadata["output_tokens"]
+        )
+        usage_metadata["output_tokens"] = 0
         if hasattr(event.message, "model"):
             response_metadata = {"model_name": event.message.model}
         else:
@@ -1817,7 +1840,11 @@ def _make_message_chunk_from_anthropic_event(
                 tool_call_chunks=[tool_call_chunk],  # type: ignore
             )
     elif event.type == "message_delta" and stream_usage:
-        usage_metadata = _create_usage_metadata(event.usage)
+        usage_metadata = UsageMetadata(
+            input_tokens=0,
+            output_tokens=event.usage.output_tokens,
+            total_tokens=event.usage.output_tokens,
+        )
         message_chunk = AIMessageChunk(
             content="",
             usage_metadata=usage_metadata,

libs/partners/anthropic/tests/integration_tests/test_chat_models.py

@@ -46,7 +46,7 @@ def test_stream() -> None:
         if token.usage_metadata is not None:
             if token.usage_metadata.get("input_tokens"):
                 chunks_with_input_token_counts += 1
-            elif token.usage_metadata.get("output_tokens"):
+            if token.usage_metadata.get("output_tokens"):
                 chunks_with_output_token_counts += 1
         chunks_with_model_name += int("model_name" in token.response_metadata)
     if chunks_with_input_token_counts != 1 or chunks_with_output_token_counts != 1:
@@ -85,7 +85,7 @@ async def test_astream() -> None:
         if token.usage_metadata is not None:
             if token.usage_metadata.get("input_tokens"):
                 chunks_with_input_token_counts += 1
-            elif token.usage_metadata.get("output_tokens"):
+            if token.usage_metadata.get("output_tokens"):
                 chunks_with_output_token_counts += 1
     if chunks_with_input_token_counts != 1 or chunks_with_output_token_counts != 1:
         raise AssertionError(
@@ -134,6 +134,9 @@ async def test_stream_usage() -> None:
     async for token in model.astream("hi"):
         assert isinstance(token, AIMessageChunk)
         assert token.usage_metadata is None
+
+
+async def test_stream_usage_override() -> None:
     # check we override with kwarg
     model = ChatAnthropic(model_name=MODEL_NAME)  # type: ignore[call-arg]
     assert model.stream_usage

libs/partners/openai/langchain_openai/chat_models/base.py

@@ -251,8 +251,6 @@ def _convert_message_to_dict(message: BaseMessage) -> dict:
         message_dict["role"] = "user"
     elif isinstance(message, AIMessage):
         message_dict["role"] = "assistant"
-        if "function_call" in message.additional_kwargs:
-            message_dict["function_call"] = message.additional_kwargs["function_call"]
         if message.tool_calls or message.invalid_tool_calls:
             message_dict["tool_calls"] = [
                 _lc_tool_call_to_openai_tool_call(tc) for tc in message.tool_calls
@@ -267,6 +265,10 @@ def _convert_message_to_dict(message: BaseMessage) -> dict:
                 {k: v for k, v in tool_call.items() if k in tool_call_supported_props}
                 for tool_call in message_dict["tool_calls"]
             ]
+        elif "function_call" in message.additional_kwargs:
+            # OpenAI raises 400 if both function_call and tool_calls are present in the
+            # same message.
+            message_dict["function_call"] = message.additional_kwargs["function_call"]
         else:
             pass
         # If tool calls present, content null value should be None not empty string.

