docs: google genai title

Add deprecation warnings to extraction chains

.github/scripts/check_diff.py

@@ -47,6 +47,13 @@ if __name__ == "__main__":
                     found = True
                 if found:
                     dirs_to_run["extended-test"].add(dir_)
+        elif file.startswith("libs/standard-tests"):
+            # TODO: update to include all packages that rely on standard-tests (all partner packages)
+            # note: won't run on external repo partners
+            dirs_to_run["lint"].add("libs/standard-tests")
+            dirs_to_run["test"].add("libs/partners/mistralai")
+            dirs_to_run["test"].add("libs/partners/openai")
+
         elif file.startswith("libs/cli"):
             # todo: add cli makefile
             pass

.github/scripts/get_min_versions.py

@@ -13,13 +13,16 @@ MIN_VERSION_LIBS = [
 
 
 def get_min_version(version: str) -> str:
+    # base regex for x.x.x with cases for rc/post/etc
+    # valid strings: https://peps.python.org/pep-0440/#public-version-identifiers
+    vstring = r"\d+(?:\.\d+){0,2}(?:(?:a|b|rc|\.post|\.dev)\d+)?"
     # case ^x.x.x
-    _match = re.match(r"^\^(\d+(?:\.\d+){0,2})$", version)
+    _match = re.match(f"^\\^({vstring})$", version)
     if _match:
         return _match.group(1)
 
     # case >=x.x.x,<y.y.y
-    _match = re.match(r"^>=(\d+(?:\.\d+){0,2}),<(\d+(?:\.\d+){0,2})$", version)
+    _match = re.match(f"^>=({vstring}),<({vstring})$", version)
     if _match:
         _min = _match.group(1)
         _max = _match.group(2)
@@ -27,7 +30,7 @@ def get_min_version(version: str) -> str:
         return _min
 
     # case x.x.x
-    _match = re.match(r"^(\d+(?:\.\d+){0,2})$", version)
+    _match = re.match(f"^({vstring})$", version)
     if _match:
         return _match.group(1)
 
@@ -52,6 +55,9 @@ def get_min_version_from_toml(toml_path: str):
             # Get the version string
             version_string = dependencies[lib]
 
+            if isinstance(version_string, dict):
+                version_string = version_string["version"]
+
             # Use parse_version to get the minimum supported version from version_string
             min_version = get_min_version(version_string)
 

.github/workflows/_release.yml

@@ -215,7 +215,6 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
           MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
           VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
         run: make integration_tests
         working-directory: ${{ inputs.working-directory }}
 

cookbook/autogpt/marathon_times.ipynb

@@ -59,7 +59,7 @@
    },
    "outputs": [],
    "source": [
-    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=1.0)"
+    "llm = ChatOpenAI(model=\"gpt-4\", temperature=1.0)"
    ]
   },
   {

cookbook/code-analysis-deeplake.ipynb

@@ -933,7 +933,7 @@
       "**Answer**: The LangChain class includes various types of retrievers such as:\n",
       "\n",
       "- ArxivRetriever\n",
-      "- AzureCognitiveSearchRetriever\n",
+      "- AzureAISearchRetriever\n",
       "- BM25Retriever\n",
       "- ChaindeskRetriever\n",
       "- ChatGPTPluginRetriever\n",
@@ -993,7 +993,7 @@
     {
      "data": {
       "text/plain": [
-       "{'question': 'LangChain possesses a variety of retrievers including:\\n\\n1. ArxivRetriever\\n2. AzureCognitiveSearchRetriever\\n3. BM25Retriever\\n4. ChaindeskRetriever\\n5. ChatGPTPluginRetriever\\n6. ContextualCompressionRetriever\\n7. DocArrayRetriever\\n8. ElasticSearchBM25Retriever\\n9. EnsembleRetriever\\n10. GoogleVertexAISearchRetriever\\n11. AmazonKendraRetriever\\n12. KNNRetriever\\n13. LlamaIndexGraphRetriever\\n14. LlamaIndexRetriever\\n15. MergerRetriever\\n16. MetalRetriever\\n17. MilvusRetriever\\n18. MultiQueryRetriever\\n19. ParentDocumentRetriever\\n20. PineconeHybridSearchRetriever\\n21. PubMedRetriever\\n22. RePhraseQueryRetriever\\n23. RemoteLangChainRetriever\\n24. SelfQueryRetriever\\n25. SVMRetriever\\n26. TFIDFRetriever\\n27. TimeWeightedVectorStoreRetriever\\n28. VespaRetriever\\n29. WeaviateHybridSearchRetriever\\n30. WebResearchRetriever\\n31. WikipediaRetriever\\n32. ZepRetriever\\n33. ZillizRetriever\\n\\nIt also includes self query translators like:\\n\\n1. ChromaTranslator\\n2. DeepLakeTranslator\\n3. MyScaleTranslator\\n4. PineconeTranslator\\n5. QdrantTranslator\\n6. WeaviateTranslator\\n\\nAnd remote retrievers like:\\n\\n1. RemoteLangChainRetriever'}"
+       "{'question': 'LangChain possesses a variety of retrievers including:\\n\\n1. ArxivRetriever\\n2. AzureAISearchRetriever\\n3. BM25Retriever\\n4. ChaindeskRetriever\\n5. ChatGPTPluginRetriever\\n6. ContextualCompressionRetriever\\n7. DocArrayRetriever\\n8. ElasticSearchBM25Retriever\\n9. EnsembleRetriever\\n10. GoogleVertexAISearchRetriever\\n11. AmazonKendraRetriever\\n12. KNNRetriever\\n13. LlamaIndexGraphRetriever\\n14. LlamaIndexRetriever\\n15. MergerRetriever\\n16. MetalRetriever\\n17. MilvusRetriever\\n18. MultiQueryRetriever\\n19. ParentDocumentRetriever\\n20. PineconeHybridSearchRetriever\\n21. PubMedRetriever\\n22. RePhraseQueryRetriever\\n23. RemoteLangChainRetriever\\n24. SelfQueryRetriever\\n25. SVMRetriever\\n26. TFIDFRetriever\\n27. TimeWeightedVectorStoreRetriever\\n28. VespaRetriever\\n29. WeaviateHybridSearchRetriever\\n30. WebResearchRetriever\\n31. WikipediaRetriever\\n32. ZepRetriever\\n33. ZillizRetriever\\n\\nIt also includes self query translators like:\\n\\n1. ChromaTranslator\\n2. DeepLakeTranslator\\n3. MyScaleTranslator\\n4. PineconeTranslator\\n5. QdrantTranslator\\n6. WeaviateTranslator\\n\\nAnd remote retrievers like:\\n\\n1. RemoteLangChainRetriever'}"
       ]
      },
      "execution_count": 31,
@@ -1117,7 +1117,7 @@
       "The LangChain class includes various types of retrievers such as:\n",
       "\n",
       "- ArxivRetriever\n",
-      "- AzureCognitiveSearchRetriever\n",
+      "- AzureAISearchRetriever\n",
       "- BM25Retriever\n",
       "- ChaindeskRetriever\n",
       "- ChatGPTPluginRetriever\n",

cookbook/elasticsearch_db_qa.ipynb

@@ -84,7 +84,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4\", temperature=0)\n",
     "chain = ElasticsearchDatabaseChain.from_llm(llm=llm, database=db, verbose=True)"
    ]
   },

cookbook/langgraph_crag.ipynb

@@ -229,7 +229,7 @@
     "    prompt = hub.pull(\"rlm/rag-prompt\")\n",
     "\n",
     "    # LLM\n",
-    "    llm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0, streaming=True)\n",
+    "    llm = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0, streaming=True)\n",
     "\n",
     "    # Post-processing\n",
     "    def format_docs(docs):\n",

cookbook/langgraph_self_rag.ipynb

@@ -236,7 +236,7 @@
     "    prompt = hub.pull(\"rlm/rag-prompt\")\n",
     "\n",
     "    # LLM\n",
-    "    llm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0)\n",
+    "    llm = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)\n",
     "\n",
     "    # Post-processing\n",
     "    def format_docs(docs):\n",

cookbook/mongodb-langchain-cache-memory.ipynb

@@ -0,0 +1,818 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "70b333e6",
+   "metadata": {},
+   "source": [
+    "[![View Article](https://img.shields.io/badge/View%20Article-blue)](https://www.mongodb.com/developer/products/atlas/advanced-rag-langchain-mongodb/)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d84a72ea",
+   "metadata": {},
+   "source": [
+    "# Adding Semantic Caching and Memory to your RAG Application using MongoDB and LangChain\n",
+    "\n",
+    "In this notebook, we will see how to use the new MongoDBCache and MongoDBChatMessageHistory in your RAG application.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "65527202",
+   "metadata": {},
+   "source": [
+    "## Step 1: Install required libraries\n",
+    "\n",
+    "- **datasets**: Python library to get access to datasets available on Hugging Face Hub\n",
+    "\n",
+    "- **langchain**: Python toolkit for LangChain\n",
+    "\n",
+    "- **langchain-mongodb**: Python package to use MongoDB as a vector store, semantic cache, chat history store etc. in LangChain\n",
+    "\n",
+    "- **langchain-openai**: Python package to use OpenAI models with LangChain\n",
+    "\n",
+    "- **pymongo**: Python toolkit for MongoDB\n",
+    "\n",
+    "- **pandas**: Python library for data analysis, exploration, and manipulation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "cbc22fa4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! pip install -qU datasets langchain langchain-mongodb langchain-openai pymongo pandas"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "39c41e87",
+   "metadata": {},
+   "source": [
+    "## Step 2: Setup pre-requisites\n",
+    "\n",
+    "* Set the MongoDB connection string. Follow the steps [here](https://www.mongodb.com/docs/manual/reference/connection-string/) to get the connection string from the Atlas UI.\n",
+    "\n",
+    "* Set the OpenAI API key. Steps to obtain an API key as [here](https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "b56412ae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "16a20d7a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Enter your MongoDB connection string:········\n"
+     ]
+    }
+   ],
+   "source": [
+    "MONGODB_URI = getpass.getpass(\"Enter your MongoDB connection string:\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "978682d4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Enter your OpenAI API key:········\n"
+     ]
+    }
+   ],
+   "source": [
+    "OPENAI_API_KEY = getpass.getpass(\"Enter your OpenAI API key:\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "606081c5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "········\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Optional-- If you want to enable Langsmith -- good for debugging\n",
+    "import os\n",
+    "\n",
+    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f6b8302c",
+   "metadata": {},
+   "source": [
+    "## Step 3: Download the dataset\n",
+    "\n",
+    "We will be using MongoDB's [embedded_movies](https://huggingface.co/datasets/MongoDB/embedded_movies) dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "1a3433a6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from datasets import load_dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aee5311b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Ensure you have an HF_TOKEN in your development enviornment:\n",
+    "# access tokens can be created or copied from the Hugging Face platform (https://huggingface.co/docs/hub/en/security-tokens)\n",
+    "\n",
+    "# Load MongoDB's embedded_movies dataset from Hugging Face\n",
+    "# https://huggingface.co/datasets/MongoDB/airbnb_embeddings\n",
+    "\n",
+    "data = load_dataset(\"MongoDB/embedded_movies\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "1d630a26",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.DataFrame(data[\"train\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a1f94f43",
+   "metadata": {},
+   "source": [
+    "## Step 4: Data analysis\n",
+    "\n",
+    "Make sure length of the dataset is what we expect, drop Nones etc."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "b276df71",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>fullplot</th>\n",
+       "      <th>type</th>\n",
+       "      <th>plot_embedding</th>\n",
+       "      <th>num_mflix_comments</th>\n",
+       "      <th>runtime</th>\n",
+       "      <th>writers</th>\n",
+       "      <th>imdb</th>\n",
+       "      <th>countries</th>\n",
+       "      <th>rated</th>\n",
+       "      <th>plot</th>\n",
+       "      <th>title</th>\n",
+       "      <th>languages</th>\n",
+       "      <th>metacritic</th>\n",
+       "      <th>directors</th>\n",
+       "      <th>awards</th>\n",
+       "      <th>genres</th>\n",
+       "      <th>poster</th>\n",
+       "      <th>cast</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Young Pauline is left a lot of money when her ...</td>\n",
+       "      <td>movie</td>\n",
+       "      <td>[0.00072939653, -0.026834568, 0.013515796, -0....</td>\n",
+       "      <td>0</td>\n",
+       "      <td>199.0</td>\n",
+       "      <td>[Charles W. Goddard (screenplay), Basil Dickey...</td>\n",
+       "      <td>{'id': 4465, 'rating': 7.6, 'votes': 744}</td>\n",
+       "      <td>[USA]</td>\n",
+       "      <td>None</td>\n",
+       "      <td>Young Pauline is left a lot of money when her ...</td>\n",
+       "      <td>The Perils of Pauline</td>\n",
+       "      <td>[English]</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[Louis J. Gasnier, Donald MacKenzie]</td>\n",
+       "      <td>{'nominations': 0, 'text': '1 win.', 'wins': 1}</td>\n",
+       "      <td>[Action]</td>\n",
+       "      <td>https://m.media-amazon.com/images/M/MV5BMzgxOD...</td>\n",
+       "      <td>[Pearl White, Crane Wilbur, Paul Panzer, Edwar...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                            fullplot   type  \\\n",
+       "0  Young Pauline is left a lot of money when her ...  movie   \n",
+       "\n",
+       "                                      plot_embedding  num_mflix_comments  \\\n",
+       "0  [0.00072939653, -0.026834568, 0.013515796, -0....                   0   \n",
+       "\n",
+       "   runtime                                            writers  \\\n",
+       "0    199.0  [Charles W. Goddard (screenplay), Basil Dickey...   \n",
+       "\n",
+       "                                        imdb countries rated  \\\n",
+       "0  {'id': 4465, 'rating': 7.6, 'votes': 744}     [USA]  None   \n",
+       "\n",
+       "                                                plot                  title  \\\n",
+       "0  Young Pauline is left a lot of money when her ...  The Perils of Pauline   \n",
+       "\n",
+       "   languages  metacritic                             directors  \\\n",
+       "0  [English]         NaN  [Louis J. Gasnier, Donald MacKenzie]   \n",
+       "\n",
+       "                                            awards    genres  \\\n",
+       "0  {'nominations': 0, 'text': '1 win.', 'wins': 1}  [Action]   \n",
+       "\n",
+       "                                              poster  \\\n",
+       "0  https://m.media-amazon.com/images/M/MV5BMzgxOD...   \n",
+       "\n",
+       "                                                cast  \n",
+       "0  [Pearl White, Crane Wilbur, Paul Panzer, Edwar...  "
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Previewing the contents of the data\n",
+    "df.head(1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "22ab375d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Only keep records where the fullplot field is not null\n",
+    "df = df[df[\"fullplot\"].notna()]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "fceed99a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Renaming the embedding field to \"embedding\" -- required by LangChain\n",
+    "df.rename(columns={\"plot_embedding\": \"embedding\"}, inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "aedec13a",
+   "metadata": {},
+   "source": [
+    "## Step 5: Create a simple RAG chain using MongoDB as the vector store"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "11d292f3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_mongodb import MongoDBAtlasVectorSearch\n",
+    "from pymongo import MongoClient\n",
+    "\n",
+    "# Initialize MongoDB python client\n",
+    "client = MongoClient(MONGODB_URI, appname=\"devrel.content.python\")\n",
+    "\n",
+    "DB_NAME = \"langchain_chatbot\"\n",
+    "COLLECTION_NAME = \"data\"\n",
+    "ATLAS_VECTOR_SEARCH_INDEX_NAME = \"vector_index\"\n",
+    "collection = client[DB_NAME][COLLECTION_NAME]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "d8292d53",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "DeleteResult({'n': 1000, 'electionId': ObjectId('7fffffff00000000000000f6'), 'opTime': {'ts': Timestamp(1710523288, 1033), 't': 246}, 'ok': 1.0, '$clusterTime': {'clusterTime': Timestamp(1710523288, 1042), 'signature': {'hash': b\"i\\xa8\\xe9'\\x1ed\\xf2u\\xf3L\\xff\\xb1\\xf5\\xbfA\\x90\\xabJ\\x12\\x83\", 'keyId': 7299545392000008318}}, 'operationTime': Timestamp(1710523288, 1033)}, acknowledged=True)"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Delete any existing records in the collection\n",
+    "collection.delete_many({})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "36c68914",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Data ingestion into MongoDB completed\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Data Ingestion\n",
+    "records = df.to_dict(\"records\")\n",
+    "collection.insert_many(records)\n",
+    "\n",
+    "print(\"Data ingestion into MongoDB completed\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "cbfca0b8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "\n",
+    "# Using the text-embedding-ada-002 since that's what was used to create embeddings in the movies dataset\n",
+    "embeddings = OpenAIEmbeddings(\n",
+    "    openai_api_key=OPENAI_API_KEY, model=\"text-embedding-ada-002\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "798e176c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Vector Store Creation\n",
+    "vector_store = MongoDBAtlasVectorSearch.from_connection_string(\n",
+    "    connection_string=MONGODB_URI,\n",
+    "    namespace=DB_NAME + \".\" + COLLECTION_NAME,\n",
+    "    embedding=embeddings,\n",
+    "    index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,\n",
+    "    text_key=\"fullplot\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "id": "c71cd087",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Using the MongoDB vector store as a retriever in a RAG chain\n",
+    "retriever = vector_store.as_retriever(search_type=\"similarity\", search_kwargs={\"k\": 5})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "b6588cd3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "# Generate context using the retriever, and pass the user question through\n",
+    "retrieve = {\n",
+    "    \"context\": retriever | (lambda docs: \"\\n\\n\".join([d.page_content for d in docs])),\n",
+    "    \"question\": RunnablePassthrough(),\n",
+    "}\n",
+    "template = \"\"\"Answer the question based only on the following context: \\\n",
+    "{context}\n",
+    "\n",
+    "Question: {question}\n",
+    "\"\"\"\n",
+    "# Defining the chat prompt\n",
+    "prompt = ChatPromptTemplate.from_template(template)\n",
+    "# Defining the model to be used for chat completion\n",
+    "model = ChatOpenAI(temperature=0, openai_api_key=OPENAI_API_KEY)\n",
+    "# Parse output as a string\n",
+    "parse_output = StrOutputParser()\n",
+    "\n",
+    "# Naive RAG chain\n",
+    "naive_rag_chain = retrieve | prompt | model | parse_output"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "aaae21f5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Once a Thief'"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "naive_rag_chain.invoke(\"What is the best movie to watch when sad?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "75f929ef",
+   "metadata": {},
+   "source": [
+    "## Step 6: Create a RAG chain with chat history"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "94e7bd4a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import MessagesPlaceholder\n",
+    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
+    "from langchain_mongodb.chat_message_histories import MongoDBChatMessageHistory"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "5bb30860",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_session_history(session_id: str) -> MongoDBChatMessageHistory:\n",
+    "    return MongoDBChatMessageHistory(\n",
+    "        MONGODB_URI, session_id, database_name=DB_NAME, collection_name=\"history\"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "id": "f51d0f35",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Given a follow-up question and history, create a standalone question\n",
+    "standalone_system_prompt = \"\"\"\n",
+    "Given a chat history and a follow-up question, rephrase the follow-up question to be a standalone question. \\\n",
+    "Do NOT answer the question, just reformulate it if needed, otherwise return it as is. \\\n",
+    "Only return the final standalone question. \\\n",
+    "\"\"\"\n",
+    "standalone_question_prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", standalone_system_prompt),\n",
+    "        MessagesPlaceholder(variable_name=\"history\"),\n",
+    "        (\"human\", \"{question}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "question_chain = standalone_question_prompt | model | parse_output"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "f3ef3354",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Generate context by passing output of the question_chain i.e. the standalone question to the retriever\n",
+    "retriever_chain = RunnablePassthrough.assign(\n",
+    "    context=question_chain\n",
+    "    | retriever\n",
+    "    | (lambda docs: \"\\n\\n\".join([d.page_content for d in docs]))\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "id": "5afb7345",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a prompt that includes the context, history and the follow-up question\n",
+    "rag_system_prompt = \"\"\"Answer the question based only on the following context: \\\n",
+    "{context}\n",
+    "\"\"\"\n",
+    "rag_prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", rag_system_prompt),\n",
+    "        MessagesPlaceholder(variable_name=\"history\"),\n",
+    "        (\"human\", \"{question}\"),\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "id": "f95f47d0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# RAG chain\n",
+    "rag_chain = retriever_chain | rag_prompt | model | parse_output"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "id": "9618d395",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'The best movie to watch when feeling down could be \"Last Action Hero.\" It\\'s a fun and action-packed film that blends reality and fantasy, offering an escape from the real world and providing an entertaining distraction.'"
+      ]
+     },
+     "execution_count": 57,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# RAG chain with history\n",
+    "with_message_history = RunnableWithMessageHistory(\n",
+    "    rag_chain,\n",
+    "    get_session_history,\n",
+    "    input_messages_key=\"question\",\n",
+    "    history_messages_key=\"history\",\n",
+    ")\n",
+    "with_message_history.invoke(\n",
+    "    {\"question\": \"What is the best movie to watch when sad?\"},\n",
+    "    {\"configurable\": {\"session_id\": \"1\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "id": "6e3080d1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'I apologize for the confusion. Another movie that might lift your spirits when you\\'re feeling sad is \"Smilla\\'s Sense of Snow.\" It\\'s a mystery thriller that could engage your mind and distract you from your sadness with its intriguing plot and suspenseful storyline.'"
+      ]
+     },
+     "execution_count": 58,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "with_message_history.invoke(\n",
+    "    {\n",
+    "        \"question\": \"Hmmm..I don't want to watch that one. Can you suggest something else?\"\n",
+    "    },\n",
+    "    {\"configurable\": {\"session_id\": \"1\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "id": "daea2953",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'For a lighter movie option, you might enjoy \"Cousins.\" It\\'s a comedy film set in Barcelona with action and humor, offering a fun and entertaining escape from reality. The storyline is engaging and filled with comedic moments that could help lift your spirits.'"
+      ]
+     },
+     "execution_count": 59,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "with_message_history.invoke(\n",
+    "    {\"question\": \"How about something more light?\"},\n",
+    "    {\"configurable\": {\"session_id\": \"1\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0de23a88",
+   "metadata": {},
+   "source": [
+    "## Step 7: Get faster responses using Semantic Cache\n",
+    "\n",
+    "**NOTE:** Semantic cache only caches the input to the LLM. When using it in retrieval chains, remember that documents retrieved can change between runs resulting in cache misses for semantically similar queries."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "id": "5d6b6741",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.globals import set_llm_cache\n",
+    "from langchain_mongodb.cache import MongoDBAtlasSemanticCache\n",
+    "\n",
+    "set_llm_cache(\n",
+    "    MongoDBAtlasSemanticCache(\n",
+    "        connection_string=MONGODB_URI,\n",
+    "        embedding=embeddings,\n",
+    "        collection_name=\"semantic_cache\",\n",
+    "        database_name=DB_NAME,\n",
+    "        index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,\n",
+    "        wait_until_ready=True,  # Optional, waits until the cache is ready to be used\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "id": "9825bc7b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 87.8 ms, sys: 670 µs, total: 88.5 ms\n",
+      "Wall time: 1.24 s\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Once a Thief'"
+      ]
+     },
+     "execution_count": 62,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "naive_rag_chain.invoke(\"What is the best movie to watch when sad?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "id": "a5e518cf",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 43.5 ms, sys: 4.16 ms, total: 47.7 ms\n",
+      "Wall time: 255 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Once a Thief'"
+      ]
+     },
+     "execution_count": 63,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "naive_rag_chain.invoke(\"What is the best movie to watch when sad?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "id": "3d3d3ad3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 115 ms, sys: 171 µs, total: 115 ms\n",
+      "Wall time: 1.38 s\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'I would recommend watching \"Last Action Hero\" when sad, as it is a fun and action-packed film that can help lift your spirits.'"
+      ]
+     },
+     "execution_count": 64,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "naive_rag_chain.invoke(\"Which movie do I watch when sad?\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "conda_pytorch_p310",
+   "language": "python",
+   "name": "conda_pytorch_p310"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/press_releases.ipynb