libs/partners/openai/langchain_openai/embeddings/base.py

@@ -447,7 +447,12 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
     # please refer to
     # https://github.com/openai/openai-cookbook/blob/main/examples/Embedding_long_inputs.ipynb
     def _get_len_safe_embeddings(
-        self, texts: list[str], *, engine: str, chunk_size: Optional[int] = None
+        self,
+        texts: list[str],
+        *,
+        engine: str,
+        chunk_size: Optional[int] = None,
+        **kwargs: Any,
     ) -> list[list[float]]:
         """
         Generate length-safe embeddings for a list of texts.
@@ -465,11 +470,12 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
             List[List[float]]: A list of embeddings for each input text.
         """
         _chunk_size = chunk_size or self.chunk_size
+        client_kwargs = {**self._invocation_params, **kwargs}
         _iter, tokens, indices = self._tokenize(texts, _chunk_size)
         batched_embeddings: list[list[float]] = []
         for i in _iter:
             response = self.client.create(
-                input=tokens[i : i + _chunk_size], **self._invocation_params
+                input=tokens[i : i + _chunk_size], **client_kwargs
             )
             if not isinstance(response, dict):
                 response = response.model_dump()
@@ -483,9 +489,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
         def empty_embedding() -> list[float]:
             nonlocal _cached_empty_embedding
             if _cached_empty_embedding is None:
-                average_embedded = self.client.create(
-                    input="", **self._invocation_params
-                )
+                average_embedded = self.client.create(input="", **client_kwargs)
                 if not isinstance(average_embedded, dict):
                     average_embedded = average_embedded.model_dump()
                 _cached_empty_embedding = average_embedded["data"][0]["embedding"]
@@ -496,7 +500,12 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
     # please refer to
     # https://github.com/openai/openai-cookbook/blob/main/examples/Embedding_long_inputs.ipynb
     async def _aget_len_safe_embeddings(
-        self, texts: list[str], *, engine: str, chunk_size: Optional[int] = None
+        self,
+        texts: list[str],
+        *,
+        engine: str,
+        chunk_size: Optional[int] = None,
+        **kwargs: Any,
     ) -> list[list[float]]:
         """
         Asynchronously generate length-safe embeddings for a list of texts.
@@ -515,11 +524,12 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
         """
 
         _chunk_size = chunk_size or self.chunk_size
+        client_kwargs = {**self._invocation_params, **kwargs}
         _iter, tokens, indices = self._tokenize(texts, _chunk_size)
         batched_embeddings: list[list[float]] = []
         for i in range(0, len(tokens), _chunk_size):
             response = await self.async_client.create(
-                input=tokens[i : i + _chunk_size], **self._invocation_params
+                input=tokens[i : i + _chunk_size], **client_kwargs
             )
 
             if not isinstance(response, dict):
@@ -535,7 +545,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
             nonlocal _cached_empty_embedding
             if _cached_empty_embedding is None:
                 average_embedded = await self.async_client.create(
-                    input="", **self._invocation_params
+                    input="", **client_kwargs
                 )
                 if not isinstance(average_embedded, dict):
                     average_embedded = average_embedded.model_dump()
@@ -545,7 +555,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
         return [e if e is not None else await empty_embedding() for e in embeddings]
 
     def embed_documents(
-        self, texts: list[str], chunk_size: int | None = None
+        self, texts: list[str], chunk_size: Optional[int] = None, **kwargs: Any
     ) -> list[list[float]]:
         """Call out to OpenAI's embedding endpoint for embedding search docs.
 
@@ -553,16 +563,18 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
             texts: The list of texts to embed.
             chunk_size: The chunk size of embeddings. If None, will use the chunk size
                 specified by the class.
+            kwargs: Additional keyword arguments to pass to the embedding API.
 
         Returns:
             List of embeddings, one for each text.
         """
         chunk_size_ = chunk_size or self.chunk_size
+        client_kwargs = {**self._invocation_params, **kwargs}
         if not self.check_embedding_ctx_length:
             embeddings: list[list[float]] = []
             for i in range(0, len(texts), chunk_size_):
                 response = self.client.create(
-                    input=texts[i : i + chunk_size_], **self._invocation_params
+                    input=texts[i : i + chunk_size_], **client_kwargs
                 )
                 if not isinstance(response, dict):
                     response = response.model_dump()
@@ -573,11 +585,11 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
         #       than the maximum context and use length-safe embedding function.
         engine = cast(str, self.deployment)
         return self._get_len_safe_embeddings(
-            texts, engine=engine, chunk_size=chunk_size
+            texts, engine=engine, chunk_size=chunk_size, **kwargs
         )
 
     async def aembed_documents(
-        self, texts: list[str], chunk_size: int | None = None
+        self, texts: list[str], chunk_size: Optional[int] = None, **kwargs: Any
     ) -> list[list[float]]:
         """Call out to OpenAI's embedding endpoint async for embedding search docs.
 