@@ -84,7 +84,7 @@
     "from langchain.retrievers import KayAiRetriever\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "model = ChatOpenAI(model_name=\"gpt-3.5-turbo\")\n",
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo\")\n",
     "retriever = KayAiRetriever.create(\n",
     "    dataset_id=\"company\", data_types=[\"PressRelease\"], num_contexts=6\n",
     ")\n",

cookbook/retrieval_in_sql.ipynb

@@ -274,7 +274,7 @@
     "db = SQLDatabase.from_uri(\n",
     "    CONNECTION_STRING\n",
     ")  # We reconnect to db so the new columns are loaded as well.\n",
-    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4\", temperature=0)\n",
     "\n",
     "sql_query_chain = (\n",
     "    RunnablePassthrough.assign(schema=get_schema)\n",

cookbook/sharedmemory_for_tools.ipynb

@@ -22,7 +22,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.agents import AgentExecutor, Tool, ZeroShotAgent\n",
+    "from langchain import hub\n",
+    "from langchain.agents import AgentExecutor, Tool, ZeroShotAgent, create_react_agent\n",
     "from langchain.chains import LLMChain\n",
     "from langchain.memory import ConversationBufferMemory, ReadOnlySharedMemory\n",
     "from langchain.prompts import PromptTemplate\n",
@@ -84,19 +85,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
-    "suffix = \"\"\"Begin!\"\n",
-    "\n",
-    "{chat_history}\n",
-    "Question: {input}\n",
-    "{agent_scratchpad}\"\"\"\n",
-    "\n",
-    "prompt = ZeroShotAgent.create_prompt(\n",
-    "    tools,\n",
-    "    prefix=prefix,\n",
-    "    suffix=suffix,\n",
-    "    input_variables=[\"input\", \"chat_history\", \"agent_scratchpad\"],\n",
-    ")"
+    "prompt = hub.pull(\"hwchase17/react\")"
    ]
   },
   {
@@ -114,16 +103,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)\n",
-    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)\n",
-    "agent_chain = AgentExecutor.from_agent_and_tools(\n",
-    "    agent=agent, tools=tools, verbose=True, memory=memory\n",
-    ")"
+    "model = OpenAI()\n",
+    "agent = create_react_agent(model, tools, prompt)\n",
+    "agent_executor = AgentExecutor(agent=agent, tools=tools, memory=memory)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 36,
    "id": "ca4bc1fb",
    "metadata": {},
    "outputs": [
@@ -133,15 +120,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I should research ChatGPT to answer this question.\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3mThought: I should research ChatGPT to answer this question.\n",
       "Action: Search\n",
-      "Action Input: \"ChatGPT\"\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
-      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001b[0m\n",
+      "Action Input: \"ChatGPT\"\u001B[0m\n",
+      "Observation: \u001B[36;1m\u001B[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "\u001B[1m> Finished chain.\u001B[0m\n"
      ]
     },
     {
@@ -153,10 +140,40 @@
      "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
+    },
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
+      "\u001B[0;31mKeyboardInterrupt\u001B[0m                         Traceback (most recent call last)",
+      "Cell \u001B[0;32mIn[36], line 1\u001B[0m\n\u001B[0;32m----> 1\u001B[0m \u001B[43magent_executor\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43minvoke\u001B[49m\u001B[43m(\u001B[49m\u001B[43m{\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43minput\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mWhat is ChatGPT?\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m}\u001B[49m\u001B[43m)\u001B[49m\n",
+      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/chains/base.py:163\u001B[0m, in \u001B[0;36mChain.invoke\u001B[0;34m(self, input, config, **kwargs)\u001B[0m\n\u001B[1;32m    161\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mBaseException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m    162\u001B[0m     run_manager\u001B[38;5;241m.\u001B[39mon_chain_error(e)\n\u001B[0;32m--> 163\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m e\n\u001B[1;32m    164\u001B[0m run_manager\u001B[38;5;241m.\u001B[39mon_chain_end(outputs)\n\u001B[1;32m    166\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m include_run_info:\n",
+      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/chains/base.py:153\u001B[0m, in \u001B[0;36mChain.invoke\u001B[0;34m(self, input, config, **kwargs)\u001B[0m\n\u001B[1;32m    150\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m    151\u001B[0m     \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_validate_inputs(inputs)\n\u001B[1;32m    152\u001B[0m     outputs \u001B[38;5;241m=\u001B[39m (\n\u001B[0;32m--> 153\u001B[0m         \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_call\u001B[49m\u001B[43m(\u001B[49m\u001B[43minputs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrun_manager\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mrun_manager\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    154\u001B[0m         \u001B[38;5;28;01mif\u001B[39;00m new_arg_supported\n\u001B[1;32m    155\u001B[0m         \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_call(inputs)\n\u001B[1;32m    156\u001B[0m     )\n\u001B[1;32m    158\u001B[0m     final_outputs: Dict[\u001B[38;5;28mstr\u001B[39m, Any] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mprep_outputs(\n\u001B[1;32m    159\u001B[0m         inputs, outputs, return_only_outputs\n\u001B[1;32m    160\u001B[0m     )\n\u001B[1;32m    161\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mBaseException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n",
+      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1432\u001B[0m, in \u001B[0;36mAgentExecutor._call\u001B[0;34m(self, inputs, run_manager)\u001B[0m\n\u001B[1;32m   1430\u001B[0m \u001B[38;5;66;03m# We now enter the agent loop (until it returns something).\u001B[39;00m\n\u001B[1;32m   1431\u001B[0m \u001B[38;5;28;01mwhile\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_should_continue(iterations, time_elapsed):\n\u001B[0;32m-> 1432\u001B[0m     next_step_output \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_take_next_step\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1433\u001B[0m \u001B[43m        \u001B[49m\u001B[43mname_to_tool_map\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1434\u001B[0m \u001B[43m        \u001B[49m\u001B[43mcolor_mapping\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1435\u001B[0m \u001B[43m        \u001B[49m\u001B[43minputs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1436\u001B[0m \u001B[43m        \u001B[49m\u001B[43mintermediate_steps\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1437\u001B[0m \u001B[43m        \u001B[49m\u001B[43mrun_manager\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mrun_manager\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1438\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1439\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28misinstance\u001B[39m(next_step_output, AgentFinish):\n\u001B[1;32m   1440\u001B[0m         \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_return(\n\u001B[1;32m   1441\u001B[0m             next_step_output, intermediate_steps, run_manager\u001B[38;5;241m=\u001B[39mrun_manager\n\u001B[1;32m   1442\u001B[0m         )\n",
+      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1138\u001B[0m, in \u001B[0;36mAgentExecutor._take_next_step\u001B[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001B[0m\n\u001B[1;32m   1129\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21m_take_next_step\u001B[39m(\n\u001B[1;32m   1130\u001B[0m     \u001B[38;5;28mself\u001B[39m,\n\u001B[1;32m   1131\u001B[0m     name_to_tool_map: Dict[\u001B[38;5;28mstr\u001B[39m, BaseTool],\n\u001B[0;32m   (...)\u001B[0m\n\u001B[1;32m   1135\u001B[0m     run_manager: Optional[CallbackManagerForChainRun] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m,\n\u001B[1;32m   1136\u001B[0m ) \u001B[38;5;241m-\u001B[39m\u001B[38;5;241m>\u001B[39m Union[AgentFinish, List[Tuple[AgentAction, \u001B[38;5;28mstr\u001B[39m]]]:\n\u001B[1;32m   1137\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_consume_next_step(\n\u001B[0;32m-> 1138\u001B[0m         [\n\u001B[1;32m   1139\u001B[0m             a\n\u001B[1;32m   1140\u001B[0m             \u001B[38;5;28;01mfor\u001B[39;00m a \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_iter_next_step(\n\u001B[1;32m   1141\u001B[0m                 name_to_tool_map,\n\u001B[1;32m   1142\u001B[0m                 color_mapping,\n\u001B[1;32m   1143\u001B[0m                 inputs,\n\u001B[1;32m   1144\u001B[0m                 intermediate_steps,\n\u001B[1;32m   1145\u001B[0m                 run_manager,\n\u001B[1;32m   1146\u001B[0m             )\n\u001B[1;32m   1147\u001B[0m         ]\n\u001B[1;32m   1148\u001B[0m     )\n",
+      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1138\u001B[0m, in \u001B[0;36m<listcomp>\u001B[0;34m(.0)\u001B[0m\n\u001B[1;32m   1129\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21m_take_next_step\u001B[39m(\n\u001B[1;32m   1130\u001B[0m     \u001B[38;5;28mself\u001B[39m,\n\u001B[1;32m   1131\u001B[0m     name_to_tool_map: Dict[\u001B[38;5;28mstr\u001B[39m, BaseTool],\n\u001B[0;32m   (...)\u001B[0m\n\u001B[1;32m   1135\u001B[0m     run_manager: Optional[CallbackManagerForChainRun] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m,\n\u001B[1;32m   1136\u001B[0m ) \u001B[38;5;241m-\u001B[39m\u001B[38;5;241m>\u001B[39m Union[AgentFinish, List[Tuple[AgentAction, \u001B[38;5;28mstr\u001B[39m]]]:\n\u001B[1;32m   1137\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_consume_next_step(\n\u001B[0;32m-> 1138\u001B[0m         [\n\u001B[1;32m   1139\u001B[0m             a\n\u001B[1;32m   1140\u001B[0m             \u001B[38;5;28;01mfor\u001B[39;00m a \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_iter_next_step(\n\u001B[1;32m   1141\u001B[0m                 name_to_tool_map,\n\u001B[1;32m   1142\u001B[0m                 color_mapping,\n\u001B[1;32m   1143\u001B[0m                 inputs,\n\u001B[1;32m   1144\u001B[0m                 intermediate_steps,\n\u001B[1;32m   1145\u001B[0m                 run_manager,\n\u001B[1;32m   1146\u001B[0m             )\n\u001B[1;32m   1147\u001B[0m         ]\n\u001B[1;32m   1148\u001B[0m     )\n",
+      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1223\u001B[0m, in \u001B[0;36mAgentExecutor._iter_next_step\u001B[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001B[0m\n\u001B[1;32m   1221\u001B[0m     \u001B[38;5;28;01myield\u001B[39;00m agent_action\n\u001B[1;32m   1222\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m agent_action \u001B[38;5;129;01min\u001B[39;00m actions:\n\u001B[0;32m-> 1223\u001B[0m     \u001B[38;5;28;01myield\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_perform_agent_action\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1224\u001B[0m \u001B[43m        \u001B[49m\u001B[43mname_to_tool_map\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcolor_mapping\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43magent_action\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrun_manager\u001B[49m\n\u001B[1;32m   1225\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n",
+      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1245\u001B[0m, in \u001B[0;36mAgentExecutor._perform_agent_action\u001B[0;34m(self, name_to_tool_map, color_mapping, agent_action, run_manager)\u001B[0m\n\u001B[1;32m   1243\u001B[0m         tool_run_kwargs[\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mllm_prefix\u001B[39m\u001B[38;5;124m\"\u001B[39m] \u001B[38;5;241m=\u001B[39m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m\"\u001B[39m\n\u001B[1;32m   1244\u001B[0m     \u001B[38;5;66;03m# We then call the tool on the tool input to get an observation\u001B[39;00m\n\u001B[0;32m-> 1245\u001B[0m     observation \u001B[38;5;241m=\u001B[39m \u001B[43mtool\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mrun\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1246\u001B[0m \u001B[43m        \u001B[49m\u001B[43magent_action\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mtool_input\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1247\u001B[0m \u001B[43m        \u001B[49m\u001B[43mverbose\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mverbose\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1248\u001B[0m \u001B[43m        \u001B[49m\u001B[43mcolor\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mcolor\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1249\u001B[0m \u001B[43m        \u001B[49m\u001B[43mcallbacks\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mrun_manager\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mget_child\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43;01mif\u001B[39;49;00m\u001B[43m \u001B[49m\u001B[43mrun_manager\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43;01melse\u001B[39;49;00m\u001B[43m \u001B[49m\u001B[38;5;28;43;01mNone\u001B[39;49;00m\u001B[43m,\u001B[49m\n\u001B[1;32m   1250\u001B[0m \u001B[43m        \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mtool_run_kwargs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1251\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1252\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[1;32m   1253\u001B[0m     tool_run_kwargs \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39magent\u001B[38;5;241m.\u001B[39mtool_run_logging_kwargs()\n",
+      "File \u001B[0;32m~/code/langchain/libs/core/langchain_core/tools.py:422\u001B[0m, in \u001B[0;36mBaseTool.run\u001B[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001B[0m\n\u001B[1;32m    420\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m (\u001B[38;5;167;01mException\u001B[39;00m, \u001B[38;5;167;01mKeyboardInterrupt\u001B[39;00m) \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m    421\u001B[0m     run_manager\u001B[38;5;241m.\u001B[39mon_tool_error(e)\n\u001B[0;32m--> 422\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m e\n\u001B[1;32m    423\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[1;32m    424\u001B[0m     run_manager\u001B[38;5;241m.\u001B[39mon_tool_end(observation, color\u001B[38;5;241m=\u001B[39mcolor, name\u001B[38;5;241m=\u001B[39m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mname, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mkwargs)\n",
+      "File \u001B[0;32m~/code/langchain/libs/core/langchain_core/tools.py:381\u001B[0m, in \u001B[0;36mBaseTool.run\u001B[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001B[0m\n\u001B[1;32m    378\u001B[0m     parsed_input \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_parse_input(tool_input)\n\u001B[1;32m    379\u001B[0m     tool_args, tool_kwargs \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_to_args_and_kwargs(parsed_input)\n\u001B[1;32m    380\u001B[0m     observation \u001B[38;5;241m=\u001B[39m (\n\u001B[0;32m--> 381\u001B[0m         \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_run\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mtool_args\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrun_manager\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mrun_manager\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mtool_kwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    382\u001B[0m         \u001B[38;5;28;01mif\u001B[39;00m new_arg_supported\n\u001B[1;32m    383\u001B[0m         \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_run(\u001B[38;5;241m*\u001B[39mtool_args, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mtool_kwargs)\n\u001B[1;32m    384\u001B[0m     )\n\u001B[1;32m    385\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m ValidationError \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m    386\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mhandle_validation_error:\n",
+      "File \u001B[0;32m~/code/langchain/libs/core/langchain_core/tools.py:588\u001B[0m, in \u001B[0;36mTool._run\u001B[0;34m(self, run_manager, *args, **kwargs)\u001B[0m\n\u001B[1;32m    579\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mfunc:\n\u001B[1;32m    580\u001B[0m     new_argument_supported \u001B[38;5;241m=\u001B[39m signature(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mfunc)\u001B[38;5;241m.\u001B[39mparameters\u001B[38;5;241m.\u001B[39mget(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mcallbacks\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n\u001B[1;32m    581\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m (\n\u001B[1;32m    582\u001B[0m         \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mfunc(\n\u001B[1;32m    583\u001B[0m             \u001B[38;5;241m*\u001B[39margs,\n\u001B[1;32m    584\u001B[0m             callbacks\u001B[38;5;241m=\u001B[39mrun_manager\u001B[38;5;241m.\u001B[39mget_child() \u001B[38;5;28;01mif\u001B[39;00m run_manager \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m,\n\u001B[1;32m    585\u001B[0m             \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mkwargs,\n\u001B[1;32m    586\u001B[0m         )\n\u001B[1;32m    587\u001B[0m         \u001B[38;5;28;01mif\u001B[39;00m new_argument_supported\n\u001B[0;32m--> 588\u001B[0m         \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mfunc\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    589\u001B[0m     )\n\u001B[1;32m    590\u001B[0m \u001B[38;5;28;01mraise\u001B[39;00m \u001B[38;5;167;01mNotImplementedError\u001B[39;00m(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mTool does not support sync\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n",
+      "File \u001B[0;32m~/code/langchain/libs/community/langchain_community/utilities/google_search.py:94\u001B[0m, in \u001B[0;36mGoogleSearchAPIWrapper.run\u001B[0;34m(self, query)\u001B[0m\n\u001B[1;32m     92\u001B[0m \u001B[38;5;250m\u001B[39m\u001B[38;5;124;03m\"\"\"Run query through GoogleSearch and parse result.\"\"\"\u001B[39;00m\n\u001B[1;32m     93\u001B[0m snippets \u001B[38;5;241m=\u001B[39m []\n\u001B[0;32m---> 94\u001B[0m results \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_google_search_results\u001B[49m\u001B[43m(\u001B[49m\u001B[43mquery\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mnum\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mk\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m     95\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mlen\u001B[39m(results) \u001B[38;5;241m==\u001B[39m \u001B[38;5;241m0\u001B[39m:\n\u001B[1;32m     96\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mNo good Google Search Result was found\u001B[39m\u001B[38;5;124m\"\u001B[39m\n",
+      "File \u001B[0;32m~/code/langchain/libs/community/langchain_community/utilities/google_search.py:62\u001B[0m, in \u001B[0;36mGoogleSearchAPIWrapper._google_search_results\u001B[0;34m(self, search_term, **kwargs)\u001B[0m\n\u001B[1;32m     60\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39msiterestrict:\n\u001B[1;32m     61\u001B[0m     cse \u001B[38;5;241m=\u001B[39m cse\u001B[38;5;241m.\u001B[39msiterestrict()\n\u001B[0;32m---> 62\u001B[0m res \u001B[38;5;241m=\u001B[39m \u001B[43mcse\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mlist\u001B[49m\u001B[43m(\u001B[49m\u001B[43mq\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43msearch_term\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcx\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mgoogle_cse_id\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mexecute\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m     63\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m res\u001B[38;5;241m.\u001B[39mget(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mitems\u001B[39m\u001B[38;5;124m\"\u001B[39m, [])\n",
+      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/googleapiclient/_helpers.py:130\u001B[0m, in \u001B[0;36mpositional.<locals>.positional_decorator.<locals>.positional_wrapper\u001B[0;34m(*args, **kwargs)\u001B[0m\n\u001B[1;32m    128\u001B[0m     \u001B[38;5;28;01melif\u001B[39;00m positional_parameters_enforcement \u001B[38;5;241m==\u001B[39m POSITIONAL_WARNING:\n\u001B[1;32m    129\u001B[0m         logger\u001B[38;5;241m.\u001B[39mwarning(message)\n\u001B[0;32m--> 130\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mwrapped\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n",
+      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/googleapiclient/http.py:923\u001B[0m, in \u001B[0;36mHttpRequest.execute\u001B[0;34m(self, http, num_retries)\u001B[0m\n\u001B[1;32m    920\u001B[0m     \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mheaders[\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mcontent-length\u001B[39m\u001B[38;5;124m\"\u001B[39m] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mstr\u001B[39m(\u001B[38;5;28mlen\u001B[39m(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mbody))\n\u001B[1;32m    922\u001B[0m \u001B[38;5;66;03m# Handle retries for server-side errors.\u001B[39;00m\n\u001B[0;32m--> 923\u001B[0m resp, content \u001B[38;5;241m=\u001B[39m \u001B[43m_retry_request\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m    924\u001B[0m \u001B[43m    \u001B[49m\u001B[43mhttp\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    925\u001B[0m \u001B[43m    \u001B[49m\u001B[43mnum_retries\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    926\u001B[0m \u001B[43m    \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mrequest\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m    927\u001B[0m \u001B[43m    \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_sleep\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    928\u001B[0m \u001B[43m    \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_rand\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    929\u001B[0m \u001B[43m    \u001B[49m\u001B[38;5;28;43mstr\u001B[39;49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43muri\u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    930\u001B[0m \u001B[43m    \u001B[49m\u001B[43mmethod\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mstr\u001B[39;49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mmethod\u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    931\u001B[0m \u001B[43m    \u001B[49m\u001B[43mbody\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mbody\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    932\u001B[0m \u001B[43m    \u001B[49m\u001B[43mheaders\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mheaders\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    933\u001B[0m \u001B[43m\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    935\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m callback \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mresponse_callbacks:\n\u001B[1;32m    936\u001B[0m     callback(resp)\n",
+      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/googleapiclient/http.py:191\u001B[0m, in \u001B[0;36m_retry_request\u001B[0;34m(http, num_retries, req_type, sleep, rand, uri, method, *args, **kwargs)\u001B[0m\n\u001B[1;32m    189\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m    190\u001B[0m     exception \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m\n\u001B[0;32m--> 191\u001B[0m     resp, content \u001B[38;5;241m=\u001B[39m \u001B[43mhttp\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mrequest\u001B[49m\u001B[43m(\u001B[49m\u001B[43muri\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mmethod\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    192\u001B[0m \u001B[38;5;66;03m# Retry on SSL errors and socket timeout errors.\u001B[39;00m\n\u001B[1;32m    193\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m _ssl_SSLError \u001B[38;5;28;01mas\u001B[39;00m ssl_error:\n",
+      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/httplib2/__init__.py:1724\u001B[0m, in \u001B[0;36mHttp.request\u001B[0;34m(self, uri, method, body, headers, redirections, connection_type)\u001B[0m\n\u001B[1;32m   1722\u001B[0m             content \u001B[38;5;241m=\u001B[39m \u001B[38;5;124mb\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m\"\u001B[39m\n\u001B[1;32m   1723\u001B[0m         \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[0;32m-> 1724\u001B[0m             (response, content) \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_request\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1725\u001B[0m \u001B[43m                \u001B[49m\u001B[43mconn\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mauthority\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43muri\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrequest_uri\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mmethod\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mbody\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mheaders\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mredirections\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcachekey\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1726\u001B[0m \u001B[43m            \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1727\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m   1728\u001B[0m     is_timeout \u001B[38;5;241m=\u001B[39m \u001B[38;5;28misinstance\u001B[39m(e, socket\u001B[38;5;241m.\u001B[39mtimeout)\n",
+      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/httplib2/__init__.py:1444\u001B[0m, in \u001B[0;36mHttp._request\u001B[0;34m(self, conn, host, absolute_uri, request_uri, method, body, headers, redirections, cachekey)\u001B[0m\n\u001B[1;32m   1441\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m auth:\n\u001B[1;32m   1442\u001B[0m     auth\u001B[38;5;241m.\u001B[39mrequest(method, request_uri, headers, body)\n\u001B[0;32m-> 1444\u001B[0m (response, content) \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_conn_request\u001B[49m\u001B[43m(\u001B[49m\u001B[43mconn\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrequest_uri\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mmethod\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mbody\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mheaders\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1446\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m auth:\n\u001B[1;32m   1447\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m auth\u001B[38;5;241m.\u001B[39mresponse(response, body):\n",
+      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/httplib2/__init__.py:1366\u001B[0m, in \u001B[0;36mHttp._conn_request\u001B[0;34m(self, conn, request_uri, method, body, headers)\u001B[0m\n\u001B[1;32m   1364\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m   1365\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m conn\u001B[38;5;241m.\u001B[39msock \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m:\n\u001B[0;32m-> 1366\u001B[0m         \u001B[43mconn\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mconnect\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1367\u001B[0m     conn\u001B[38;5;241m.\u001B[39mrequest(method, request_uri, body, headers)\n\u001B[1;32m   1368\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m socket\u001B[38;5;241m.\u001B[39mtimeout:\n",
+      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/httplib2/__init__.py:1156\u001B[0m, in \u001B[0;36mHTTPSConnectionWithTimeout.connect\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m   1154\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m has_timeout(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mtimeout):\n\u001B[1;32m   1155\u001B[0m     sock\u001B[38;5;241m.\u001B[39msettimeout(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mtimeout)\n\u001B[0;32m-> 1156\u001B[0m \u001B[43msock\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mconnect\u001B[49m\u001B[43m(\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mhost\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mport\u001B[49m\u001B[43m)\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1158\u001B[0m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39msock \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_context\u001B[38;5;241m.\u001B[39mwrap_socket(sock, server_hostname\u001B[38;5;241m=\u001B[39m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mhost)\n\u001B[1;32m   1160\u001B[0m \u001B[38;5;66;03m# Python 3.3 compatibility: emulate the check_hostname behavior\u001B[39;00m\n",
+      "\u001B[0;31mKeyboardInterrupt\u001B[0m: "
+     ]
     }
    ],
    "source": [
-    "agent_chain.run(input=\"What is ChatGPT?\")"
+    "agent_executor.invoke({\"input\": \"What is ChatGPT?\"})"
    ]
   },
   {
@@ -179,15 +196,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to find out who developed ChatGPT\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3mThought: I need to find out who developed ChatGPT\n",
       "Action: Search\n",
-      "Action Input: Who developed ChatGPT\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: ChatGPT was developed by OpenAI.\u001b[0m\n",
+      "Action Input: Who developed ChatGPT\u001B[0m\n",
+      "Observation: \u001B[36;1m\u001B[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer\n",
+      "Final Answer: ChatGPT was developed by OpenAI.\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "\u001B[1m> Finished chain.\u001B[0m\n"
      ]
     },
     {
@@ -202,7 +219,7 @@
     }
    ],
    "source": [
-    "agent_chain.run(input=\"Who developed it?\")"
+    "agent_executor.invoke({\"input\": \"Who developed it?\"})"
    ]
   },
   {
@@ -217,14 +234,14 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
       "Action: Summary\n",
-      "Action Input: My daughter 5 years old\u001b[0m\n",
+      "Action Input: My daughter 5 years old\u001B[0m\n",
       "\n",
-      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
+      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
       "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mThis is a conversation between a human and a bot:\n",
+      "\u001B[32;1m\u001B[1;3mThis is a conversation between a human and a bot:\n",
       "\n",
       "Human: What is ChatGPT?\n",
       "AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\n",
@@ -232,16 +249,16 @@
       "AI: ChatGPT was developed by OpenAI.\n",
       "\n",
       "Write a summary of the conversation for My daughter 5 years old:\n",
-      "\u001b[0m\n",
+      "\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001B[1m> Finished chain.\u001B[0m\n",
       "\n",
-      "Observation: \u001b[33;1m\u001b[1;3m\n",
-      "The conversation was about ChatGPT, an artificial intelligence chatbot. It was created by OpenAI and can send and receive images while chatting.\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
-      "Final Answer: ChatGPT is an artificial intelligence chatbot created by OpenAI that can send and receive images while chatting.\u001b[0m\n",
+      "Observation: \u001B[33;1m\u001B[1;3m\n",
+      "The conversation was about ChatGPT, an artificial intelligence chatbot. It was created by OpenAI and can send and receive images while chatting.\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot created by OpenAI that can send and receive images while chatting.\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "\u001B[1m> Finished chain.\u001B[0m\n"
      ]
     },
     {
@@ -256,8 +273,8 @@
     }
    ],
    "source": [
-    "agent_chain.run(\n",
-    "    input=\"Thanks. Summarize the conversation, for my daughter 5 years old.\"\n",
+    "agent_executor.invoke(\n",
+    "    {\"input\": \"Thanks. Summarize the conversation, for my daughter 5 years old.\"}\n",
     ")"
    ]
   },
@@ -289,9 +306,17 @@
     }
    ],
    "source": [
-    "print(agent_chain.memory.buffer)"
+    "print(agent_executor.memory.buffer)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "84ca95c30e262e00",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": []
+  },
   {
    "cell_type": "markdown",
    "id": "cc3d0aa4",
@@ -340,25 +365,9 @@
     "    ),\n",
     "]\n",
     "\n",
-    "prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
-    "suffix = \"\"\"Begin!\"\n",
-    "\n",
-    "{chat_history}\n",
-    "Question: {input}\n",
-    "{agent_scratchpad}\"\"\"\n",
-    "\n",
-    "prompt = ZeroShotAgent.create_prompt(\n",
-    "    tools,\n",
-    "    prefix=prefix,\n",
-    "    suffix=suffix,\n",
-    "    input_variables=[\"input\", \"chat_history\", \"agent_scratchpad\"],\n",
-    ")\n",
-    "\n",
-    "llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)\n",
-    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)\n",
-    "agent_chain = AgentExecutor.from_agent_and_tools(\n",
-    "    agent=agent, tools=tools, verbose=True, memory=memory\n",
-    ")"
+    "prompt = hub.pull(\"hwchase17/react\")\n",
+    "agent = create_react_agent(model, tools, prompt)\n",
+    "agent_executor = AgentExecutor(agent=agent, tools=tools, memory=memory)"
    ]
   },
   {
@@ -373,15 +382,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I should research ChatGPT to answer this question.\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3mThought: I should research ChatGPT to answer this question.\n",
       "Action: Search\n",
-      "Action Input: \"ChatGPT\"\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
-      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001b[0m\n",
+      "Action Input: \"ChatGPT\"\u001B[0m\n",
+      "Observation: \u001B[36;1m\u001B[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "\u001B[1m> Finished chain.\u001B[0m\n"
      ]
     },
     {
@@ -396,7 +405,7 @@
     }
    ],
    "source": [
-    "agent_chain.run(input=\"What is ChatGPT?\")"
+    "agent_executor.invoke({\"input\": \"What is ChatGPT?\"})"
    ]
   },
   {
@@ -411,15 +420,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to find out who developed ChatGPT\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3mThought: I need to find out who developed ChatGPT\n",
       "Action: Search\n",
-      "Action Input: Who developed ChatGPT\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: ChatGPT was developed by OpenAI.\u001b[0m\n",
+      "Action Input: Who developed ChatGPT\u001B[0m\n",
+      "Observation: \u001B[36;1m\u001B[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer\n",
+      "Final Answer: ChatGPT was developed by OpenAI.\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "\u001B[1m> Finished chain.\u001B[0m\n"
      ]
     },
     {
@@ -434,7 +443,7 @@
     }
    ],
    "source": [
-    "agent_chain.run(input=\"Who developed it?\")"
+    "agent_executor.invoke({\"input\": \"Who developed it?\"})"
    ]
   },
   {
@@ -449,14 +458,14 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
       "Action: Summary\n",
-      "Action Input: My daughter 5 years old\u001b[0m\n",
+      "Action Input: My daughter 5 years old\u001B[0m\n",
       "\n",
-      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
+      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
       "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mThis is a conversation between a human and a bot:\n",
+      "\u001B[32;1m\u001B[1;3mThis is a conversation between a human and a bot:\n",
       "\n",
       "Human: What is ChatGPT?\n",
       "AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\n",
@@ -464,16 +473,16 @@
       "AI: ChatGPT was developed by OpenAI.\n",
       "\n",
       "Write a summary of the conversation for My daughter 5 years old:\n",
-      "\u001b[0m\n",
+      "\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001B[1m> Finished chain.\u001B[0m\n",
       "\n",
-      "Observation: \u001b[33;1m\u001b[1;3m\n",
-      "The conversation was about ChatGPT, an artificial intelligence chatbot developed by OpenAI. It is designed to have conversations with humans and can also send and receive images.\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
-      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI that can have conversations with humans and send and receive images.\u001b[0m\n",
+      "Observation: \u001B[33;1m\u001B[1;3m\n",
+      "The conversation was about ChatGPT, an artificial intelligence chatbot developed by OpenAI. It is designed to have conversations with humans and can also send and receive images.\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI that can have conversations with humans and send and receive images.\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "\u001B[1m> Finished chain.\u001B[0m\n"
      ]
     },
     {
@@ -488,8 +497,8 @@
     }
    ],
    "source": [
-    "agent_chain.run(\n",
-    "    input=\"Thanks. Summarize the conversation, for my daughter 5 years old.\"\n",
+    "agent_executor.invoke(\n",
+    "    {\"input\": \"Thanks. Summarize the conversation, for my daughter 5 years old.\"}\n",
     ")"
    ]
   },
@@ -524,7 +533,7 @@
     }
    ],
    "source": [
-    "print(agent_chain.memory.buffer)"
+    "print(agent_executor.memory.buffer)"
    ]
   }
  ],

cookbook/tool_call_messages.ipynb

@@ -0,0 +1,199 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c48812ed-35bd-4fbe-9a2c-6c7335e5645e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_anthropic import ChatAnthropic\n",
+    "from langchain_core.runnables import ConfigurableField\n",
+    "from langchain_core.tools import tool\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def multiply(x: float, y: float) -> float:\n",
+    "    \"\"\"Multiply 'x' times 'y'.\"\"\"\n",
+    "    return x * y\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def exponentiate(x: float, y: float) -> float:\n",
+    "    \"\"\"Raise 'x' to the 'y'.\"\"\"\n",
+    "    return x**y\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def add(x: float, y: float) -> float:\n",
+    "    \"\"\"Add 'x' and 'y'.\"\"\"\n",
+    "    return x + y\n",
+    "\n",
+    "\n",
+    "tools = [multiply, exponentiate, add]\n",
+    "\n",
+    "gpt35 = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0).bind_tools(tools)\n",
+    "claude3 = ChatAnthropic(model=\"claude-3-sonnet-20240229\").bind_tools(tools)\n",
+    "llm_with_tools = gpt35.configurable_alternatives(\n",
+    "    ConfigurableField(id=\"llm\"), default_key=\"gpt35\", claude3=claude3\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9c186263-1b98-4cb2-b6d1-71f65eb0d811",
+   "metadata": {},
+   "source": [
+    "# LangGraph"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "28fc2c60-7dbc-428a-8983-1a6a15ea30d2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import operator\n",
+    "from typing import Annotated, Sequence, TypedDict\n",
+    "\n",
+    "from langchain_core.messages import AIMessage, BaseMessage, HumanMessage, ToolMessage\n",
+    "from langchain_core.runnables import RunnableLambda\n",
+    "from langgraph.graph import END, StateGraph\n",
+    "\n",
+    "\n",
+    "class AgentState(TypedDict):\n",
+    "    messages: Annotated[Sequence[BaseMessage], operator.add]\n",
+    "\n",
+    "\n",
+    "def should_continue(state):\n",
+    "    return \"continue\" if state[\"messages\"][-1].tool_calls else \"end\"\n",
+    "\n",
+    "\n",
+    "def call_model(state, config):\n",
+    "    return {\"messages\": [llm_with_tools.invoke(state[\"messages\"], config=config)]}\n",
+    "\n",
+    "\n",
+    "def _invoke_tool(tool_call):\n",
+    "    tool = {tool.name: tool for tool in tools}[tool_call[\"name\"]]\n",
+    "    return ToolMessage(tool.invoke(tool_call[\"args\"]), tool_call_id=tool_call[\"id\"])\n",
+    "\n",
+    "\n",
+    "tool_executor = RunnableLambda(_invoke_tool)\n",
+    "\n",
+    "\n",
+    "def call_tools(state):\n",
+    "    last_message = state[\"messages\"][-1]\n",
+    "    return {\"messages\": tool_executor.batch(last_message.tool_calls)}\n",
+    "\n",
+    "\n",
+    "workflow = StateGraph(AgentState)\n",
+    "workflow.add_node(\"agent\", call_model)\n",
+    "workflow.add_node(\"action\", call_tools)\n",
+    "workflow.set_entry_point(\"agent\")\n",
+    "workflow.add_conditional_edges(\n",
+    "    \"agent\",\n",
+    "    should_continue,\n",
+    "    {\n",
+    "        \"continue\": \"action\",\n",
+    "        \"end\": END,\n",
+    "    },\n",
+    ")\n",
+    "workflow.add_edge(\"action\", \"agent\")\n",
+    "graph = workflow.compile()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3710e724-2595-4625-ba3a-effb81e66e4a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'messages': [HumanMessage(content=\"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"),\n",
+       "  AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_6yMU2WsS4Bqgi1WxFHxtfJRc', 'function': {'arguments': '{\"x\": 8, \"y\": 2.743}', 'name': 'exponentiate'}, 'type': 'function'}, {'id': 'call_GAL3dQiKFF9XEV0RrRLPTvVp', 'function': {'arguments': '{\"x\": 17.24, \"y\": -918.1241}', 'name': 'add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 58, 'prompt_tokens': 168, 'total_tokens': 226}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-528302fc-7acf-4c11-82c4-119ccf40c573-0', tool_calls=[{'name': 'exponentiate', 'args': {'x': 8, 'y': 2.743}, 'id': 'call_6yMU2WsS4Bqgi1WxFHxtfJRc'}, {'name': 'add', 'args': {'x': 17.24, 'y': -918.1241}, 'id': 'call_GAL3dQiKFF9XEV0RrRLPTvVp'}]),\n",
+       "  ToolMessage(content='300.03770462067547', tool_call_id='call_6yMU2WsS4Bqgi1WxFHxtfJRc'),\n",
+       "  ToolMessage(content='-900.8841', tool_call_id='call_GAL3dQiKFF9XEV0RrRLPTvVp'),\n",
+       "  AIMessage(content='The result of \\\\(3 + 5^{2.743}\\\\) is approximately 300.04, and the result of \\\\(17.24 - 918.1241\\\\) is approximately -900.88.', response_metadata={'token_usage': {'completion_tokens': 44, 'prompt_tokens': 251, 'total_tokens': 295}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'stop', 'logprobs': None}, id='run-d1161669-ed09-4b18-94bd-6d8530df5aa8-0')]}"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "graph.invoke(\n",
+    "    {\n",
+    "        \"messages\": [\n",
+    "            HumanMessage(\n",
+    "                \"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"\n",
+    "            )\n",
+    "        ]\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "073c074e-d722-42e0-85ec-c62c079207e4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'messages': [HumanMessage(content=\"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"),\n",
+       "  AIMessage(content=[{'text': \"Okay, let's break this down into two parts:\", 'type': 'text'}, {'id': 'toolu_01DEhqcXkXTtzJAiZ7uMBeDC', 'input': {'x': 3, 'y': 5}, 'name': 'add', 'type': 'tool_use'}], response_metadata={'id': 'msg_01AkLGH8sxMHaH15yewmjwkF', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 450, 'output_tokens': 81}}, id='run-f35bfae8-8ded-4f8a-831b-0940d6ad16b6-0', tool_calls=[{'name': 'add', 'args': {'x': 3, 'y': 5}, 'id': 'toolu_01DEhqcXkXTtzJAiZ7uMBeDC'}]),\n",
+       "  ToolMessage(content='8.0', tool_call_id='toolu_01DEhqcXkXTtzJAiZ7uMBeDC'),\n",
+       "  AIMessage(content=[{'id': 'toolu_013DyMLrvnrto33peAKMGMr1', 'input': {'x': 8.0, 'y': 2.743}, 'name': 'exponentiate', 'type': 'tool_use'}], response_metadata={'id': 'msg_015Fmp8aztwYcce2JDAFfce3', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 545, 'output_tokens': 75}}, id='run-48aaeeeb-a1e5-48fd-a57a-6c3da2907b47-0', tool_calls=[{'name': 'exponentiate', 'args': {'x': 8.0, 'y': 2.743}, 'id': 'toolu_013DyMLrvnrto33peAKMGMr1'}]),\n",
+       "  ToolMessage(content='300.03770462067547', tool_call_id='toolu_013DyMLrvnrto33peAKMGMr1'),\n",
+       "  AIMessage(content=[{'text': 'So 3 plus 5 raised to the 2.743 power is 300.04.\\n\\nFor the second part:', 'type': 'text'}, {'id': 'toolu_01UTmMrGTmLpPrPCF1rShN46', 'input': {'x': 17.24, 'y': -918.1241}, 'name': 'add', 'type': 'tool_use'}], response_metadata={'id': 'msg_015TkhfRBENPib2RWAxkieH6', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 638, 'output_tokens': 105}}, id='run-45fb62e3-d102-4159-881d-241c5dbadeed-0', tool_calls=[{'name': 'add', 'args': {'x': 17.24, 'y': -918.1241}, 'id': 'toolu_01UTmMrGTmLpPrPCF1rShN46'}]),\n",
+       "  ToolMessage(content='-900.8841', tool_call_id='toolu_01UTmMrGTmLpPrPCF1rShN46'),\n",
+       "  AIMessage(content='Therefore, 17.24 - 918.1241 = -900.8841', response_metadata={'id': 'msg_01LgKnRuUcSyADCpxv9tPoYD', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 759, 'output_tokens': 24}}, id='run-1008254e-ccd1-497c-8312-9550dd77bd08-0')]}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "graph.invoke(\n",
+    "    {\n",
+    "        \"messages\": [\n",
+    "            HumanMessage(\n",
+    "                \"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"\n",
+    "            )\n",
+    "        ]\n",
+    "    },\n",
+    "    config={\"configurable\": {\"llm\": \"claude3\"}},\n",
+    ")"
+   ]
+  }
+ ],
+ "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": 5
+}

cookbook/twitter-the-algorithm-analysis-deeplake.ipynb

@@ -3811,7 +3811,7 @@
     "from langchain.chains import ConversationalRetrievalChain\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "model = ChatOpenAI(model_name=\"gpt-3.5-turbo-0613\")  # switch to 'gpt-4'\n",
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo-0613\")  # switch to 'gpt-4'\n",
     "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
    ]
   },

cookbook/two_agent_debate_tools.ipynb

@@ -424,7 +424,7 @@
     "    DialogueAgentWithTools(\n",
     "        name=name,\n",
     "        system_message=SystemMessage(content=system_message),\n",
-    "        model=ChatOpenAI(model_name=\"gpt-4\", temperature=0.2),\n",
+    "        model=ChatOpenAI(model=\"gpt-4\", temperature=0.2),\n",
     "        tool_names=tools,\n",
     "        top_k_results=2,\n",
     "    )\n",

cookbook/wikibase_agent.ipynb

@@ -601,7 +601,7 @@
    "source": [
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0)"
+    "llm = ChatOpenAI(model=\"gpt-4\", temperature=0)"
    ]
   },
   {

docs/docs/contributing/integrations.mdx

@@ -190,12 +190,9 @@ Maintainer steps (Contributors should **not** do these):
 
 ## Partner package in external repo
 
-If you are creating a partner package in an external repo, you should follow the same steps as above, 
-but you will need to set up your own CI/CD and package management.
+Partner packages in external repos must be coordinated between the LangChain team and
+the partner organization to ensure that they are maintained and updated.
 