@@ -585,16 +597,18 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
             texts: The list of texts to embed.
             chunk_size: The chunk size of embeddings. If None, will use the chunk size
                 specified by the class.
+            kwargs: Additional keyword arguments to pass to the embedding API.
 
         Returns:
             List of embeddings, one for each text.
         """
         chunk_size_ = chunk_size or self.chunk_size
+        client_kwargs = {**self._invocation_params, **kwargs}
         if not self.check_embedding_ctx_length:
             embeddings: list[list[float]] = []
             for i in range(0, len(texts), chunk_size_):
                 response = await self.async_client.create(
-                    input=texts[i : i + chunk_size_], **self._invocation_params
+                    input=texts[i : i + chunk_size_], **client_kwargs
                 )
                 if not isinstance(response, dict):
                     response = response.model_dump()
@@ -605,28 +619,30 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
         #       than the maximum context and use length-safe embedding function.
         engine = cast(str, self.deployment)
         return await self._aget_len_safe_embeddings(
-            texts, engine=engine, chunk_size=chunk_size
+            texts, engine=engine, chunk_size=chunk_size, **kwargs
         )
 
-    def embed_query(self, text: str) -> list[float]:
+    def embed_query(self, text: str, **kwargs: Any) -> list[float]:
         """Call out to OpenAI's embedding endpoint for embedding query text.
 
         Args:
             text: The text to embed.
+            kwargs: Additional keyword arguments to pass to the embedding API.
 
         Returns:
             Embedding for the text.
         """
-        return self.embed_documents([text])[0]
+        return self.embed_documents([text], **kwargs)[0]
 
-    async def aembed_query(self, text: str) -> list[float]:
+    async def aembed_query(self, text: str, **kwargs: Any) -> list[float]:
         """Call out to OpenAI's embedding endpoint async for embedding query text.
 
         Args:
             text: The text to embed.
+            kwargs: Additional keyword arguments to pass to the embedding API.
 
         Returns:
             Embedding for the text.
         """
-        embeddings = await self.aembed_documents([text])
+        embeddings = await self.aembed_documents([text], **kwargs)
         return embeddings[0]

libs/partners/openai/pyproject.toml

@@ -7,12 +7,12 @@ authors = []
 license = { text = "MIT" }
 requires-python = ">=3.9"
 dependencies = [
-    "langchain-core<1.0.0,>=0.3.58",
+    "langchain-core<1.0.0,>=0.3.59",
     "openai<2.0.0,>=1.68.2",
     "tiktoken<1,>=0.7",
 ]
 name = "langchain-openai"
-version = "0.3.16"
+version = "0.3.17"
 description = "An integration package connecting OpenAI and LangChain"
 readme = "README.md"
 

libs/partners/openai/tests/unit_tests/chat_models/test_base.py

@@ -614,6 +614,50 @@ def test_openai_invoke_name(mock_client: MagicMock) -> None:
         assert res.name == "Erick"
 
 
+def test_function_calls_with_tool_calls(mock_client: MagicMock) -> None:
+    # Test that we ignore function calls if tool_calls are present
+    llm = ChatOpenAI(model="gpt-4.1-mini")
+    tool_call_message = AIMessage(
+        content="",
+        additional_kwargs={
+            "function_call": {
+                "name": "get_weather",
+                "arguments": '{"location": "Boston"}',
+            }
+        },
+        tool_calls=[
+            {
+                "name": "get_weather",
+                "args": {"location": "Boston"},
+                "id": "abc123",
+                "type": "tool_call",
+            }
+        ],
+    )
+    messages = [
+        HumanMessage("What's the weather in Boston?"),
+        tool_call_message,
+        ToolMessage(content="It's sunny.", name="get_weather", tool_call_id="abc123"),
+    ]
+    with patch.object(llm, "client", mock_client):
+        _ = llm.invoke(messages)
+        _, call_kwargs = mock_client.create.call_args
+        call_messages = call_kwargs["messages"]
+        tool_call_message_payload = call_messages[1]
+        assert "tool_calls" in tool_call_message_payload
+        assert "function_call" not in tool_call_message_payload
+
+    # Test we don't ignore function calls if tool_calls are not present
+    cast(AIMessage, messages[1]).tool_calls = []
+    with patch.object(llm, "client", mock_client):
+        _ = llm.invoke(messages)
+        _, call_kwargs = mock_client.create.call_args
+        call_messages = call_kwargs["messages"]
+        tool_call_message_payload = call_messages[1]
+        assert "function_call" in tool_call_message_payload
+        assert "tool_calls" not in tool_call_message_payload
+
+
 def test_custom_token_counting() -> None:
     def token_encoder(text: str) -> list[int]:
         return [1, 2, 3]