-Name your package as `langchain-{partner}-{integration}`.
-
-Still, you have to create the `libs/partners/{partner}-{integration}` folder in the `LangChain` monorepo
-and add a `README.md` file with a link to the external repo. 
-See this [example](https://github.com/langchain-ai/langchain/tree/master/libs/partners/google-genai).
-This allows keeping track of all the partner packages in the `LangChain` documentation.
+If you're interested in creating a partner package in an external repo, please start
+with one in the LangChain repo, and then reach out to the LangChain team to discuss
+how to move it to an external repo.

docs/docs/expression_language/get_started.ipynb

@@ -440,7 +440,7 @@
    "id": "e6833844-f1c4-444c-a3d2-31b3c6b31d46",
    "metadata": {},
    "source": [
-    "We then use the `RunnableParallel` to prepare the expected inputs into the prompt by using the entries for the retrieved documents as well as the original user question, using the retriever for document search, and RunnablePassthrough to pass the user’s question:"
+    "We then use the `RunnableParallel` to prepare the expected inputs into the prompt by using the entries for the retrieved documents as well as the original user question, using the retriever for document search, and `RunnablePassthrough` to pass the user’s question:"
    ]
   },
   {

docs/docs/get_started/quickstart.mdx

@@ -94,12 +94,12 @@ from langchain_openai import ChatOpenAI
 llm = ChatOpenAI()
 ```
 
-If you'd prefer not to set an environment variable you can pass the key in directly via the `openai_api_key` named parameter when initiating the OpenAI LLM class:
+If you'd prefer not to set an environment variable you can pass the key in directly via the `api_key` named parameter when initiating the OpenAI LLM class:
 
 ```python
 from langchain_openai import ChatOpenAI
 
-llm = ChatOpenAI(openai_api_key="...")
+llm = ChatOpenAI(api_key="...")
 ```
 
   </TabItem>
@@ -141,10 +141,10 @@ from langchain_anthropic import ChatAnthropic
 llm = ChatAnthropic(model="claude-3-sonnet-20240229", temperature=0.2, max_tokens=1024)
 ```
 
-If you'd prefer not to set an environment variable you can pass the key in directly via the `anthropic_api_key` named parameter when initiating the Anthropic Chat Model class:
+If you'd prefer not to set an environment variable you can pass the key in directly via the `api_key` named parameter when initiating the Anthropic Chat Model class:
 
 ```python
-llm = ChatAnthropic(anthropic_api_key="...")
+llm = ChatAnthropic(api_key="...")
 ```
 
   </TabItem>
@@ -509,7 +509,7 @@ from langchain.agents import AgentExecutor
 # Get the prompt to use - you can modify this!
 prompt = hub.pull("hwchase17/openai-functions-agent")
 
-# You need to set OPENAI_API_KEY environment variable or pass it as argument `openai_api_key`.
+# You need to set OPENAI_API_KEY environment variable or pass it as argument `api_key`.
 llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
 agent = create_openai_functions_agent(llm, tools, prompt)
 agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

docs/docs/guides/development/debugging.md

@@ -27,7 +27,7 @@ Let's suppose we have a simple agent, and want to visualize the actions it takes
 from langchain.agents import AgentType, initialize_agent, load_tools
 from langchain_openai import ChatOpenAI
 
-llm = ChatOpenAI(model_name="gpt-4", temperature=0)
+llm = ChatOpenAI(model="gpt-4", temperature=0)
 tools = load_tools(["ddg-search", "llm-math"], llm=llm)
 agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION)
 ```

docs/docs/guides/productionization/fallbacks.ipynb

@@ -204,7 +204,7 @@
     "    ]\n",
     ")\n",
     "# Here we're going to use a bad model name to easily create a chain that will error\n",
-    "chat_model = ChatOpenAI(model_name=\"gpt-fake\")\n",
+    "chat_model = ChatOpenAI(model=\"gpt-fake\")\n",
     "bad_chain = chat_prompt | chat_model | StrOutputParser()"
    ]
   },

docs/docs/integrations/chat/google_generative_ai.ipynb

@@ -6,7 +6,7 @@
    "metadata": {},
    "source": [
     "---\n",
-    "sidebar_label: Google AI\n",
+    "sidebar_label: Google Generative AI\n",
     "keywords: [gemini, ChatGoogleGenerativeAI, gemini-pro]\n",
     "---"
    ]
@@ -389,7 +389,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/google_vertex_ai_palm.ipynb

@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -261,31 +261,46 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pprint import pprint\n",
+    "\n",
+    "from langchain_core.messages import HumanMessage\n",
+    "from langchain_google_vertexai import HarmBlockThreshold, HarmCategory"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'is_blocked': False,\n",
-      " 'safety_ratings': [{'category': 'HARM_CATEGORY_HARASSMENT',\n",
+      "{'citation_metadata': None,\n",
+      " 'is_blocked': False,\n",
+      " 'safety_ratings': [{'blocked': False,\n",
+      "                     'category': 'HARM_CATEGORY_HATE_SPEECH',\n",
       "                     'probability_label': 'NEGLIGIBLE'},\n",
-      "                    {'category': 'HARM_CATEGORY_HATE_SPEECH',\n",
+      "                    {'blocked': False,\n",
+      "                     'category': 'HARM_CATEGORY_DANGEROUS_CONTENT',\n",
       "                     'probability_label': 'NEGLIGIBLE'},\n",
-      "                    {'category': 'HARM_CATEGORY_SEXUALLY_EXPLICIT',\n",
+      "                    {'blocked': False,\n",
+      "                     'category': 'HARM_CATEGORY_HARASSMENT',\n",
       "                     'probability_label': 'NEGLIGIBLE'},\n",
-      "                    {'category': 'HARM_CATEGORY_DANGEROUS_CONTENT',\n",
-      "                     'probability_label': 'NEGLIGIBLE'}]}\n"
+      "                    {'blocked': False,\n",
+      "                     'category': 'HARM_CATEGORY_SEXUALLY_EXPLICIT',\n",
+      "                     'probability_label': 'NEGLIGIBLE'}],\n",
+      " 'usage_metadata': {'candidates_token_count': 6,\n",
+      "                    'prompt_token_count': 12,\n",
+      "                    'total_token_count': 18}}\n"
      ]
     }
    ],
    "source": [
-    "from pprint import pprint\n",
-    "\n",
-    "from langchain_core.messages import HumanMessage\n",
-    "from langchain_google_vertexai import ChatVertexAI, HarmBlockThreshold, HarmCategory\n",
-    "\n",
     "human = \"Translate this sentence from English to French. I love programming.\"\n",
     "messages = [HumanMessage(content=human)]\n",
     "\n",
@@ -315,18 +330,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'is_blocked': False,\n",
-      " 'safety_attributes': {'Derogatory': 0.1,\n",
-      "                       'Finance': 0.3,\n",
-      "                       'Insult': 0.1,\n",
-      "                       'Sexual': 0.1}}\n"
+      "{'errors': (),\n",
+      " 'grounding_metadata': {'citations': [], 'search_queries': []},\n",
+      " 'is_blocked': False,\n",
+      " 'safety_attributes': [{'Derogatory': 0.1, 'Insult': 0.1, 'Sexual': 0.2}],\n",
+      " 'usage_metadata': {'candidates_billable_characters': 88.0,\n",
+      "                    'candidates_token_count': 24.0,\n",
+      "                    'prompt_billable_characters': 58.0,\n",
+      "                    'prompt_token_count': 12.0}}\n"
      ]
     }
    ],
@@ -341,40 +359,149 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Function Calling with Gemini\n",
+    "## Tool calling (a.k.a. function calling) with Gemini\n",
     "\n",
-    "We can call Gemini models with tools."
+    "We can pass tool definitions to Gemini models to get the model to invoke those tools when appropriate. This is useful not only for LLM-powered tool use but also for getting structured outputs out of models more generally.\n",
+    "\n",
+    "With `ChatVertexAI.bind_tools()`, we can easily pass in Pydantic classes, dict schemas, LangChain tools, or even functions as tools to the model. Under the hood these are converted to a Gemini tool schema, which looks like:\n",
+    "```python\n",
+    "{\n",
+    "    \"name\": \"...\",  # tool name\n",
+    "    \"description\": \"...\",  # tool description\n",
+    "    \"parameters\": {...}  # tool input schema as JSONSchema\n",
+    "}\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'function_call': {'name': 'GetWeather', 'arguments': '{\"location\": \"San Francisco, CA\"}'}}, response_metadata={'is_blocked': False, 'safety_ratings': [{'category': 'HARM_CATEGORY_HATE_SPEECH', 'probability_label': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_DANGEROUS_CONTENT', 'probability_label': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_HARASSMENT', 'probability_label': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_SEXUALLY_EXPLICIT', 'probability_label': 'NEGLIGIBLE', 'blocked': False}], 'citation_metadata': None, 'usage_metadata': {'prompt_token_count': 41, 'candidates_token_count': 7, 'total_token_count': 48}}, id='run-05e760dc-0682-4286-88e1-5b23df69b083-0', tool_calls=[{'name': 'GetWeather', 'args': {'location': 'San Francisco, CA'}, 'id': 'cd2499c4-4513-4059-bfff-5321b6e922d0'}])"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class GetWeather(BaseModel):\n",
+    "    \"\"\"Get the current weather in a given location\"\"\"\n",
+    "\n",
+    "    location: str = Field(..., description=\"The city and state, e.g. San Francisco, CA\")\n",
+    "\n",
+    "\n",
+    "llm = ChatVertexAI(model_name=\"gemini-pro\", temperature=0)\n",
+    "llm_with_tools = llm.bind_tools([GetWeather])\n",
+    "ai_msg = llm_with_tools.invoke(\n",
+    "    \"what is the weather like in San Francisco\",\n",
+    ")\n",
+    "ai_msg"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The tool calls can be access via the `AIMessage.tool_calls` attribute, where they are extracted in a model-agnostic format:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'GetWeather',\n",
+       "  'args': {'location': 'San Francisco, CA'},\n",
+       "  'id': 'cd2499c4-4513-4059-bfff-5321b6e922d0'}]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ai_msg.tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "For a complete guide on tool calling [head here](/docs/modules/model_io/chat/function_calling/)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Structured outputs\n",
+    "\n",
+    "Many applications require structured model outputs. Tool calling makes it much easier to do this reliably. The [with_structured_outputs](https://api.python.langchain.com/en/latest/chat_models/langchain_google_vertexai.chat_models.ChatVertexAI.html) constructor provides a simple interface built on top of tool calling for getting structured outputs out of a model. For a complete guide on structured outputs [head here](/docs/modules/model_io/chat/structured_output/).\n",
+    "\n",
+    "###  ChatVertexAI.with_structured_outputs()\n",
+    "\n",
+    "To get structured outputs from our Gemini model all we need to do is to specify a desired schema, either as a Pydantic class or as a JSON schema, "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Person(name='Stefan', age=13)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "class Person(BaseModel):\n",
+    "    \"\"\"Save information about a person.\"\"\"\n",
+    "\n",
+    "    name: str = Field(..., description=\"The person's name.\")\n",
+    "    age: int = Field(..., description=\"The person's age.\")\n",
+    "\n",
+    "\n",
+    "structured_llm = llm.with_structured_output(Person)\n",
+    "structured_llm.invoke(\"Stefan is already 13 years old\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### [Legacy] Using `create_structured_runnable()`\n",
+    "\n",
+    "The legacy wasy to get structured outputs is using the `create_structured_runnable` constructor:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "MyModel(name='Erick', age=27)"
-      ]
-     },
-     "execution_count": null,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "from langchain.pydantic_v1 import BaseModel\n",
     "from langchain_google_vertexai import create_structured_runnable\n",
     "\n",
-    "llm = ChatVertexAI(model_name=\"gemini-pro\")\n",
-    "\n",
-    "\n",
-    "class MyModel(BaseModel):\n",
-    "    name: str\n",
-    "    age: int\n",
-    "\n",
-    "\n",
-    "chain = create_structured_runnable(MyModel, llm)\n",
+    "chain = create_structured_runnable(Person, llm)\n",
     "chain.invoke(\"My name is Erick and I'm 27 years old\")"
    ]
   },
@@ -484,11 +611,21 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "",
-   "name": ""
+   "display_name": "poetry-venv-2",
+   "language": "python",
+   "name": "poetry-venv-2"
   },
   "language_info": {
-   "name": "python"
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/mistralai.ipynb

@@ -48,7 +48,7 @@
    "source": [
     "import getpass\n",
     "\n",
-    "mistral_api_key = getpass.getpass()"
+    "api_key = getpass.getpass()"
    ]
   },
   {
@@ -81,8 +81,8 @@
    },
    "outputs": [],
    "source": [
-    "# If mistral_api_key is not passed, default behavior is to use the `MISTRAL_API_KEY` environment variable.\n",
-    "chat = ChatMistralAI(mistral_api_key=mistral_api_key)"
+    "# If api_key is not passed, default behavior is to use the `MISTRAL_API_KEY` environment variable.\n",
+    "chat = ChatMistralAI(api_key=api_key)"
    ]
   },
   {

docs/docs/integrations/chat/mlx.ipynb

@@ -0,0 +1,217 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# MLX\n",
+    "\n",
+    "This notebook shows how to get started using `MLX` LLM's as chat models.\n",
+    "\n",
+    "In particular, we will:\n",
+    "1. Utilize the [MLXPipeline](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/llms/mlx_pipelines.py), \n",
+    "2. Utilize the `ChatMLX` class to enable any of these LLMs to interface with LangChain's [Chat Messages](https://python.langchain.com/docs/modules/model_io/chat/#messages) abstraction.\n",
+    "3. Demonstrate how to use an open-source LLM to power an `ChatAgent` pipeline\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  mlx-lm transformers huggingface_hub"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 1. Instantiate an LLM\n",
+    "\n",
+    "There are three LLM options to choose from."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.llms.mlx_pipeline import MLXPipeline\n",
+    "\n",
+    "llm = MLXPipeline.from_model_id(\n",
+    "    \"mlx-community/quantized-gemma-2b-it\",\n",
+    "    pipeline_kwargs={\"max_tokens\": 10, \"temp\": 0.1},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 2. Instantiate the `ChatMLX` to apply chat templates"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Instantiate the chat model and some messages to pass."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.schema import (\n",
+    "    HumanMessage,\n",
+    ")\n",
+    "from langchain_community.chat_models.mlx import ChatMLX\n",
+    "\n",
+    "messages = [\n",
+    "    HumanMessage(\n",
+    "        content=\"What happens when an unstoppable force meets an immovable object?\"\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "chat_model = ChatMLX(llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Inspect how the chat messages are formatted for the LLM call."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat_model._to_chat_prompt(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Call the model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "res = chat_model.invoke(messages)\n",
+    "print(res.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 3. Take it for a spin as an agent!\n",
+    "\n",
+    "Here we'll test out `gemma-2b-it` as a zero-shot `ReAct` Agent. The example below is taken from [here](https://python.langchain.com/docs/modules/agents/agent_types/react#using-chat-models).\n",
+    "\n",
+    "> Note: To run this section, you'll need to have a [SerpAPI Token](https://serpapi.com/) saved as an environment variable: `SERPAPI_API_KEY`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain import hub\n",
+    "from langchain.agents import AgentExecutor, load_tools\n",
+    "from langchain.agents.format_scratchpad import format_log_to_str\n",
+    "from langchain.agents.output_parsers import (\n",
+    "    ReActJsonSingleInputOutputParser,\n",
+    ")\n",
+    "from langchain.tools.render import render_text_description\n",
+    "from langchain_community.utilities import SerpAPIWrapper"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Configure the agent with a `react-json` style prompt and access to a search engine and calculator."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# setup tools\n",
+    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)\n",
+    "\n",
+    "# setup ReAct style prompt\n",
+    "prompt = hub.pull(\"hwchase17/react-json\")\n",
+    "prompt = prompt.partial(\n",
+    "    tools=render_text_description(tools),\n",
+    "    tool_names=\", \".join([t.name for t in tools]),\n",
+    ")\n",
+    "\n",
+    "# define the agent\n",
+    "chat_model_with_stop = chat_model.bind(stop=[\"\\nObservation\"])\n",
+    "agent = (\n",
+    "    {\n",
+    "        \"input\": lambda x: x[\"input\"],\n",
+    "        \"agent_scratchpad\": lambda x: format_log_to_str(x[\"intermediate_steps\"]),\n",
+    "    }\n",
+    "    | prompt\n",
+    "    | chat_model_with_stop\n",
+    "    | ReActJsonSingleInputOutputParser()\n",
+    ")\n",
+    "\n",
+    "# instantiate AgentExecutor\n",
+    "agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent_executor.invoke(\n",
+    "    {\n",
+    "        \"input\": \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"\n",
+    "    }\n",
+    ")"
+   ]
+  }
+ ],
+ "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": "3.9.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/docs/integrations/chat/openai.ipynb

@@ -22,7 +22,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 3,
    "id": "522686de",
    "metadata": {
     "tags": []
@@ -30,24 +30,20 @@
    "outputs": [],
    "source": [
     "from langchain_core.messages import HumanMessage, SystemMessage\n",
-    "from langchain_core.prompts.chat import (\n",
-    "    ChatPromptTemplate,\n",
-    "    HumanMessagePromptTemplate,\n",
-    "    SystemMessagePromptTemplate,\n",
-    ")\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
     "from langchain_openai import ChatOpenAI"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
    "id": "62e0dbc3",
    "metadata": {
     "tags": []
    },
    "outputs": [],
    "source": [
-    "chat = ChatOpenAI(temperature=0)"
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
    ]
   },
   {
@@ -58,14 +54,14 @@
     "The above cell assumes that your OpenAI API key is set in your environment variables. If you would rather manually specify your API key and/or organization ID, use the following code:\n",
     "\n",
     "```python\n",
-    "chat = ChatOpenAI(temperature=0, openai_api_key=\"YOUR_API_KEY\", openai_organization=\"YOUR_ORGANIZATION_ID\")\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0, api_key=\"YOUR_API_KEY\", openai_organization=\"YOUR_ORGANIZATION_ID\")\n",
     "```\n",
     "Remove the openai_organization parameter should it not apply to you."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "id": "ce16ad78-8e6f-48cd-954e-98be75eb5836",
    "metadata": {
     "tags": []
@@ -74,63 +70,7 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"J'adore la programmation.\", additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "messages = [\n",
-    "    SystemMessage(\n",
-    "        content=\"You are a helpful assistant that translates English to French.\"\n",
-    "    ),\n",
-    "    HumanMessage(\n",
-    "        content=\"Translate this sentence from English to French. I love programming.\"\n",
-    "    ),\n",
-    "]\n",
-    "chat.invoke(messages)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "778f912a-66ea-4a5d-b3de-6c7db4baba26",
-   "metadata": {},
-   "source": [
-    "You can make use of templating by using a `MessagePromptTemplate`. You can build a `ChatPromptTemplate` from one or more `MessagePromptTemplates`. You can use `ChatPromptTemplate`'s `format_prompt` -- this returns a `PromptValue`, which you can convert to a string or Message object, depending on whether you want to use the formatted value as input to an llm or chat model.\n",
-    "\n",
-    "For convenience, there is a `from_template` method exposed on the template. If you were to use this template, this is what it would look like:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "180c5cc8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "template = (\n",
-    "    \"You are a helpful assistant that translates {input_language} to {output_language}.\"\n",
-    ")\n",
-    "system_message_prompt = SystemMessagePromptTemplate.from_template(template)\n",
-    "human_template = \"{text}\"\n",
-    "human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "fbb043e6",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"J'adore la programmation.\", additional_kwargs={}, example=False)"
+       "AIMessage(content=\"J'adore programmer.\", response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 34, 'total_tokens': 40}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'stop', 'logprobs': None}, id='run-8591eae1-b42b-402b-a23a-dfdb0cd151bd-0')"
       ]
      },
      "execution_count": 5,
@@ -139,18 +79,168 @@
     }
    ],
    "source": [
-    "chat_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [system_message_prompt, human_message_prompt]\n",
+    "messages = [\n",
+    "    (\"system\", \"You are a helpful assistant that translates English to French.\"),\n",
+    "    (\"human\", \"Translate this sentence from English to French. I love programming.\"),\n",
+    "]\n",
+    "llm.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "778f912a-66ea-4a5d-b3de-6c7db4baba26",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "We can chain our model with a prompt template like so:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "fbb043e6",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Ich liebe Programmieren.', response_metadata={'token_usage': {'completion_tokens': 5, 'prompt_tokens': 26, 'total_tokens': 31}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'stop', 'logprobs': None}, id='run-94fa6741-c99b-4513-afce-c3f562631c79-0')"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
     ")\n",
     "\n",
-    "# get a chat completion from the formatted messages\n",
-    "chat.invoke(\n",
-    "    chat_prompt.format_prompt(\n",
-    "        input_language=\"English\", output_language=\"French\", text=\"I love programming.\"\n",
-    "    ).to_messages()\n",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "0b1b52a5-b58d-40c9-bcdd-88eb8fb351e2",
+   "metadata": {},
+   "source": [
+    "## Tool calling\n",
+    "\n",
+    "OpenAI has a [tool calling](https://platform.openai.com/docs/guides/function-calling) (we use \"tool calling\" and \"function calling\" interchangeably here) API that lets you describe tools and their arguments, and have the model return a JSON object with a tool to invoke and the inputs to that tool. tool-calling is extremely useful for building tool-using chains and agents, and for getting structured outputs from models more generally.\n",
+    "\n",
+    "### ChatOpenAI.bind_tools()\n",
+    "\n",
+    "With `ChatAnthropic.bind_tools`, we can easily pass in Pydantic classes, dict schemas, LangChain tools, or even functions as tools to the model. Under the hood these are converted to an Anthropic tool schemas, which looks like:\n",
+    "```\n",
+    "{\n",
+    "    \"name\": \"...\",\n",
+    "    \"description\": \"...\",\n",
+    "    \"parameters\": {...}  # JSONSchema\n",
+    "}\n",
+    "```\n",
+    "and passed in every model invocation."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "b7ea7690-ec7a-4337-b392-e87d1f39a6ec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class GetWeather(BaseModel):\n",
+    "    \"\"\"Get the current weather in a given location\"\"\"\n",
+    "\n",
+    "    location: str = Field(..., description=\"The city and state, e.g. San Francisco, CA\")\n",
+    "\n",
+    "\n",
+    "llm_with_tools = llm.bind_tools([GetWeather])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "1d1ab955-6a68-42f8-bb5d-86eb1111478a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_H7fABDuzEau48T10Qn0Lsh0D', 'function': {'arguments': '{\"location\":\"San Francisco\"}', 'name': 'GetWeather'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 15, 'prompt_tokens': 70, 'total_tokens': 85}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-b469135e-2718-446a-8164-eef37e672ba2-0', tool_calls=[{'name': 'GetWeather', 'args': {'location': 'San Francisco'}, 'id': 'call_H7fABDuzEau48T10Qn0Lsh0D'}])"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ai_msg = llm_with_tools.invoke(\n",
+    "    \"what is the weather like in San Francisco\",\n",
+    ")\n",
+    "ai_msg"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "768d1ae4-4b1a-48eb-a329-c8d5051067a3",
+   "metadata": {},
+   "source": [
+    "### AIMessage.tool_calls\n",
+    "Notice that the AIMessage has a `tool_calls` attribute. This contains in a standardized ToolCall format that is model-provider agnostic."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "166cb7ce-831d-4a7c-9721-abc107f11084",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'GetWeather',\n",
+       "  'args': {'location': 'San Francisco'},\n",
+       "  'id': 'call_H7fABDuzEau48T10Qn0Lsh0D'}]"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ai_msg.tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e082c9ac-c7c7-4aff-a8ec-8e220262a59c",
+   "metadata": {},
+   "source": [
+    "For more on binding tools and tool call outputs, head to the [tool calling](/docs/modules/model_io/chat/function_calling/) docs."
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "57e27714",
@@ -205,7 +295,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat_loaders/telegram.ipynb

@@ -10,7 +10,7 @@
     "This notebook shows how to use the Telegram chat loader. This class helps map exported Telegram conversations to LangChain chat messages.\n",
     "\n",
     "The process has three steps:\n",
-    "1. Export  the chat .txt file by copying chats from the Discord app and pasting them in a file on your local computer\n",
+    "1. Export  the chat .txt file by copying chats from the Telegram app and pasting them in a file on your local computer\n",
     "2. Create the `TelegramChatLoader` with the file path pointed to the json file or directory of JSON files\n",
     "3. Call `loader.load()` (or `loader.lazy_load()`) to perform the conversion. Optionally use `merge_chat_runs` to combine message from the same sender in sequence, and/or `map_ai_messages` to convert messages from the specified sender to the \"AIMessage\" class.\n",
     "\n",

docs/docs/integrations/document_loaders/pebblo.ipynb

@@ -62,6 +62,35 @@
     "documents = loader.load()\n",
     "print(documents)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Send semantic topics and identities to Pebblo cloud server\n",
+    "\n",
+    "To send semantic data to pebblo-cloud, pass api-key to PebbloSafeLoader as an argument or alternatively, put the api-ket in `PEBBLO_API_KEY` environment variable."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders.csv_loader import CSVLoader\n",
+    "from langchain_community.document_loaders import PebbloSafeLoader\n",
+    "\n",
+    "loader = PebbloSafeLoader(\n",
+    "    CSVLoader(\"data/corp_sens_data.csv\"),\n",
+    "    name=\"acme-corp-rag-1\",  # App name (Mandatory)\n",
+    "    owner=\"Joe Smith\",  # Owner (Optional)\n",
+    "    description=\"Support productivity RAG application\",  # Description (Optional)\n",
+    "    api_key=\"my-api-key\",  # API key (Optional, can be set in the environment variable PEBBLO_API_KEY)\n",
+    ")\n",
+    "documents = loader.load()\n",
+    "print(documents)"
+   ]
   }
  ],
  "metadata": {

docs/docs/integrations/document_loaders/youtube_audio.ipynb

@@ -218,7 +218,7 @@
    "source": [
     "# Build a QA chain\n",
     "qa_chain = RetrievalQA.from_chain_type(\n",
-    "    llm=ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0),\n",
+    "    llm=ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0),\n",
     "    chain_type=\"stuff\",\n",
     "    retriever=vectordb.as_retriever(),\n",
     ")"

docs/docs/integrations/graphs/amazon_neptune_open_cypher.ipynb

@@ -12,12 +12,23 @@
     ">\n",
     ">[Cypher](https://en.wikipedia.org/wiki/Cypher_(query_language)) is a declarative graph query language that allows for expressive and efficient data querying in a property graph.\n",
     ">\n",
-    ">[openCypher](https://opencypher.org/) is an open-source implementation of Cypher."
+    ">[openCypher](https://opencypher.org/) is an open-source implementation of Cypher.",
+    "# Neptune Open Cypher QA Chain\n",
+    "This QA chain queries Amazon Neptune using openCypher and returns human readable response\n",
+    "\n",
+    "LangChain supports both [Neptune Database](https://docs.aws.amazon.com/neptune/latest/userguide/intro.html) and [Neptune Analytics](https://docs.aws.amazon.com/neptune-analytics/latest/userguide/what-is-neptune-analytics.html) with `NeptuneOpenCypherQAChain` \n",
+    "\n",
+    "\n",
+    "Neptune Database is a serverless graph database designed for optimal scalability and availability. It provides a solution for graph database workloads that need to scale to 100,000 queries per second, Multi-AZ high availability, and multi-Region deployments. You can use Neptune Database for social networking, fraud alerting, and Customer 360 applications.\n",
+    "\n",
+    "Neptune Analytics is an analytics database engine that can quickly analyze large amounts of graph data in memory to get insights and find trends. Neptune Analytics is a solution for quickly analyzing existing graph databases or graph datasets stored in a data lake. It uses popular graph analytic algorithms and low-latency analytic queries.\n",
+    "\n",
+    "## Using Neptune Database"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -30,9 +41,36 @@
     "graph = NeptuneGraph(host=host, port=port, use_https=use_https)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Using Neptune Analytics"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.graphs import NeptuneAnalyticsGraph\n",
+    "\n",
+    "graph = NeptuneAnalyticsGraph(graph_identifier=\"<neptune-analytics-graph-id>\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Using NeptuneOpenCypherQAChain\n",
+    "\n",
+    "This QA chain queries Neptune graph database using openCypher and returns human readable response."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -54,7 +92,7 @@
     "\n",
     "chain = NeptuneOpenCypherQAChain.from_llm(llm=llm, graph=graph)\n",
     "\n",
-    "chain.run(\"how many outgoing routes does the Austin airport have?\")"
+    "chain.invoke(\"how many outgoing routes does the Austin airport have?\")"
    ]
   }
  ],

docs/docs/integrations/graphs/falkordb.ipynb

@@ -22,7 +22,7 @@
     "You can run the `falkordb` Docker container locally:\n",
     "\n",
     "```bash\n",
-    "docker run -p 6379:6379 -it --rm falkordb/falkordb:edge\n",
+    "docker run -p 6379:6379 -it --rm falkordb/falkordb\n",
     "```\n",
     "\n",
     "Once launched, you create a database on the local machine and connect to it."

docs/docs/integrations/llms/bittensor.ipynb

@@ -136,45 +136,29 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from langchain import hub\n",
     "from langchain.agents import (\n",
     "    AgentExecutor,\n",
-    "    ZeroShotAgent,\n",
+    "    create_react_agent,\n",
     ")\n",
-    "from langchain.chains import LLMChain\n",
     "from langchain.memory import ConversationBufferMemory\n",
     "from langchain_community.llms import NIBittensorLLM\n",
-    "from langchain_core.prompts import PromptTemplate\n",
-    "\n",
-    "memory = ConversationBufferMemory(memory_key=\"chat_history\")\n",
     "\n",
     "tools = [tool]\n",
-    "prefix = \"\"\"Answer prompt based on LLM if there is need to search something then use internet and observe internet result and give accurate reply of user questions also try to use authenticated sources\"\"\"\n",
-    "suffix = \"\"\"Begin!\n",
-    "            {chat_history}\n",
-    "            Question: {input}\n",
-    "            {agent_scratchpad}\"\"\"\n",
     "\n",
-    "prompt = ZeroShotAgent.create_prompt(\n",
-    "    tools=tools,\n",
-    "    prefix=prefix,\n",
-    "    suffix=suffix,\n",
-    "    input_variables=[\"input\", \"chat_history\", \"agent_scratchpad\"],\n",
-    ")\n",
+    "prompt = hub.pull(\"hwchase17/react\")\n",
+    "\n",
     "\n",
     "llm = NIBittensorLLM(\n",
     "    system_prompt=\"Your task is to determine a response based on user prompt\"\n",
     ")\n",
     "\n",
-    "llm_chain = LLMChain(llm=llm, prompt=prompt)\n",
-    "\n",
     "memory = ConversationBufferMemory(memory_key=\"chat_history\")\n",
     "\n",
-    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)\n",
-    "agent_chain = AgentExecutor.from_agent_and_tools(\n",
-    "    agent=agent, tools=tools, verbose=True, memory=memory\n",
-    ")\n",
+    "agent = create_react_agent(llm, tools, prompt)\n",
+    "agent_executor = AgentExecutor(agent=agent, tools=tools, memory=memory)\n",
     "\n",
-    "response = agent_chain.run(input=prompt)"
+    "response = agent_executor.invoke({\"input\": prompt})"
    ]
   }
  ],

docs/docs/integrations/llms/ibm_watsonx.ipynb

@@ -124,7 +124,7 @@
     "In this example, we’ll use the `project_id` and Dallas url.\n",
     "\n",
     "\n",
-    "You need to specify `model_id` that will be used for inferencing. All avaliable models you can find in [documentation](https://ibm.github.io/watsonx-ai-python-sdk/fm_model.html#ibm_watsonx_ai.foundation_models.utils.enums.ModelTypes)."
+    "You need to specify `model_id` that will be used for inferencing. All available models you can find in [documentation](https://ibm.github.io/watsonx-ai-python-sdk/fm_model.html#ibm_watsonx_ai.foundation_models.utils.enums.ModelTypes)."
    ]
   },
   {

docs/docs/integrations/llms/mlx_pipelines.ipynb

@@ -0,0 +1,142 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "959300d4",
+   "metadata": {},
+   "source": [
+    "# MLX Local Pipelines\n",
+    "\n",
+    "MLX models can be run locally through the `MLXPipeline` class.\n",
+    "\n",
+    "The [MLX Community](https://huggingface.co/mlx-community) hosts over 150 models, all open source and publicly available on Hugging Face Model Hub a online platform where people can easily collaborate and build ML together.\n",
+    "\n",
+    "These can be called from LangChain either through this local pipeline wrapper or by calling their hosted inference endpoints through the MlXPipeline class. For more information on mlx, see the [examples repo](https://github.com/ml-explore/mlx-examples/tree/main/llms) notebook."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4c1b8450-5eaf-4d34-8341-2d785448a1ff",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "To use, you should have the ``mlx-lm`` python [package installed](https://pypi.org/project/mlx-lm/), as well as [transformers](https://pypi.org/project/transformers/). You can also install `huggingface_hub`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d772b637-de00-4663-bd77-9bc96d798db2",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  mlx-lm transformers huggingface_hub"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "91ad075f-71d5-4bc8-ab91-cc0ad5ef16bb",
+   "metadata": {},
+   "source": [
+    "### Model Loading\n",
+    "\n",
+    "Models can be loaded by specifying the model parameters using the `from_model_id` method."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "165ae236-962a-4763-8052-c4836d78a5d2",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_community.llms.mlx_pipeline import MLXPipeline\n",
+    "\n",
+    "pipe = MLXPipeline.from_model_id(\n",
+    "    \"mlx-community/quantized-gemma-2b-it\",\n",
+    "    pipeline_kwargs={\"max_tokens\": 10, \"temp\": 0.1},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "00104b27-0c15-4a97-b198-4512337ee211",
+   "metadata": {},
+   "source": [
+    "They can also be loaded by passing in an existing `transformers` pipeline directly"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7f426a4f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline\n",
+    "from mlx_lm import load\n",
+    "\n",
+    "model, tokenizer = load(\"mlx-community/quantized-gemma-2b-it\")\n",
+    "pipe = MLXPipeline(model=model, tokenizer=tokenizer)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "60e7ba8d",
+   "metadata": {},
+   "source": [
+    "### Create Chain\n",
+    "\n",
+    "With the model loaded into memory, you can compose it with a prompt to\n",
+    "form a chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3acf0069",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import PromptTemplate\n",
+    "\n",
+    "template = \"\"\"Question: {question}\n",
+    "\n",
+    "Answer: Let's think step by step.\"\"\"\n",
+    "prompt = PromptTemplate.from_template(template)\n",
+    "\n",
+    "chain = prompt | pipe\n",
+    "\n",
+    "question = \"What is electroencephalography?\"\n",
+    "\n",
+    "print(chain.invoke({\"question\": question}))"
+   ]
+  }
+ ],
+ "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": "3.9.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/llms/predibase.ipynb

@@ -50,7 +50,41 @@
     "from langchain_community.llms import Predibase\n",
     "\n",
     "model = Predibase(\n",
-    "    model=\"vicuna-13b\", predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\")\n",
+    "    model=\"mistral-7b\",\n",
+    "    predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\"),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.llms import Predibase\n",
+    "\n",
+    "# With a fine-tuned adapter hosted at Predibase (adapter_version can be specified; omitting it is equivalent to the most recent version).\n",
+    "model = Predibase(\n",
+    "    model=\"mistral-7b\",\n",
+    "    adapter_id=\"e2e_nlg\",\n",
+    "    adapter_version=1,\n",
+    "    predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\"),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.llms import Predibase\n",
+    "\n",
+    "# With a fine-tuned adapter hosted at HuggingFace (adapter_version does not apply and will be ignored).\n",
+    "model = Predibase(\n",
+    "    model=\"mistral-7b\",\n",
+    "    adapter_id=\"predibase/e2e_nlg\",\n",
+    "    predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\"),\n",
     ")"
    ]
   },
@@ -66,19 +100,62 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
    "source": [
     "## Chain Call Setup"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_community.llms import Predibase\n",
+    "\n",
+    "model = Predibase(\n",
+    "    model=\"mistral-7b\", predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\")\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# With a fine-tuned adapter hosted at Predibase (adapter_version can be specified; omitting it is equivalent to the most recent version).\n",
+    "model = Predibase(\n",
+    "    model=\"mistral-7b\",\n",
+    "    adapter_id=\"e2e_nlg\",\n",
+    "    adapter_version=1,\n",
+    "    predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\"),\n",
+    ")"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
+    "# With a fine-tuned adapter hosted at HuggingFace (adapter_version does not apply and will be ignored).\n",
     "llm = Predibase(\n",
-    "    model=\"vicuna-13b\", predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\")\n",
+    "    model=\"mistral-7b\",\n",
+    "    adapter_id=\"predibase/e2e_nlg\",\n",
+    "    predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\"),\n",
     ")"
    ]
   },
@@ -169,7 +246,12 @@
     "from langchain_community.llms import Predibase\n",
     "\n",
     "model = Predibase(\n",
-    "    model=\"my-finetuned-LLM\", predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\")\n",
+    "    model=\"my-base-LLM\",\n",
+    "    adapter_id=\"my-finetuned-adapter-id\",  # Supports both, Predibase-hosted and HuggingFace-hosted model repositories.\n",
+    "    # adapter_version=1,  # optional (returns the latest, if omitted)\n",
+    "    predibase_api_key=os.environ.get(\n",
+    "        \"PREDIBASE_API_TOKEN\"\n",
+    "    ),  # Adapter argument is optional.\n",
     ")\n",
     "# replace my-finetuned-LLM with the name of your model in Predibase"
    ]

docs/docs/integrations/platforms/google.mdx

@@ -229,7 +229,7 @@ pip install langchain-google-cloud-sql-pg
 See [usage example](/docs/integrations/document_loaders/google_cloud_sql_pg).
 
 ```python
-from langchain_google_cloud_sql_pg import PostgreSQLEngine, PostgreSQLLoader
+from langchain_google_cloud_sql_pg import PostgresEngine, PostgresLoader
 ```
 
 ### Cloud Storage
@@ -486,6 +486,21 @@ See [usage example](/docs/integrations/vectorstores/google_spanner).
 from langchain_google_spanner import SpannerVectorStore
 ```
 
+### Cloud SQL for MySQL
+
+> [Google Cloud SQL for MySQL](https://cloud.google.com/sql) is a fully-managed database service that helps you set up, maintain, manage, and administer your MySQL relational databases on Google Cloud.
+Install the python package:
+
+```bash
+pip install langchain-google-cloud-sql-mysql
+```
+
+See [usage example](/docs/integrations/vectorstores/google_cloud_sql_mysql).
+
+```python
+from langchain_google_cloud_sql_mysql import MySQLEngine, MySQLVectorStore
+```
+
 ### Cloud SQL for PostgreSQL
 
 > [Google Cloud SQL for PostgreSQL](https://cloud.google.com/sql) is a fully-managed database service that helps you set up, maintain, manage, and administer your PostgreSQL relational databases on Google Cloud.
@@ -498,7 +513,7 @@ pip install langchain-google-cloud-sql-pg
 See [usage example](/docs/integrations/vectorstores/google_cloud_sql_pg).
 
 ```python
-from langchain_google_cloud_sql_pg import PostgreSQLEngine, PostgresVectorStore
+from langchain_google_cloud_sql_pg import PostgresEngine, PostgresVectorStore
 ```
 
 ### Vertex AI Vector Search
@@ -783,7 +798,7 @@ See [usage example](/docs/integrations/memory/google_sql_pg).
 
 
 ```python
-from langchain_google_cloud_sql_pg import PostgreSQLEngine, PostgreSQLChatMessageHistory
+from langchain_google_cloud_sql_pg import PostgresEngine, PostgresChatMessageHistory
 ```
 
 ### Cloud SQL for MySQL

docs/docs/integrations/platforms/microsoft.mdx

@@ -252,23 +252,23 @@ from langchain_community.vectorstores import AzureCosmosDBVectorSearch
 ```
 
 ## Retrievers
-### Azure Cognitive Search
+### Azure AI Search
 
->[Azure Cognitive Search](https://learn.microsoft.com/en-us/azure/search/search-what-is-azure-search) (formerly known as `Azure Search`) is a cloud search service that gives developers infrastructure, APIs, and tools for building a rich search experience over private, heterogeneous content in web, mobile, and enterprise applications.
+>[Azure AI Search](https://learn.microsoft.com/en-us/azure/search/search-what-is-azure-search) (formerly known as `Azure Search` or `Azure Cognitive Search` ) is a cloud search service that gives developers infrastructure, APIs, and tools for building a rich search experience over private, heterogeneous content in web, mobile, and enterprise applications.
 
 >Search is foundational to any app that surfaces text to users, where common scenarios include catalog or document search, online retail apps, or data exploration over proprietary content. When you create a search service, you'll work with the following capabilities:
 >- A search engine for full text search over a search index containing user-owned content
 >- Rich indexing, with lexical analysis and optional AI enrichment for content extraction and transformation
 >- Rich query syntax for text search, fuzzy search, autocomplete, geo-search and more
 >- Programmability through REST APIs and client libraries in Azure SDKs
->- Azure integration at the data layer, machine learning layer, and AI (Cognitive Services)
+>- Azure integration at the data layer, machine learning layer, and AI (AI Services)
 
 See [set up instructions](https://learn.microsoft.com/en-us/azure/search/search-create-service-portal).
 
-See a [usage example](/docs/integrations/retrievers/azure_cognitive_search).
+See a [usage example](/docs/integrations/retrievers/azure_ai_search).
 
 ```python
-from langchain.retrievers import AzureCognitiveSearchRetriever
+from langchain.retrievers import AzureAISearchRetriever
 ```
 
 ## Toolkits

docs/docs/integrations/providers/fireworks.md

@@ -24,10 +24,10 @@ There are two ways to authenticate using your Fireworks API key:
     os.environ["FIREWORKS_API_KEY"] = "<KEY>"
     ```
 
-2.  Setting `fireworks_api_key` field in the Fireworks LLM module.
+2.  Setting `api_key` field in the Fireworks LLM module.
 
     ```python
-    llm = Fireworks(fireworks_api_key="<KEY>")
+    llm = Fireworks(api_key="<KEY>")
     ```
 
 ## Using the Fireworks LLM module
@@ -39,7 +39,7 @@ will work the mixtral-8x7b-instruct model.
 from langchain_fireworks import Fireworks 
 
 llm = Fireworks(
-    fireworks_api_key="<KEY>",
+    api_key="<KEY>",
     model="accounts/fireworks/models/mixtral-8x7b-instruct",
     max_tokens=256)
 llm("Name 3 sports.")

docs/docs/integrations/providers/log10.mdx

@@ -30,7 +30,7 @@ messages = [
     HumanMessage(content="Ping?"),
 ]
 
-llm = ChatOpenAI(model_name="gpt-3.5-turbo", callbacks=[log10_callback])
+llm = ChatOpenAI(model="gpt-3.5-turbo", callbacks=[log10_callback])
 ```
 
 [Log10 + Langchain + Logs docs](https://github.com/log10-io/log10/blob/main/logging.md#langchain-logger)
@@ -55,7 +55,7 @@ messages = [
     HumanMessage(content="Ping?"),
 ]
 
-llm = ChatOpenAI(model_name="gpt-3.5-turbo", callbacks=[log10_callback], temperature=0.5, tags=["test"])
+llm = ChatOpenAI(model="gpt-3.5-turbo", callbacks=[log10_callback], temperature=0.5, tags=["test"])
 completion = llm.predict_messages(messages, tags=["foobar"])
 print(completion)
 

docs/docs/integrations/providers/predibase.md

@@ -17,7 +17,37 @@ os.environ["PREDIBASE_API_TOKEN"] = "{PREDIBASE_API_TOKEN}"
 
 from langchain_community.llms import Predibase
 
-model =  Predibase(model = 'vicuna-13b', predibase_api_key=os.environ.get('PREDIBASE_API_TOKEN'))
+model = Predibase(model="mistral-7b"", predibase_api_key=os.environ.get("PREDIBASE_API_TOKEN"))
+
+response = model("Can you recommend me a nice dry wine?")
+print(response)
+```
+
+Predibase also supports Predibase-hosted and HuggingFace-hosted adapters that are fine-tuned on the base model given by the `model` argument:
+
+```python
+import os
+os.environ["PREDIBASE_API_TOKEN"] = "{PREDIBASE_API_TOKEN}"
+
+from langchain_community.llms import Predibase
+
+# The fine-tuned adapter is hosted at Predibase (adapter_version can be specified; omitting it is equivalent to the most recent version).
+model =  Predibase(model="mistral-7b"", adapter_id="e2e_nlg", adapter_version=1, predibase_api_key=os.environ.get("PREDIBASE_API_TOKEN"))
+
+response = model("Can you recommend me a nice dry wine?")
+print(response)
+```
+
+Predibase also supports adapters that are fine-tuned on the base model given by the `model` argument:
+
+```python
+import os
+os.environ["PREDIBASE_API_TOKEN"] = "{PREDIBASE_API_TOKEN}"
+
+from langchain_community.llms import Predibase
+
+# The fine-tuned adapter is hosted at HuggingFace (adapter_version does not apply and will be ignored).
+model =  Predibase(model="mistral-7b"", adapter_id="predibase/e2e_nlg", predibase_api_key=os.environ.get("PREDIBASE_API_TOKEN"))
 
 response = model("Can you recommend me a nice dry wine?")
 print(response)

docs/docs/integrations/retrievers/arxiv.ipynb

@@ -203,7 +203,7 @@
     "from langchain.chains import ConversationalRetrievalChain\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "model = ChatOpenAI(model_name=\"gpt-3.5-turbo\")  # switch to 'gpt-4'\n",
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo\")  # switch to 'gpt-4'\n",
     "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
    ]
   },

docs/docs/integrations/retrievers/azure_cognitive_search.ipynb

@@ -1,147 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "1edb9e6b",
-   "metadata": {},
-   "source": [
-    "# Azure Cognitive Search\n",
-    "\n",
-    ">[Azure Cognitive Search](https://learn.microsoft.com/en-us/azure/search/search-what-is-azure-search) (formerly known as `Azure Search`) is a cloud search service that gives developers infrastructure, APIs, and tools for building a rich search experience over private, heterogeneous content in web, mobile, and enterprise applications.\n",
-    "\n",
-    ">Search is foundational to any app that surfaces text to users, where common scenarios include catalog or document search, online retail apps, or data exploration over proprietary content. When you create a search service, you'll work with the following capabilities:\n",
-    ">- A search engine for full text search over a search index containing user-owned content\n",
-    ">- Rich indexing, with lexical analysis and optional AI enrichment for content extraction and transformation\n",
-    ">- Rich query syntax for text search, fuzzy search, autocomplete, geo-search and more\n",
-    ">- Programmability through REST APIs and client libraries in Azure SDKs\n",
-    ">- Azure integration at the data layer, machine learning layer, and AI (Cognitive Services)\n",
-    "\n",
-    "This notebook shows how to use Azure Cognitive Search (ACS) within LangChain."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "074b0004",
-   "metadata": {},
-   "source": [
-    "## Set up Azure Cognitive Search\n",
-    "\n",
-    "To set up ACS, please follow the instructions [here](https://learn.microsoft.com/en-us/azure/search/search-create-service-portal).\n",
-    "\n",
-    "Please note\n",
-    "1. the name of your ACS service, \n",
-    "2. the name of your ACS index,\n",
-    "3. your API key.\n",
-    "\n",
-    "Your API key can be either Admin or Query key, but as we only read data it is recommended to use a Query key."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0474661d",
-   "metadata": {},
-   "source": [
-    "## Using the Azure Cognitive Search Retriever"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "39d6074e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "from langchain_community.retrievers import (\n",
-    "    AzureCognitiveSearchRetriever,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b7243e6d",
-   "metadata": {},
-   "source": [
-    "Set Service Name, Index Name and API key as environment variables (alternatively, you can pass them as arguments to `AzureCognitiveSearchRetriever`)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "33fd23d1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "os.environ[\"AZURE_COGNITIVE_SEARCH_SERVICE_NAME\"] = \"<YOUR_ACS_SERVICE_NAME>\"\n",
-    "os.environ[\"AZURE_COGNITIVE_SEARCH_INDEX_NAME\"] = \"<YOUR_ACS_INDEX_NAME>\"\n",
-    "os.environ[\"AZURE_COGNITIVE_SEARCH_API_KEY\"] = \"<YOUR_API_KEY>\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "057deaad",
-   "metadata": {},
-   "source": [
-    "Create the Retriever"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "c18d0c4c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "retriever = AzureCognitiveSearchRetriever(content_key=\"content\", top_k=10)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e94ea104",
-   "metadata": {},
-   "source": [
-    "Now you can use retrieve documents from Azure Cognitive Search"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "c8b5794b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "retriever.get_relevant_documents(\"what is langchain\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "72eca08e",
-   "metadata": {},
-   "source": [
-    "You can change the number of results returned with the `top_k` parameter. The default value is `None`, which returns all results. "
-   ]
-  }
- ],
- "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": "3.10.12"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/integrations/retrievers/kay.ipynb