libs/partners/openai/tests/unit_tests/embeddings/test_base.py

@@ -57,3 +57,42 @@ def test_embed_documents_with_custom_chunk_size_no_check_ctx_length() -> None:
         mock_create.assert_any_call(input=texts[3:4], **embeddings._invocation_params)
 
     assert result == [[0.1, 0.2], [0.3, 0.4], [0.5, 0.6], [0.7, 0.8]]
+
+
+def test_embed_with_kwargs() -> None:
+    embeddings = OpenAIEmbeddings(
+        model="text-embedding-3-small", check_embedding_ctx_length=False
+    )
+    texts = ["text1", "text2"]
+    with patch.object(embeddings.client, "create") as mock_create:
+        mock_create.side_effect = [
+            {"data": [{"embedding": [0.1, 0.2, 0.3]}, {"embedding": [0.4, 0.5, 0.6]}]}
+        ]
+
+        result = embeddings.embed_documents(texts, dimensions=3)
+        mock_create.assert_any_call(
+            input=texts, dimensions=3, **embeddings._invocation_params
+        )
+
+    assert result == [[0.1, 0.2, 0.3], [0.4, 0.5, 0.6]]
+
+
+async def test_embed_with_kwargs_async() -> None:
+    embeddings = OpenAIEmbeddings(
+        model="text-embedding-3-small",
+        check_embedding_ctx_length=False,
+        dimensions=4,  # also check that runtime kwargs take precedence
+    )
+    texts = ["text1", "text2"]
+    with patch.object(embeddings.async_client, "create") as mock_create:
+        mock_create.side_effect = [
+            {"data": [{"embedding": [0.1, 0.2, 0.3]}, {"embedding": [0.4, 0.5, 0.6]}]}
+        ]
+
+        result = await embeddings.aembed_documents(texts, dimensions=3)
+        client_kwargs = embeddings._invocation_params.copy()
+        assert client_kwargs["dimensions"] == 4
+        client_kwargs["dimensions"] = 3
+        mock_create.assert_any_call(input=texts, **client_kwargs)
+
+    assert result == [[0.1, 0.2, 0.3], [0.4, 0.5, 0.6]]

libs/partners/openai/uv.lock

@@ -462,7 +462,7 @@ wheels = [
 
 [[package]]
 name = "langchain-core"
-version = "0.3.58"
+version = "0.3.59"
 source = { editable = "../../core" }
 dependencies = [
     { name = "jsonpatch" },
@@ -477,10 +477,9 @@ dependencies = [
 [package.metadata]
 requires-dist = [
     { name = "jsonpatch", specifier = ">=1.33,<2.0" },
-    { name = "langsmith", specifier = ">=0.1.125,<0.4" },
+    { name = "langsmith", specifier = ">=0.1.126,<0.4" },
     { name = "packaging", specifier = ">=23.2,<25" },
-    { name = "pydantic", marker = "python_full_version < '3.12.4'", specifier = ">=2.5.2,<3.0.0" },
-    { name = "pydantic", marker = "python_full_version >= '3.12.4'", specifier = ">=2.7.4,<3.0.0" },
+    { name = "pydantic", specifier = ">=2.7.4" },
     { name = "pyyaml", specifier = ">=5.3" },
     { name = "tenacity", specifier = ">=8.1.0,!=8.4.0,<10.0.0" },
     { name = "typing-extensions", specifier = ">=4.7" },
@@ -521,7 +520,7 @@ typing = [
 
 [[package]]
 name = "langchain-openai"
-version = "0.3.16"
+version = "0.3.17"
 source = { editable = "." }
 dependencies = [
     { name = "langchain-core" },

libs/text-splitters/langchain_text_splitters/character.py

@@ -18,14 +18,30 @@ class CharacterTextSplitter(TextSplitter):
         self._is_separator_regex = is_separator_regex
 
     def split_text(self, text: str) -> List[str]:
-        """Split incoming text and return chunks."""
-        # First we naively split the large input into a bunch of smaller ones.
-        separator = (
+        """Split into chunks without re-inserting lookaround separators."""
+        # 1. Determine split pattern: raw regex or escaped literal
+        sep_pattern = (
             self._separator if self._is_separator_regex else re.escape(self._separator)
         )
-        splits = _split_text_with_regex(text, separator, self._keep_separator)
-        _separator = "" if self._keep_separator else self._separator
-        return self._merge_splits(splits, _separator)
+
+        # 2. Initial split (keep separator if requested)
+        splits = _split_text_with_regex(text, sep_pattern, self._keep_separator)
+
+        # 3. Detect zero-width lookaround so we never re-insert it
+        lookaround_prefixes = ("(?=", "(?<!", "(?<=", "(?!")
+        is_lookaround = self._is_separator_regex and any(
+            self._separator.startswith(p) for p in lookaround_prefixes
+        )
+
+        # 4. Decide merge separator:
+        #    - if keep_separator or lookaround → don’t re-insert
+        #    - else → re-insert literal separator
+        merge_sep = ""
+        if not (self._keep_separator or is_lookaround):
+            merge_sep = self._separator
+
+        # 5. Merge adjacent splits and return
+        return self._merge_splits(splits, merge_sep)
 
 
 def _split_text_with_regex(

libs/text-splitters/tests/unit_tests/test_text_splitters.py

@@ -3373,3 +3373,51 @@ def test_html_splitter_with_media_preservation() -> None:
     ]
 
     assert documents == expected
+
+
+def test_character_text_splitter_discard_regex_separator_on_merge() -> None:
+    """Test that regex lookahead separator is not re-inserted when merging."""
+    text = "SCE191 First chunk. SCE103 Second chunk."
+    splitter = CharacterTextSplitter(
+        separator=r"(?=SCE\d{3})",
+        is_separator_regex=True,
+        chunk_size=200,
+        chunk_overlap=0,
+        keep_separator=False,
+    )
+    output = splitter.split_text(text)
+    assert output == ["SCE191 First chunk. SCE103 Second chunk."]
+
+
+@pytest.mark.parametrize(
+    "separator,is_regex,text,chunk_size,expected",
+    [
+        # 1) regex lookaround & split happens
+        #   "abcmiddef" split by "(?<=mid)" → ["abcmid","def"], chunk_size=5 keeps both
+        (r"(?<=mid)", True, "abcmiddef", 5, ["abcmid", "def"]),
+        # 2) regex lookaround & no split
+        #   chunk_size=100 merges back into ["abcmiddef"]
+        (r"(?<=mid)", True, "abcmiddef", 100, ["abcmiddef"]),
+        # 3) literal separator & split happens
+        #   split on "mid" → ["abc","def"], chunk_size=3 keeps both
+        ("mid", False, "abcmiddef", 3, ["abc", "def"]),
+        # 4) literal separator & no split
+        #   chunk_size=100 merges back into ["abcmiddef"]
+        ("mid", False, "abcmiddef", 100, ["abcmiddef"]),
+    ],
+)
+def test_character_text_splitter_chunk_size_effect(
+    separator: str,
+    is_regex: bool,
+    text: str,
+    chunk_size: int,
+    expected: List[str],
+) -> None:
+    splitter = CharacterTextSplitter(
+        separator=separator,
+        is_separator_regex=is_regex,
+        chunk_size=chunk_size,
+        chunk_overlap=0,
+        keep_separator=False,
+    )
+    assert splitter.split_text(text) == expected