@@ -153,7 +153,7 @@
     "from langchain.chains import ConversationalRetrievalChain\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "model = ChatOpenAI(model_name=\"gpt-3.5-turbo\")\n",
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo\")\n",
     "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
    ]
   },

docs/docs/integrations/retrievers/outline.ipynb

@@ -140,7 +140,7 @@
     "from langchain.chains import ConversationalRetrievalChain\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "model = ChatOpenAI(model_name=\"gpt-3.5-turbo\")\n",
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo\")\n",
     "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
    ]
   },

docs/docs/integrations/retrievers/sec_filings.ipynb

@@ -81,7 +81,7 @@
     "from langchain_community.retrievers import KayAiRetriever\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "model = ChatOpenAI(model_name=\"gpt-3.5-turbo\")\n",
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo\")\n",
     "retriever = KayAiRetriever.create(\n",
     "    dataset_id=\"company\", data_types=[\"10-K\", \"10-Q\"], num_contexts=6\n",
     ")\n",

docs/docs/integrations/retrievers/self_query/tencentvectordb.ipynb

@@ -0,0 +1,441 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1ad7250ddd99fba9",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "# Tencent Cloud VectorDB\n",
+    "\n",
+    "> [Tencent Cloud VectorDB](https://cloud.tencent.com/document/product/1709) is a fully managed, self-developed, enterprise-level distributed database    service designed for storing, retrieving, and analyzing multi-dimensional vector data.\n",
+    "\n",
+    "In the walkthrough, we'll demo the `SelfQueryRetriever` with a Tencent Cloud VectorDB."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "209652d4ab38ba7f",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "## create a TencentVectorDB instance\n",
+    "First we'll want to create a TencentVectorDB and seed it with some data. We've created a small demo set of documents that contain summaries of movies.\n",
+    "\n",
+    "**Note:** The self-query retriever requires you to have `lark` installed (`pip install lark`) along with integration-specific requirements."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "b68da3303b0625f2",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-29T02:39:28.887634Z",
+     "start_time": "2024-03-29T02:39:27.277978Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\r\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;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\r\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\r\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "%pip install --upgrade --quiet tcvectordb langchain-openai tiktoken lark"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a1113af6008f3f3d",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "We want to use `OpenAIEmbeddings` so we have to get the OpenAI API Key."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c243e15bcf72d539",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-29T02:40:59.788206Z",
+     "start_time": "2024-03-29T02:40:59.783798Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e5277a4dba027bb8",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "create a TencentVectorDB instance and seed it with some data:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "fd0c70c0be7d7130",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-29T02:42:28.467682Z",
+     "start_time": "2024-03-29T02:42:21.255335Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_community.vectorstores.tencentvectordb import (\n",
+    "    ConnectionParams,\n",
+    "    MetaField,\n",
+    "    TencentVectorDB,\n",
+    ")\n",
+    "from langchain_core.documents import Document\n",
+    "from tcvectordb.model.enum import FieldType\n",
+    "\n",
+    "meta_fields = [\n",
+    "    MetaField(name=\"year\", data_type=\"uint64\", index=True),\n",
+    "    MetaField(name=\"rating\", data_type=\"string\", index=False),\n",
+    "    MetaField(name=\"genre\", data_type=FieldType.String, index=True),\n",
+    "    MetaField(name=\"director\", data_type=FieldType.String, index=True),\n",
+    "]\n",
+    "\n",
+    "docs = [\n",
+    "    Document(\n",
+    "        page_content=\"The Shawshank Redemption is a 1994 American drama film written and directed by Frank Darabont.\",\n",
+    "        metadata={\n",
+    "            \"year\": 1994,\n",
+    "            \"rating\": \"9.3\",\n",
+    "            \"genre\": \"drama\",\n",
+    "            \"director\": \"Frank Darabont\",\n",
+    "        },\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"The Godfather is a 1972 American crime film directed by Francis Ford Coppola.\",\n",
+    "        metadata={\n",
+    "            \"year\": 1972,\n",
+    "            \"rating\": \"9.2\",\n",
+    "            \"genre\": \"crime\",\n",
+    "            \"director\": \"Francis Ford Coppola\",\n",
+    "        },\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"The Dark Knight is a 2008 superhero film directed by Christopher Nolan.\",\n",
+    "        metadata={\n",
+    "            \"year\": 2008,\n",
+    "            \"rating\": \"9.0\",\n",
+    "            \"genre\": \"science fiction\",\n",
+    "            \"director\": \"Christopher Nolan\",\n",
+    "        },\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"Inception is a 2010 science fiction action film written and directed by Christopher Nolan.\",\n",
+    "        metadata={\n",
+    "            \"year\": 2010,\n",
+    "            \"rating\": \"8.8\",\n",
+    "            \"genre\": \"science fiction\",\n",
+    "            \"director\": \"Christopher Nolan\",\n",
+    "        },\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"The Avengers is a 2012 American superhero film based on the Marvel Comics superhero team of the same name.\",\n",
+    "        metadata={\n",
+    "            \"year\": 2012,\n",
+    "            \"rating\": \"8.0\",\n",
+    "            \"genre\": \"science fiction\",\n",
+    "            \"director\": \"Joss Whedon\",\n",
+    "        },\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"Black Panther is a 2018 American superhero film based on the Marvel Comics character of the same name.\",\n",
+    "        metadata={\n",
+    "            \"year\": 2018,\n",
+    "            \"rating\": \"7.3\",\n",
+    "            \"genre\": \"science fiction\",\n",
+    "            \"director\": \"Ryan Coogler\",\n",
+    "        },\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "vector_db = TencentVectorDB.from_documents(\n",
+    "    docs,\n",
+    "    None,\n",
+    "    connection_params=ConnectionParams(\n",
+    "        url=\"http://10.0.X.X\",\n",
+    "        key=\"eC4bLRy2va******************************\",\n",
+    "        username=\"root\",\n",
+    "        timeout=20,\n",
+    "    ),\n",
+    "    collection_name=\"self_query_movies\",\n",
+    "    meta_fields=meta_fields,\n",
+    "    drop_old=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3810b731a981a957",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "## Creating our self-querying retriever\n",
+    "Now we can instantiate our retriever. To do this we'll need to provide some information upfront about the metadata fields that our documents support and a short description of the document contents."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "7095b68ea997468c",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-29T02:42:37.901230Z",
+     "start_time": "2024-03-29T02:42:36.836827Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.chains.query_constructor.base import AttributeInfo\n",
+    "from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "metadata_field_info = [\n",
+    "    AttributeInfo(\n",
+    "        name=\"genre\",\n",
+    "        description=\"The genre of the movie\",\n",
+    "        type=\"string\",\n",
+    "    ),\n",
+    "    AttributeInfo(\n",
+    "        name=\"year\",\n",
+    "        description=\"The year the movie was released\",\n",
+    "        type=\"integer\",\n",
+    "    ),\n",
+    "    AttributeInfo(\n",
+    "        name=\"director\",\n",
+    "        description=\"The name of the movie director\",\n",
+    "        type=\"string\",\n",
+    "    ),\n",
+    "    AttributeInfo(\n",
+    "        name=\"rating\", description=\"A 1-10 rating for the movie\", type=\"string\"\n",
+    "    ),\n",
+    "]\n",
+    "document_content_description = \"Brief summary of a movie\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "cbbf7e54054bb3aa",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-29T02:42:45.187071Z",
+     "start_time": "2024-03-29T02:42:45.138462Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "llm = ChatOpenAI(temperature=0, model=\"gpt-4\", max_tokens=4069)\n",
+    "retriever = SelfQueryRetriever.from_llm(\n",
+    "    llm, vector_db, document_content_description, metadata_field_info, verbose=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "65ff2054be9d5236",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "## Test it out\n",
+    "And now we can try actually using our retriever!\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "267e2a68f26505b1",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-29T02:42:51.526470Z",
+     "start_time": "2024-03-29T02:42:48.328191Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "[Document(page_content='The Dark Knight is a 2008 superhero film directed by Christopher Nolan.', metadata={'year': 2008, 'rating': '9.0', 'genre': 'science fiction', 'director': 'Christopher Nolan'}),\n Document(page_content='The Avengers is a 2012 American superhero film based on the Marvel Comics superhero team of the same name.', metadata={'year': 2012, 'rating': '8.0', 'genre': 'science fiction', 'director': 'Joss Whedon'}),\n Document(page_content='Black Panther is a 2018 American superhero film based on the Marvel Comics character of the same name.', metadata={'year': 2018, 'rating': '7.3', 'genre': 'science fiction', 'director': 'Ryan Coogler'}),\n Document(page_content='The Godfather is a 1972 American crime film directed by Francis Ford Coppola.', metadata={'year': 1972, 'rating': '9.2', 'genre': 'crime', 'director': 'Francis Ford Coppola'})]"
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# This example only specifies a relevant query\n",
+    "retriever.get_relevant_documents(\"movies about a superhero\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "3afd98ca20782dda",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-29T02:42:55.179002Z",
+     "start_time": "2024-03-29T02:42:53.057022Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "[Document(page_content='The Avengers is a 2012 American superhero film based on the Marvel Comics superhero team of the same name.', metadata={'year': 2012, 'rating': '8.0', 'genre': 'science fiction', 'director': 'Joss Whedon'}),\n Document(page_content='Black Panther is a 2018 American superhero film based on the Marvel Comics character of the same name.', metadata={'year': 2018, 'rating': '7.3', 'genre': 'science fiction', 'director': 'Ryan Coogler'})]"
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# This example only specifies a filter\n",
+    "retriever.get_relevant_documents(\"movies that were released after 2010\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "9974f641e11abfe8",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-29T02:42:58.472620Z",
+     "start_time": "2024-03-29T02:42:56.131594Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "[Document(page_content='The Avengers is a 2012 American superhero film based on the Marvel Comics superhero team of the same name.', metadata={'year': 2012, 'rating': '8.0', 'genre': 'science fiction', 'director': 'Joss Whedon'}),\n Document(page_content='Black Panther is a 2018 American superhero film based on the Marvel Comics character of the same name.', metadata={'year': 2018, 'rating': '7.3', 'genre': 'science fiction', 'director': 'Ryan Coogler'})]"
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# This example specifies both a relevant query and a filter\n",
+    "retriever.get_relevant_documents(\n",
+    "    \"movies about a superhero which were released after 2010\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "be593d3a6c508517",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "## Filter k\n",
+    "\n",
+    "We can also use the self query retriever to specify `k`: the number of documents to fetch.\n",
+    "\n",
+    "We can do this by passing `enable_limit=True` to the constructor."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "e255b69c937fa424",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-29T02:43:02.779337Z",
+     "start_time": "2024-03-29T02:43:02.759900Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "retriever = SelfQueryRetriever.from_llm(\n",
+    "    llm,\n",
+    "    vector_db,\n",
+    "    document_content_description,\n",
+    "    metadata_field_info,\n",
+    "    verbose=True,\n",
+    "    enable_limit=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "45674137c7f8a9d",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-29T02:43:07.357830Z",
+     "start_time": "2024-03-29T02:43:04.854323Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "[Document(page_content='The Dark Knight is a 2008 superhero film directed by Christopher Nolan.', metadata={'year': 2008, 'rating': '9.0', 'genre': 'science fiction', 'director': 'Christopher Nolan'}),\n Document(page_content='The Avengers is a 2012 American superhero film based on the Marvel Comics superhero team of the same name.', metadata={'year': 2012, 'rating': '8.0', 'genre': 'science fiction', 'director': 'Joss Whedon'})]"
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "retriever.get_relevant_documents(\"what are two movies about a superhero\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/retrievers/wikipedia.ipynb

@@ -202,7 +202,7 @@
     "from langchain.chains import ConversationalRetrievalChain\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "model = ChatOpenAI(model_name=\"gpt-3.5-turbo\")  # switch to 'gpt-4'\n",
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo\")  # switch to 'gpt-4'\n",
     "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
    ]
   },

docs/docs/integrations/text_embedding/mistralai.ipynb

@@ -45,7 +45,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "embedding = MistralAIEmbeddings(mistral_api_key=\"your-api-key\")"
+    "embedding = MistralAIEmbeddings(api_key=\"your-api-key\")"
    ]
   },
   {

docs/docs/integrations/toolkits/openapi.ipynb

@@ -10,6 +10,18 @@
     "We can construct agents to consume arbitrary APIs, here APIs conformant to the `OpenAPI`/`Swagger` specification."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "798a442b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# NOTE: In this example. We must set `allow_dangerous_request=True` to enable the OpenAPI Agent to automatically use the Request Tool.\n",
+    "# This can be dangerous for calling unwanted requests. Please make sure your custom OpenAPI spec (yaml) is safe.\n",
+    "ALLOW_DANGEROUS_REQUEST = True"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "a389367b",
@@ -46,6 +58,14 @@
     "import yaml"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "816011d8",
+   "metadata": {},
+   "source": [
+    "You will be able to get OpenAPI specs from here: [APIs-guru/openapi-directory](https://github.com/APIs-guru/openapi-directory)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 2,
@@ -261,9 +281,9 @@
    ],
    "source": [
     "from langchain_community.agent_toolkits.openapi import planner\n",
-    "from langchain_openai import OpenAI\n",
+    "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "llm = OpenAI(model_name=\"gpt-4\", temperature=0.0)"
+    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0.0)"
    ]
   },
   {
@@ -335,11 +355,17 @@
     }
    ],
    "source": [
-    "spotify_agent = planner.create_openapi_agent(spotify_api_spec, requests_wrapper, llm)\n",
+    "# NOTE: set allow_dangerous_requests manually for security concern https://python.langchain.com/docs/security\n",
+    "spotify_agent = planner.create_openapi_agent(\n",
+    "    spotify_api_spec,\n",
+    "    requests_wrapper,\n",
+    "    llm,\n",
+    "    allow_dangerous_requests=ALLOW_DANGEROUS_REQUEST,\n",
+    ")\n",
     "user_query = (\n",
     "    \"make me a playlist with the first song from kind of blue. call it machine blues.\"\n",
     ")\n",
-    "spotify_agent.run(user_query)"
+    "spotify_agent.invoke(user_query)"
    ]
   },
   {
@@ -420,7 +446,7 @@
    ],
    "source": [
     "user_query = \"give me a song I'd like, make it blues-ey\"\n",
-    "spotify_agent.run(user_query)"
+    "spotify_agent.invoke(user_query)"
    ]
   },
   {
@@ -549,12 +575,12 @@
    ],
    "source": [
     "# Meta!\n",
-    "llm = OpenAI(model_name=\"gpt-4\", temperature=0.25)\n",
+    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0.25)\n",
     "openai_agent = planner.create_openapi_agent(\n",
     "    openai_api_spec, openai_requests_wrapper, llm\n",
     ")\n",
     "user_query = \"generate a short piece of advice\"\n",
-    "openai_agent.run(user_query)"
+    "openai_agent.invoke(user_query)"
    ]
   },
   {
@@ -606,7 +632,10 @@
     "    OpenAI(temperature=0), json_spec, openai_requests_wrapper, verbose=True\n",
     ")\n",
     "openapi_agent_executor = create_openapi_agent(\n",
-    "    llm=OpenAI(temperature=0), toolkit=openapi_toolkit, verbose=True\n",
+    "    llm=OpenAI(temperature=0),\n",
+    "    toolkit=openapi_toolkit,\n",
+    "    allow_dangerous_requests=ALLOW_DANGEROUS_REQUEST,\n",
+    "    verbose=True,\n",
     ")"
    ]
   },

docs/docs/integrations/vectorstores/elasticsearch.ipynb

@@ -736,6 +736,50 @@
     "```"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "05cdb43d-5e46-46f6-a2dc-91df4aa56ec7",
+   "metadata": {},
+   "source": [
+    "## BM25RetrievalStrategy\n",
+    "This strategy allows the user to perform searches using pure BM25 without vector search.\n",
+    "\n",
+    "To use this, specify `BM25RetrievalStrategy` in `ElasticsearchStore` constructor.\n",
+    "\n",
+    "Note that in the example below, the embedding option is not specified, indicating that the search is conducted without using embeddings."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4464a657-08c5-4a1a-b0e8-dba65f5b7ec0",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[Document(page_content='foo'), Document(page_content='foo bar'), Document(page_content='foo bar baz')]\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_elasticsearch import ElasticsearchStore\n",
+    "\n",
+    "db = ElasticsearchStore(\n",
+    "    es_url=\"http://localhost:9200\",\n",
+    "    index_name=\"test_index\",\n",
+    "    strategy=ElasticsearchStore.BM25RetrievalStrategy(),\n",
+    ")\n",
+    "\n",
+    "db.add_texts(\n",
+    "    [\"foo\", \"foo bar\", \"foo bar baz\", \"bar\", \"bar baz\", \"baz\"],\n",
+    ")\n",
+    "\n",
+    "results = db.similarity_search(query=\"foo\", k=10)\n",
+    "print(results)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "0960fa0a",
@@ -993,7 +1037,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.7"
+   "version": "3.11.8"
   }
  },
  "nbformat": 4,

docs/docs/integrations/vectorstores/google_cloud_sql_mysql.ipynb

@@ -0,0 +1,585 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Google Cloud SQL for MySQL\n",
+        "\n",
+        "> [Cloud SQL](https://cloud.google.com/sql) is a fully managed relational database service that offers high performance, seamless integration, and impressive scalability. It offers PostgreSQL, MySQL, and SQL Server database engines. Extend your database application to build AI-powered experiences leveraging Cloud SQL's LangChain integrations.\n",
+        "\n",
+        "This notebook goes over how to use `Cloud SQL for MySQL` to store vector embeddings with the `MySQLVectorStore` class.\n",
+        "\n",
+        "Learn more about the package on [GitHub](https://github.com/googleapis/langchain-google-cloud-sql-mysql-python/).\n",
+        "\n",
+        "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/googleapis/langchain-google-cloud-sql-mysql-python/blob/main/docs/vector_store.ipynb)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "To run this notebook, you will need to do the following:\n",
+        "\n",
+        " * [Create a Google Cloud Project](https://developers.google.com/workspace/guides/create-project)\n",
+        " * [Enable the Cloud SQL Admin API.](https://console.cloud.google.com/flows/enableapi?apiid=sqladmin.googleapis.com)\n",
+        " * [Create a Cloud SQL instance.](https://cloud.google.com/sql/docs/mysql/connect-instance-auth-proxy#create-instance) (version must be >= **8.0.36** with **cloudsql_vector** database flag configured to \"On\")\n",
+        " * [Create a Cloud SQL database.](https://cloud.google.com/sql/docs/mysql/create-manage-databases)\n",
+        " * [Add a User to the database.](https://cloud.google.com/sql/docs/mysql/create-manage-users)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### 🦜🔗 Library Installation\n",
+        "Install the integration library, `langchain-google-cloud-sql-mysql`, and the library for the embedding service, `langchain-google-vertexai`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "0ZITIDE160OD"
+      },
+      "outputs": [],
+      "source": [
+        "%pip install --upgrade --quiet langchain-google-cloud-sql-mysql langchain-google-vertexai"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "v40bB_GMcr9f"
+      },
+      "source": [
+        "**Colab only:** Uncomment the following cell to restart the kernel or use the button to restart the kernel. For Vertex AI Workbench you can restart the terminal using the button on top."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "v6jBDnYnNM08"
+      },
+      "outputs": [],
+      "source": [
+        "# # Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
+        "\n",
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "yygMe6rPWxHS"
+      },
+      "source": [
+        "### 🔐 Authentication\n",
+        "Authenticate to Google Cloud as the IAM user logged into this notebook in order to access your Google Cloud Project.\n",
+        "\n",
+        "* If you are using Colab to run this notebook, use the cell below and continue.\n",
+        "* If you are using Vertex AI Workbench, check out the setup instructions [here](https://github.com/GoogleCloudPlatform/generative-ai/tree/main/setup-env)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "PTXN1_DSXj2b"
+      },
+      "outputs": [],
+      "source": [
+        "from google.colab import auth\n",
+        "\n",
+        "auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "NEvB9BoLEulY"
+      },
+      "source": [
+        "### ☁ Set Your Google Cloud Project\n",
+        "Set your Google Cloud project so that you can leverage Google Cloud resources within this notebook.\n",
+        "\n",
+        "If you don't know your project ID, try the following:\n",
+        "\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "cellView": "form",
+        "id": "gfkS3yVRE4_W"
+      },
+      "outputs": [],
+      "source": [
+        "# @markdown Please fill in the value below with your Google Cloud project ID and then run the cell.\n",
+        "\n",
+        "PROJECT_ID = \"my-project-id\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "!gcloud config set project {PROJECT_ID}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f8f2830ee9ca1e01"
+      },
+      "source": [
+        "## Basic Usage"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "OMvzMWRrR6n7"
+      },
+      "source": [
+        "### Set Cloud SQL database values\n",
+        "Find your database values, in the [Cloud SQL Instances page](https://console.cloud.google.com/sql?_ga=2.223735448.2062268965.1707700487-2088871159.1707257687).\n",
+        "\n",
+        "**Note:** MySQL vector support is only available on MySQL instances with version **>= 8.0.36**.\n",
+        "\n",
+        "For existing instances, you may need to perform a [self-service maintenance update](https://cloud.google.com/sql/docs/mysql/self-service-maintenance) to update your maintenance version to **MYSQL_8_0_36.R20240401.03_00** or greater. Once updated, [configure your database flags](https://cloud.google.com/sql/docs/mysql/flags) to have the new **cloudsql_vector** flag to \"On\"."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# @title Set Your Values Here { display-mode: \"form\" }\n",
+        "REGION = \"us-central1\"  # @param {type: \"string\"}\n",
+        "INSTANCE = \"my-mysql-instance\"  # @param {type: \"string\"}\n",
+        "DATABASE = \"my-database\"  # @param {type: \"string\"}\n",
+        "TABLE_NAME = \"vector_store\"  # @param {type: \"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "QuQigs4UoFQ2"
+      },
+      "source": [
+        "### MySQLEngine Connection Pool\n",
+        "\n",
+        "One of the requirements and arguments to establish Cloud SQL as a vector store is a `MySQLEngine` object. The `MySQLEngine` configures a connection pool to your Cloud SQL database, enabling successful connections from your application and following industry best practices.\n",
+        "\n",
+        "To create a `MySQLEngine` using `MySQLEngine.from_instance()` you need to provide only 4 things:\n",
+        "\n",
+        "1. `project_id` : Project ID of the Google Cloud Project where the Cloud SQL instance is located.\n",
+        "1. `region` : Region where the Cloud SQL instance is located.\n",
+        "1. `instance` : The name of the Cloud SQL instance.\n",
+        "1. `database` : The name of the database to connect to on the Cloud SQL instance.\n",
+        "\n",
+        "By default, [IAM database authentication](https://cloud.google.com/sql/docs/mysql/iam-authentication#iam-db-auth) will be used as the method of database authentication. This library uses the IAM principal belonging to the [Application Default Credentials (ADC)](https://cloud.google.com/docs/authentication/application-default-credentials) sourced from the envionment.\n",
+        "\n",
+        "For more informatin on IAM database authentication please see:\n",
+        "\n",
+        "* [Configure an instance for IAM database authentication](https://cloud.google.com/sql/docs/mysql/create-edit-iam-instances)\n",
+        "* [Manage users with IAM database authentication](https://cloud.google.com/sql/docs/mysql/add-manage-iam-users)\n",
+        "\n",
+        "Optionally, [built-in database authentication](https://cloud.google.com/sql/docs/mysql/built-in-authentication) using a username and password to access the Cloud SQL database can also be used. Just provide the optional `user` and `password` arguments to `MySQLEngine.from_instance()`:\n",
+        "\n",
+        "* `user` : Database user to use for built-in database authentication and login\n",
+        "* `password` : Database password to use for built-in database authentication and login.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "guVURf1QLL53"
+      },
+      "outputs": [],
+      "source": [
+        "from langchain_google_cloud_sql_mysql import MySQLEngine\n",
+        "\n",
+        "engine = MySQLEngine.from_instance(\n",
+        "    project_id=PROJECT_ID, region=REGION, instance=INSTANCE, database=DATABASE\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Initialize a table\n",
+        "The `MySQLVectorStore` class requires a database table. The `MySQLEngine` class has a helper method `init_vectorstore_table()` that can be used to create a table with the proper schema for you."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "avlyHEMn6gzU"
+      },
+      "outputs": [],
+      "source": [
+        "engine.init_vectorstore_table(\n",
+        "    table_name=TABLE_NAME,\n",
+        "    vector_size=768,  # Vector size for VertexAI model(textembedding-gecko@latest)\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create an embedding class instance\n",
+        "\n",
+        "You can use any [LangChain embeddings model](/docs/integrations/text_embedding/).\n",
+        "You may need to enable the Vertex AI API to use `VertexAIEmbeddings`.\n",
+        "\n",
+        "We recommend pinning the embedding model's version for production, learn more about the [Text embeddings models](https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/text-embeddings)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "5utKIdq7KYi5"
+      },
+      "outputs": [],
+      "source": [
+        "# enable Vertex AI API\n",
+        "!gcloud services enable aiplatform.googleapis.com"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Vb2RJocV9_LQ"
+      },
+      "outputs": [],
+      "source": [
+        "from langchain_google_vertexai import VertexAIEmbeddings\n",
+        "\n",
+        "embedding = VertexAIEmbeddings(\n",
+        "    model_name=\"textembedding-gecko@latest\", project=PROJECT_ID\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e1tl0aNx7SWy"
+      },
+      "source": [
+        "### Initialize a default MySQLVectorStore\n",
+        "\n",
+        "To initialize a `MySQLVectorStore` class you need to provide only 3 things:\n",
+        "\n",
+        "1. `engine` - An instance of a `MySQLEngine` engine.\n",
+        "1. `embedding_service` - An instance of a LangChain embedding model.\n",
+        "1. `table_name` : The name of the table within the Cloud SQL database to use as the vector store."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "z-AZyzAQ7bsf"
+      },
+      "outputs": [],
+      "source": [
+        "from langchain_google_cloud_sql_mysql import MySQLVectorStore\n",
+        "\n",
+        "store = MySQLVectorStore(\n",
+        "    engine=engine,\n",
+        "    embedding_service=embedding,\n",
+        "    table_name=TABLE_NAME,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Add texts"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "nrDvGWIOLL54"
+      },
+      "outputs": [],
+      "source": [
+        "import uuid\n",
+        "\n",
+        "all_texts = [\"Apples and oranges\", \"Cars and airplanes\", \"Pineapple\", \"Train\", \"Banana\"]\n",
+        "metadatas = [{\"len\": len(t)} for t in all_texts]\n",
+        "ids = [str(uuid.uuid4()) for _ in all_texts]\n",
+        "\n",
+        "store.add_texts(all_texts, metadatas=metadatas, ids=ids)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Delete texts\n",
+        "\n",
+        "Delete vectors from the vector store by ID."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "store.delete([ids[1]])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Search for documents"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 17,
+      "metadata": {
+        "id": "fpqeZgUeLL54",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "f674a3af-452c-4d58-bb62-cbf514a9e1e3"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Pineapple\n"
+          ]
+        }
+      ],
+      "source": [
+        "query = \"I'd like a fruit.\"\n",
+        "docs = store.similarity_search(query)\n",
+        "print(docs[0].page_content)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Search for documents by vector\n",
+        "\n",
+        "It is also possible to do a search for documents similar to a given embedding vector using `similarity_search_by_vector` which accepts an embedding vector as a parameter instead of a string."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "N-NC5jgGLL55",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "69a1f9de-a830-450d-8a5e-118b36815a46"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "[Document(page_content='Pineapple', metadata={'len': 9}), Document(page_content='Banana', metadata={'len': 6})]\n"
+          ]
+        }
+      ],
+      "source": [
+        "query_vector = embedding.embed_query(query)\n",
+        "docs = store.similarity_search_by_vector(query_vector, k=2)\n",
+        "print(docs)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Add an index\n",
+        "Speed up vector search queries by applying a vector index. Learn more about [MySQL vector indexes](https://github.com/googleapis/langchain-google-cloud-sql-mysql-python/blob/main/src/langchain_google_cloud_sql_mysql/indexes.py).\n",
+        "\n",
+        "**Note:** For IAM database authentication (default usage), the IAM database user will need to be granted the following permissions by a privileged database user for full control of vector indexes.\n",
+        "\n",
+        "```\n",
+        "GRANT EXECUTE ON PROCEDURE mysql.create_vector_index TO '<IAM_DB_USER>'@'%';\n",
+        "GRANT EXECUTE ON PROCEDURE mysql.alter_vector_index TO '<IAM_DB_USER>'@'%';\n",
+        "GRANT EXECUTE ON PROCEDURE mysql.drop_vector_index TO '<IAM_DB_USER>'@'%';\n",
+        "GRANT SELECT ON mysql.vector_indexes TO '<IAM_DB_USER>'@'%';\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_google_cloud_sql_mysql import VectorIndex\n",
+        "\n",
+        "store.apply_vector_index(VectorIndex())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Remove an index"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "store.drop_vector_index()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Advanced Usage"
+      ],
+      "metadata": {}
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create a MySQLVectorStore with custom metadata\n",
+        "\n",
+        "A vector store can take advantage of relational data to filter similarity searches.\n",
+        "\n",
+        "Create a table and `MySQLVectorStore` instance with custom metadata columns."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "eANG7_8qLL55"
+      },
+      "outputs": [],
+      "source": [
+        "from langchain_google_cloud_sql_mysql import Column\n",
+        "\n",
+        "# set table name\n",
+        "CUSTOM_TABLE_NAME = \"vector_store_custom\"\n",
+        "\n",
+        "engine.init_vectorstore_table(\n",
+        "    table_name=CUSTOM_TABLE_NAME,\n",
+        "    vector_size=768,  # VertexAI model: textembedding-gecko@latest\n",
+        "    metadata_columns=[Column(\"len\", \"INTEGER\")],\n",
+        ")\n",
+        "\n",
+        "\n",
+        "# initialize MySQLVectorStore with custom metadata columns\n",
+        "custom_store = MySQLVectorStore(\n",
+        "    engine=engine,\n",
+        "    embedding_service=embedding,\n",
+        "    table_name=CUSTOM_TABLE_NAME,\n",
+        "    metadata_columns=[\"len\"],\n",
+        "    # connect to an existing VectorStore by customizing the table schema:\n",
+        "    # id_column=\"uuid\",\n",
+        "    # content_column=\"documents\",\n",
+        "    # embedding_column=\"vectors\",\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bj2d-c2sLL5-"
+      },
+      "source": [
+        "### Search for documents with metadata filter\n",
+        "\n",
+        "It can be helpful to narrow down the documents before working with them.\n",
+        "\n",
+        "For example, documents can be filtered on metadata using the `filter` argument."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Sqfgk6EOLL5-",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "a10c74e2-fe48-4cf9-ba2f-85aecb2490d0"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "[Document(page_content='Pineapple', metadata={'len': 9}), Document(page_content='Banana', metadata={'len': 6}), Document(page_content='Apples and oranges', metadata={'len': 18}), Document(page_content='Cars and airplanes', metadata={'len': 18})]\n"
+          ]
+        }
+      ],
+      "source": [
+        "import uuid\n",
+        "\n",
+        "# add texts to the vector store\n",
+        "all_texts = [\"Apples and oranges\", \"Cars and airplanes\", \"Pineapple\", \"Train\", \"Banana\"]\n",
+        "metadatas = [{\"len\": len(t)} for t in all_texts]\n",
+        "ids = [str(uuid.uuid4()) for _ in all_texts]\n",
+        "custom_store.add_texts(all_texts, metadatas=metadatas, ids=ids)\n",
+        "\n",
+        "# use filter on search\n",
+        "query_vector = embedding.embed_query(\"I'd like a fruit.\")\n",
+        "docs = custom_store.similarity_search_by_vector(query_vector, filter=\"len >= 6\")\n",
+        "\n",
+        "print(docs)"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "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": "3.11.5"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

docs/docs/integrations/vectorstores/jaguar.ipynb

@@ -144,7 +144,7 @@
     "prompt = ChatPromptTemplate.from_template(template)\n",
     "\n",
     "\"\"\" Obtain a Large Language Model \"\"\"\n",
-    "LLM = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0)\n",
+    "LLM = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)\n",
     "\n",
     "\"\"\" Create a chain for the RAG flow \"\"\"\n",
     "rag_chain = (\n",

docs/docs/integrations/vectorstores/momento_vector_index.ipynb

@@ -394,7 +394,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)\n",
     "qa_chain = RetrievalQA.from_chain_type(llm, retriever=vector_db.as_retriever())"
    ]
   },

docs/docs/integrations/vectorstores/sap_hanavector.ipynb

@@ -437,7 +437,7 @@
    "source": [
     "from langchain.chains import ConversationalRetrievalChain\n",
     "\n",
-    "llm = ChatOpenAI(model_name=\"gpt-3.5-turbo\")\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo\")\n",
     "memory = ConversationBufferMemory(\n",
     "    memory_key=\"chat_history\", output_key=\"answer\", return_messages=True\n",
     ")\n",

docs/docs/integrations/vectorstores/tencentvectordb.ipynb

@@ -3,10 +3,7 @@
   {
    "cell_type": "markdown",
    "metadata": {
-    "collapsed": true,
-    "jupyter": {
-     "outputs_hidden": true
-    }
+    "collapsed": true
    },
    "source": [
     "# Tencent Cloud VectorDB\n",
@@ -15,7 +12,9 @@
     "\n",
     "This notebook shows how to use functionality related to the Tencent vector database.\n",
     "\n",
-    "To run, you should have a [Database instance.](https://cloud.tencent.com/document/product/1709/95101)."
+    "To run, you should have a [Database instance.](https://cloud.tencent.com/document/product/1709/95101).\n",
+    "\n",
+    "## Basic Usage\n"
    ]
   },
   {
@@ -29,8 +28,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   "execution_count": 4,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-27T10:15:08.594144Z",
+     "start_time": "2024-03-27T10:15:08.588985Z"
+    }
+   },
    "outputs": [],
    "source": [
     "from langchain_community.document_loaders import TextLoader\n",
@@ -40,23 +44,93 @@
     "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "load the documents, split them into chunks."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   "execution_count": 5,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-27T10:15:11.824060Z",
+     "start_time": "2024-03-27T10:15:11.819351Z"
+    }
+   },
    "outputs": [],
    "source": [
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "docs = text_splitter.split_documents(documents)\n",
-    "embeddings = FakeEmbeddings(size=128)"
+    "docs = text_splitter.split_documents(documents)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "we support two ways to embed the documents:\n",
+    "- Use any Embeddings models compatible with Langchain Embeddings.\n",
+    "- Specify the Embedding model name of the Tencent VectorStore DB, choices are:\n",
+    "    - `bge-base-zh`, dimension: 768\n",
+    "    - `m3e-base`, dimension: 768\n",
+    "    - `text2vec-large-chinese`, dimension: 1024\n",
+    "    - `e5-large-v2`, dimension: 1024\n",
+    "    - `multilingual-e5-base`, dimension: 768 \n",
+    "\n",
+    "flowing code shows both ways to embed the documents, you can choose one of them by commenting the other:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   "execution_count": 6,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-27T10:15:14.949218Z",
+     "start_time": "2024-03-27T10:15:14.946314Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "##  you can use a Langchain Embeddings model, like OpenAIEmbeddings:\n",
+    "\n",
+    "# from langchain_community.embeddings.openai import OpenAIEmbeddings\n",
+    "#\n",
+    "# embeddings = OpenAIEmbeddings()\n",
+    "# t_vdb_embedding = None\n",
+    "\n",
+    "## Or you can use a Tencent Embedding model, like `bge-base-zh`:\n",
+    "\n",
+    "t_vdb_embedding = \"bge-base-zh\"  # bge-base-zh is the default model\n",
+    "embeddings = None"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "now we can create a TencentVectorDB instance, you must provide at least one of the `embeddings` or `t_vdb_embedding` parameters. if both are provided, the `embeddings` parameter will be used:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-27T10:15:22.954428Z",
+     "start_time": "2024-03-27T10:15:19.069173Z"
+    }
+   },
    "outputs": [],
    "source": [
     "conn_params = ConnectionParams(\n",
@@ -67,18 +141,29 @@
     ")\n",
     "\n",
     "vector_db = TencentVectorDB.from_documents(\n",
-    "    docs,\n",
-    "    embeddings,\n",
-    "    connection_params=conn_params,\n",
-    "    # drop_old=True,\n",
+    "    docs, embeddings, connection_params=conn_params, t_vdb_embedding=t_vdb_embedding\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "execution_count": 8,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-27T10:15:27.030880Z",
+     "start_time": "2024-03-27T10:15:26.996104Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "'Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.'"
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "query = \"What did the president say about Ketanji Brown Jackson\"\n",
     "docs = vector_db.similarity_search(query)\n",
@@ -87,9 +172,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "execution_count": 9,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-27T10:15:47.229114Z",
+     "start_time": "2024-03-27T10:15:47.084162Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "'Ankush went to Princeton'"
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "vector_db = TencentVectorDB(embeddings, conn_params)\n",
     "\n",
@@ -98,6 +197,119 @@
     "docs = vector_db.max_marginal_relevance_search(query)\n",
     "docs[0].page_content"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "## Metadata and filtering\n",
+    "\n",
+    "Tencent VectorDB supports metadata and [filtering](https://cloud.tencent.com/document/product/1709/95099#c6f6d3a3-02c5-4891-b0a1-30fe4daf18d8). You can add metadata to the documents and filter the search results based on the metadata.\n",
+    "\n",
+    "now we will create a new TencentVectorDB collection with metadata and demonstrate how to filter the search results based on the metadata:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-28T04:13:18.103028Z",
+     "start_time": "2024-03-28T04:13:14.670032Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "[Document(page_content='The Dark Knight is a 2008 superhero film directed by Christopher Nolan.', metadata={'year': 2008, 'rating': '9.0', 'genre': 'superhero', 'director': 'Christopher Nolan'}),\n Document(page_content='The Dark Knight is a 2008 superhero film directed by Christopher Nolan.', metadata={'year': 2008, 'rating': '9.0', 'genre': 'superhero', 'director': 'Christopher Nolan'}),\n Document(page_content='The Dark Knight is a 2008 superhero film directed by Christopher Nolan.', metadata={'year': 2008, 'rating': '9.0', 'genre': 'superhero', 'director': 'Christopher Nolan'}),\n Document(page_content='Inception is a 2010 science fiction action film written and directed by Christopher Nolan.', metadata={'year': 2010, 'rating': '8.8', 'genre': 'science fiction', 'director': 'Christopher Nolan'})]"
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_community.vectorstores.tencentvectordb import (\n",
+    "    META_FIELD_TYPE_STRING,\n",
+    "    META_FIELD_TYPE_UINT64,\n",
+    "    ConnectionParams,\n",
+    "    MetaField,\n",
+    "    TencentVectorDB,\n",
+    ")\n",
+    "from langchain_core.documents import Document\n",
+    "\n",
+    "meta_fields = [\n",
+    "    MetaField(name=\"year\", data_type=META_FIELD_TYPE_UINT64, index=True),\n",
+    "    MetaField(name=\"rating\", data_type=META_FIELD_TYPE_STRING, index=False),\n",
+    "    MetaField(name=\"genre\", data_type=META_FIELD_TYPE_STRING, index=True),\n",
+    "    MetaField(name=\"director\", data_type=META_FIELD_TYPE_STRING, index=True),\n",
+    "]\n",
+    "\n",
+    "docs = [\n",
+    "    Document(\n",
+    "        page_content=\"The Shawshank Redemption is a 1994 American drama film written and directed by Frank Darabont.\",\n",
+    "        metadata={\n",
+    "            \"year\": 1994,\n",
+    "            \"rating\": \"9.3\",\n",
+    "            \"genre\": \"drama\",\n",
+    "            \"director\": \"Frank Darabont\",\n",
+    "        },\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"The Godfather is a 1972 American crime film directed by Francis Ford Coppola.\",\n",
+    "        metadata={\n",
+    "            \"year\": 1972,\n",
+    "            \"rating\": \"9.2\",\n",
+    "            \"genre\": \"crime\",\n",
+    "            \"director\": \"Francis Ford Coppola\",\n",
+    "        },\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"The Dark Knight is a 2008 superhero film directed by Christopher Nolan.\",\n",
+    "        metadata={\n",
+    "            \"year\": 2008,\n",
+    "            \"rating\": \"9.0\",\n",
+    "            \"genre\": \"superhero\",\n",
+    "            \"director\": \"Christopher Nolan\",\n",
+    "        },\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"Inception is a 2010 science fiction action film written and directed by Christopher Nolan.\",\n",
+    "        metadata={\n",
+    "            \"year\": 2010,\n",
+    "            \"rating\": \"8.8\",\n",
+    "            \"genre\": \"science fiction\",\n",
+    "            \"director\": \"Christopher Nolan\",\n",
+    "        },\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "vector_db = TencentVectorDB.from_documents(\n",
+    "    docs,\n",
+    "    None,\n",
+    "    connection_params=ConnectionParams(\n",
+    "        url=\"http://10.0.X.X\",\n",
+    "        key=\"eC4bLRy2va******************************\",\n",
+    "        username=\"root\",\n",
+    "        timeout=20,\n",
+    "    ),\n",
+    "    collection_name=\"movies\",\n",
+    "    meta_fields=meta_fields,\n",
+    ")\n",
+    "\n",
+    "query = \"film about dream by Christopher Nolan\"\n",
+    "\n",
+    "# you can use the tencentvectordb filtering syntax with the `expr` parameter:\n",
+    "result = vector_db.similarity_search(query, expr='director=\"Christopher Nolan\"')\n",
+    "\n",
+    "# you can either use the langchain filtering syntax with the `filter` parameter:\n",
+    "# result = vector_db.similarity_search(query, filter='eq(\"director\", \"Christopher Nolan\")')\n",
+    "\n",
+    "result"
+   ]
   }
  ],
  "metadata": {

docs/docs/integrations/vectorstores/weaviate.ipynb

@@ -589,7 +589,7 @@
    "source": [
     "from langchain_community.chat_models import ChatOpenAI\n",
     "\n",
-    "llm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)\n",
     "llm.predict(\"What did the president say about Justice Breyer\")"
    ]
   },
@@ -824,7 +824,7 @@
    "source": [
     "from langchain_community.chat_models import ChatOpenAI\n",
     "\n",
-    "llm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0)"
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)"
    ]
   },
   {

docs/docs/modules/agents/agent_types/index.mdx

@@ -33,8 +33,9 @@ Our commentary on when you should consider using this agent type.
 
 | Agent Type | Intended Model Type | Supports Chat History | Supports Multi-Input Tools | Supports Parallel Function Calling | Required Model Params | When to Use | API |
 |--------------------------------------------|---------------------|-----------------------|----------------------------|-------------------------------------|----------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------|
-| [OpenAI Tools](./openai_tools)             | Chat                | ✅                    | ✅                         | ✅                                   | `tools`              | If you are using a recent OpenAI model (`1106` onwards) | [Ref](https://api.python.langchain.com/en/latest/agents/langchain.agents.openai_tools.base.create_openai_tools_agent.html) |
-| [OpenAI Functions](./openai_functions_agent)| Chat                | ✅                    | ✅                         |                                     | `functions`          | If you are using an OpenAI model, or an open-source model that has been finetuned for function calling and exposes the same `functions` parameters as OpenAI | [Ref](https://api.python.langchain.com/en/latest/agents/langchain.agents.openai_functions_agent.base.create_openai_functions_agent.html) |
+| [Tool Calling](/docs/modules/agents/agent_types/tool_calling)             | Chat                | ✅                    | ✅                         | ✅                                   | `tools`              | If you are using a tool-calling model | [Ref](https://api.python.langchain.com/en/latest/agents/langchain.agents.tool_calling_agent.base.create_tool_calling_agent.html) |
+| [OpenAI Tools](./openai_tools)             | Chat                | ✅                    | ✅                         | ✅                                   | `tools`              | [Legacy] If you are using a recent OpenAI model (`1106` onwards). Generic Tool Calling agent recommended instead. | [Ref](https://api.python.langchain.com/en/latest/agents/langchain.agents.openai_tools.base.create_openai_tools_agent.html) |
+| [OpenAI Functions](./openai_functions_agent)| Chat                | ✅                    | ✅                         |                                     | `functions`          | [Legacy] If you are using an OpenAI model, or an open-source model that has been finetuned for function calling and exposes the same `functions` parameters as OpenAI. Generic Tool Calling agent recommended instead | [Ref](https://api.python.langchain.com/en/latest/agents/langchain.agents.openai_functions_agent.base.create_openai_functions_agent.html) |
 | [XML](./xml_agent)                         | LLM                 | ✅                    |                            |                                     |                      | If you are using Anthropic models, or other models good at XML | [Ref](https://api.python.langchain.com/en/latest/agents/langchain.agents.xml.base.create_xml_agent.html)                                                                                               |
 | [Structured Chat](./structured_chat)       | Chat                | ✅                    | ✅                         |                                     |                      | If you need to support tools with multiple inputs | [Ref](https://api.python.langchain.com/en/latest/agents/langchain.agents.structured_chat.base.create_structured_chat_agent.html) |
 | [JSON Chat](./json_agent)                  | Chat                | ✅                    |                            |                                     |                      | If you are using a model good at JSON | [Ref](https://api.python.langchain.com/en/latest/agents/langchain.agents.json_chat.base.create_json_chat_agent.html) |

docs/docs/modules/agents/agent_types/openai_tools.ipynb

@@ -6,7 +6,7 @@
    "metadata": {},
    "source": [
     "---\n",
-    "sidebar_position: 0\n",
+    "sidebar_position: 0.1\n",
     "---"
    ]
   },
@@ -252,7 +252,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/modules/agents/agent_types/tool_calling.ipynb

@@ -0,0 +1,312 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 0\n",
+    "sidebar_label: Tool calling\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Tool calling agent\n",
+    "\n",
+    "[Tool calling](/docs/modules/model_io/chat/function_calling) allows a model to detect when one or more tools should be called and respond with the inputs that should be passed to those tools. In an API call, you can describe tools and have the model intelligently choose to output a structured object like JSON containing arguments to call these tools. The goal of tools APIs is to more reliably return valid and useful tool calls than what can be done using a generic text completion or chat API.\n",
+    "\n",
+    "We can take advantage of this structured output, combined with the fact that you can bind multiple tools to a [tool calling chat model](/docs/integrations/chat/) and\n",
+    "allow the model to choose which one to call, to create an agent that repeatedly calls tools and receives results until a query is resolved.\n",
+    "\n",
+    "This is a more generalized version of the [OpenAI tools agent](/docs/modules/agents/agent_types/openai_tools/), which was designed for OpenAI's specific style of\n",
+    "tool calling. It uses LangChain's ToolCall interface to support a wider range of\n",
+    "provider implementations, such as [Anthropic](/docs/integrations/chat/anthropic/), [Google Gemini](/docs/integrations/chat/google_vertex_ai_palm/), and [Mistral](/docs/integrations/chat/mistralai/)\n",
+    "in addition to [OpenAI](/docs/integrations/chat/openai/).\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "Any models that support tool calling can be used in this agent. You can see which models support tool calling [here](/docs/integrations/chat/)\n",
+    "\n",
+    "This demo uses [Tavily](https://app.tavily.com), but you can also swap in any other [built-in tool](/docs/integrations/tools) or add [custom tools](/docs/modules/tools/custom_tools/).\n",
+    "You'll need to sign up for an API key and set it as `process.env.TAVILY_API_KEY`.\n",
+    "\n",
+    "```{=mdx}\n",
+    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
+    "\n",
+    "<ChatModelTabs\n",
+    "  customVarName=\"llm\"\n",
+    "  hideCohere\n",
+    "/>\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# | output: false\n",
+    "# | echo: false\n",
+    "\n",
+    "from langchain_anthropic import ChatAnthropic\n",
+    "\n",
+    "llm = ChatAnthropic(model=\"claude-3-sonnet-20240229\", temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Initialize Tools\n",
+    "\n",
+    "We will first create a tool that can search the web:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import AgentExecutor, create_tool_calling_agent\n",
+    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "tools = [TavilySearchResults(max_results=1)]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create Agent\n",
+    "\n",
+    "Next, let's initialize our tool calling agent:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant. Make sure to use the tavily_search_results_json tool for information.\",\n",
+    "        ),\n",
+    "        (\"placeholder\", \"{chat_history}\"),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "        (\"placeholder\", \"{agent_scratchpad}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "# Construct the Tools agent\n",
+    "agent = create_tool_calling_agent(llm, tools, prompt)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Run Agent\n",
+    "\n",
+    "Now, let's initialize the executor that will run our agent and invoke it!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/bagatur/langchain/libs/partners/anthropic/langchain_anthropic/chat_models.py:347: UserWarning: stream: Tool use is not yet supported in streaming mode.\n",
+      "  warnings.warn(\"stream: Tool use is not yet supported in streaming mode.\")\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[32;1m\u001b[1;3m\n",
+      "Invoking: `tavily_search_results_json` with `{'query': 'LangChain'}`\n",
+      "responded: [{'id': 'toolu_01QxrrT9srzkYCNyEZMDhGeg', 'input': {'query': 'LangChain'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]\n",
+      "\n",
+      "\u001b[0m\u001b[36;1m\u001b[1;3m[{'url': 'https://github.com/langchain-ai/langchain', 'content': 'About\\n⚡ Building applications with LLMs through composability ⚡\\nResources\\nLicense\\nCode of conduct\\nSecurity policy\\nStars\\nWatchers\\nForks\\nReleases\\n291\\nPackages\\n0\\nUsed by 39k\\nContributors\\n1,848\\nLanguages\\nFooter\\nFooter navigation Latest commit\\nGit stats\\nFiles\\nREADME.md\\n🦜️🔗 LangChain\\n⚡ Building applications with LLMs through composability ⚡\\nLooking for the JS/TS library? ⚡ Building applications with LLMs through composability ⚡\\nLicense\\nlangchain-ai/langchain\\nName already in use\\nUse Git or checkout with SVN using the web URL.\\n 📖 Documentation\\nPlease see here for full documentation, which includes:\\n💁 Contributing\\nAs an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.\\n What can you build with LangChain?\\n❓ Retrieval augmented generation\\n💬 Analyzing structured data\\n🤖 Chatbots\\nAnd much more!'}]\u001b[0m"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/bagatur/langchain/libs/partners/anthropic/langchain_anthropic/chat_models.py:347: UserWarning: stream: Tool use is not yet supported in streaming mode.\n",
+      "  warnings.warn(\"stream: Tool use is not yet supported in streaming mode.\")\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[32;1m\u001b[1;3mLangChain is an open-source Python library that helps developers build applications with large language models (LLMs) through composability. Some key features of LangChain include:\n",
+      "\n",
+      "- Retrieval augmented generation - Allowing LLMs to retrieve and utilize external data sources when generating outputs.\n",
+      "\n",
+      "- Analyzing structured data - Tools for working with structured data like databases, APIs, PDFs, etc. and allowing LLMs to reason over this data.\n",
+      "\n",
+      "- Building chatbots and agents - Frameworks for building conversational AI applications.\n",
+      "\n",
+      "- Composability - LangChain allows you to chain together different LLM capabilities and data sources in a modular and reusable way.\n",
+      "\n",
+      "The library aims to make it easier to build real-world applications that leverage the power of large language models in a scalable and robust way. It provides abstractions and primitives for working with LLMs from different providers like OpenAI, Anthropic, Cohere, etc. LangChain is open-source and has an active community contributing new features and improvements.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'input': 'what is LangChain?',\n",
+       " 'output': 'LangChain is an open-source Python library that helps developers build applications with large language models (LLMs) through composability. Some key features of LangChain include:\\n\\n- Retrieval augmented generation - Allowing LLMs to retrieve and utilize external data sources when generating outputs.\\n\\n- Analyzing structured data - Tools for working with structured data like databases, APIs, PDFs, etc. and allowing LLMs to reason over this data.\\n\\n- Building chatbots and agents - Frameworks for building conversational AI applications.\\n\\n- Composability - LangChain allows you to chain together different LLM capabilities and data sources in a modular and reusable way.\\n\\nThe library aims to make it easier to build real-world applications that leverage the power of large language models in a scalable and robust way. It provides abstractions and primitives for working with LLMs from different providers like OpenAI, Anthropic, Cohere, etc. LangChain is open-source and has an active community contributing new features and improvements.'}"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Create an agent executor by passing in the agent and tools\n",
+    "agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)\n",
+    "agent_executor.invoke({\"input\": \"what is LangChain?\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "```{=mdx}\n",
+    ":::tip\n",
+    "[LangSmith trace](https://smith.langchain.com/public/2f956a2e-0820-47c4-a798-c83f024e5ca1/r)\n",
+    ":::\n",
+    "```\n",
+    "\n",
+    "## Using with chat history\n",
+    "\n",
+    "This type of agent can optionally take chat messages representing previous conversation turns. It can use that previous history to respond conversationally. For more details, see [this section of the agent quickstart](/docs/modules/agents/quick_start#adding-in-memory)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/bagatur/langchain/libs/partners/anthropic/langchain_anthropic/chat_models.py:347: UserWarning: stream: Tool use is not yet supported in streaming mode.\n",
+      "  warnings.warn(\"stream: Tool use is not yet supported in streaming mode.\")\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[32;1m\u001b[1;3mBased on what you told me, your name is Bob. I don't need to use any tools to look that up since you directly provided your name.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'input': \"what's my name? Don't use tools to look this up unless you NEED to\",\n",
+       " 'chat_history': [HumanMessage(content='hi! my name is bob'),\n",
+       "  AIMessage(content='Hello Bob! How can I assist you today?')],\n",
+       " 'output': \"Based on what you told me, your name is Bob. I don't need to use any tools to look that up since you directly provided your name.\"}"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import AIMessage, HumanMessage\n",
+    "\n",
+    "agent_executor.invoke(\n",
+    "    {\n",
+    "        \"input\": \"what's my name? Don't use tools to look this up unless you NEED to\",\n",
+    "        \"chat_history\": [\n",
+    "            HumanMessage(content=\"hi! my name is bob\"),\n",
+    "            AIMessage(content=\"Hello Bob! How can I assist you today?\"),\n",
+    "        ],\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "```{=mdx}\n",
+    ":::tip\n",
+    "[LangSmith trace](https://smith.langchain.com/public/e21ececb-2e60-49e5-9f06-a91b0fb11fb8/r)\n",
+    ":::\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv-2",
+   "language": "python",
+   "name": "poetry-venv-2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/docs/modules/agents/quick_start.ipynb

@@ -78,20 +78,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 3,
    "id": "e593bbf6",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[{'url': 'https://www.metoffice.gov.uk/weather/forecast/9q8yym8kr',\n",
-       "  'content': 'Thu 11 Jan Thu 11 Jan Seven day forecast for San Francisco  San Francisco (United States of America) weather Find a forecast  Sat 6 Jan Sat 6 Jan Sun 7 Jan Sun 7 Jan Mon 8 Jan Mon 8 Jan Tue 9 Jan Tue 9 Jan Wed 10 Jan Wed 10 Jan Thu 11 Jan  Find a forecast Please choose your location from the nearest places to : Forecast days Today Today Sat 6 Jan Sat 6 JanSan Francisco 7 day weather forecast including weather warnings, temperature, rain, wind, visibility, humidity and UV ... (11 January 2024) Time 00:00 01:00 02:00 03:00 04:00 05:00 06:00 07:00 08:00 09:00 10:00 11:00 12:00 ... Oakland Int. 11.5 miles; San Francisco International 11.5 miles; Corte Madera 12.3 miles; Redwood City 23.4 miles;'},\n",
-       " {'url': 'https://www.latimes.com/travel/story/2024-01-11/east-brother-light-station-lighthouse-california',\n",
-       "  'content': \"May 18, 2023  Jan. 4, 2024 Subscribe for unlimited accessSite Map Follow Us MORE FROM THE L.A. TIMES  Jan. 8, 2024 Travel & Experiences This must be Elysian Valley (a.k.a. Frogtown) Jan. 5, 2024 Food  June 30, 2023The East Brother Light Station in the San Francisco Bay is not a destination for everyone. ... Jan. 11, 2024 3 AM PT ... Champagne and hors d'oeuvres are served in late afternoon — outdoors if ...\"}]"
+       "[{'url': 'https://www.weatherapi.com/',\n",
+       "  'content': \"{'location': {'name': 'San Francisco', 'region': 'California', 'country': 'United States of America', 'lat': 37.78, 'lon': -122.42, 'tz_id': 'America/Los_Angeles', 'localtime_epoch': 1712847697, 'localtime': '2024-04-11 8:01'}, 'current': {'last_updated_epoch': 1712847600, 'last_updated': '2024-04-11 08:00', 'temp_c': 11.1, 'temp_f': 52.0, 'is_day': 1, 'condition': {'text': 'Partly cloudy', 'icon': '//cdn.weatherapi.com/weather/64x64/day/116.png', 'code': 1003}, 'wind_mph': 2.2, 'wind_kph': 3.6, 'wind_degree': 10, 'wind_dir': 'N', 'pressure_mb': 1015.0, 'pressure_in': 29.98, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 97, 'cloud': 25, 'feelslike_c': 11.5, 'feelslike_f': 52.6, 'vis_km': 14.0, 'vis_miles': 8.0, 'uv': 4.0, 'gust_mph': 2.8, 'gust_kph': 4.4}}\"},\n",
+       " {'url': 'https://www.yahoo.com/news/april-11-2024-san-francisco-122026435.html',\n",
+       "  'content': \"2024 NBA Mock Draft 6.0: Projections for every pick following March Madness With the NCAA tournament behind us, here's an updated look at Yahoo Sports' first- and second-round projections for the ...\"},\n",
+       " {'url': 'https://world-weather.info/forecast/usa/san_francisco/april-2024/',\n",
+       "  'content': 'Extended weather forecast in San Francisco. Hourly Week 10 days 14 days 30 days Year. Detailed ⚡ San Francisco Weather Forecast for April 2024 - day/night 🌡️ temperatures, precipitations - World-Weather.info.'},\n",
+       " {'url': 'https://www.wunderground.com/hourly/us/ca/san-francisco/94144/date/date/2024-4-11',\n",
+       "  'content': 'Personal Weather Station. Inner Richmond (KCASANFR1685) Location: San Francisco, CA. Elevation: 207ft. Nearby Weather Stations. Hourly Forecast for Today, Thursday 04/11Hourly for Today, Thu 04/11 ...'},\n",
+       " {'url': 'https://weatherspark.com/h/y/557/2024/Historical-Weather-during-2024-in-San-Francisco-California-United-States',\n",
+       "  'content': 'San Francisco Temperature History 2024\\nHourly Temperature in 2024 in San Francisco\\nCompare San Francisco to another city:\\nCloud Cover in 2024 in San Francisco\\nDaily Precipitation in 2024 in San Francisco\\nObserved Weather in 2024 in San Francisco\\nHours of Daylight and Twilight in 2024 in San Francisco\\nSunrise & Sunset with Twilight and Daylight Saving Time in 2024 in San Francisco\\nSolar Elevation and Azimuth in 2024 in San Francisco\\nMoon Rise, Set & Phases in 2024 in San Francisco\\nHumidity Comfort Levels in 2024 in San Francisco\\nWind Speed in 2024 in San Francisco\\nHourly Wind Speed in 2024 in San Francisco\\nHourly Wind Direction in 2024 in San Francisco\\nAtmospheric Pressure in 2024 in San Francisco\\nData Sources\\n See all nearby weather stations\\nLatest Report — 3:56 PM\\nWed, Jan 24, 2024\\xa0\\xa0\\xa0\\xa013 min ago\\xa0\\xa0\\xa0\\xa0UTC 23:56\\nCall Sign KSFO\\nTemp.\\n60.1°F\\nPrecipitation\\nNo Report\\nWind\\n6.9 mph\\nCloud Cover\\nMostly Cloudy\\n1,800 ft\\nRaw: KSFO 242356Z 18006G19KT 10SM FEW015 BKN018 BKN039 16/12 A3004 RMK AO2 SLP171 T01560122 10156 20122 55001\\n While having the tremendous advantages of temporal and spatial completeness, these reconstructions: (1) are based on computer models that may have model-based errors, (2) are coarsely sampled on a 50 km grid and are therefore unable to reconstruct the local variations of many microclimates, and (3) have particular difficulty with the weather in some coastal areas, especially small islands.\\n We further caution that our travel scores are only as good as the data that underpin them, that weather conditions at any given location and time are unpredictable and variable, and that the definition of the scores reflects a particular set of preferences that may not agree with those of any particular reader.\\n 2024 Weather History in San Francisco California, United States\\nThe data for this report comes from the San Francisco International Airport.'}]"
       ]
      },
-     "execution_count": 24,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -140,7 +146,7 @@
     {
      "data": {
       "text/plain": [
-       "Document(page_content=\"dataset uploading.Once we have a dataset, how can we use it to test changes to a prompt or chain? The most basic approach is to run the chain over the data points and visualize the outputs. Despite technological advancements, there still is no substitute for looking at outputs by eye. Currently, running the chain over the data points needs to be done client-side. The LangSmith client makes it easy to pull down a dataset and then run a chain over them, logging the results to a new project associated with the dataset. From there, you can review them. We've made it easy to assign feedback to runs and mark them as correct or incorrect directly in the web app, displaying aggregate statistics for each test project.We also make it easier to evaluate these runs. To that end, we've added a set of evaluators to the open-source LangChain library. These evaluators can be specified when initiating a test run and will evaluate the results once the test run completes. If we’re being honest, most of\", metadata={'source': 'https://docs.smith.langchain.com/overview', 'title': 'LangSmith Overview and User Guide | 🦜️🛠️ LangSmith', 'description': 'Building reliable LLM applications can be challenging. LangChain simplifies the initial setup, but there is still work needed to bring the performance of prompts, chains and agents up the level where they are reliable enough to be used in production.', 'language': 'en'})"
+       "Document(page_content='import Clientfrom langsmith.evaluation import evaluateclient = Client()# Define dataset: these are your test casesdataset_name = \"Sample Dataset\"dataset = client.create_dataset(dataset_name, description=\"A sample dataset in LangSmith.\")client.create_examples(    inputs=[        {\"postfix\": \"to LangSmith\"},        {\"postfix\": \"to Evaluations in LangSmith\"},    ],    outputs=[        {\"output\": \"Welcome to LangSmith\"},        {\"output\": \"Welcome to Evaluations in LangSmith\"},    ],    dataset_id=dataset.id,)# Define your evaluatordef exact_match(run, example):    return {\"score\": run.outputs[\"output\"] == example.outputs[\"output\"]}experiment_results = evaluate(    lambda input: \"Welcome \" + input[\\'postfix\\'], # Your AI system goes here    data=dataset_name, # The data to predict and grade over    evaluators=[exact_match], # The evaluators to score the results    experiment_prefix=\"sample-experiment\", # The name of the experiment    metadata={      \"version\": \"1.0.0\",      \"revision_id\":', metadata={'source': 'https://docs.smith.langchain.com/overview', 'title': 'Getting started with LangSmith | 🦜️🛠️ LangSmith', 'description': 'Introduction', 'language': 'en'})"
       ]
      },
      "execution_count": 5,
@@ -225,7 +231,7 @@
    "source": [
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)"
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
    ]
   },
   {
@@ -283,9 +289,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.agents import create_openai_functions_agent\n",
+    "from langchain.agents import create_tool_calling_agent\n",
     "\n",
-    "agent = create_openai_functions_agent(llm, tools, prompt)"
+    "agent = create_tool_calling_agent(llm, tools, prompt)"
    ]
   },
   {
@@ -367,20 +373,26 @@
       "\n",
       "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
       "\u001b[32;1m\u001b[1;3m\n",
-      "Invoking: `langsmith_search` with `{'query': 'LangSmith testing'}`\n",
+      "Invoking: `langsmith_search` with `{'query': 'how can LangSmith help with testing'}`\n",
       "\n",
       "\n",
-      "\u001b[0m\u001b[33;1m\u001b[1;3m[Document(page_content='LangSmith Overview and User Guide | 🦜️🛠️ LangSmith', metadata={'source': 'https://docs.smith.langchain.com/overview', 'title': 'LangSmith Overview and User Guide | 🦜️🛠️ LangSmith', 'description': 'Building reliable LLM applications can be challenging. LangChain simplifies the initial setup, but there is still work needed to bring the performance of prompts, chains and agents up the level where they are reliable enough to be used in production.', 'language': 'en'}), Document(page_content='Skip to main content🦜️🛠️ LangSmith DocsPython DocsJS/TS DocsSearchGo to AppLangSmithOverviewTracingTesting & EvaluationOrganizationsHubLangSmith CookbookOverviewOn this pageLangSmith Overview and User GuideBuilding reliable LLM applications can be challenging. LangChain simplifies the initial setup, but there is still work needed to bring the performance of prompts, chains and agents up the level where they are reliable enough to be used in production.Over the past two months, we at LangChain have been building and using LangSmith with the goal of bridging this gap. This is our tactical user guide to outline effective ways to use LangSmith and maximize its benefits.On by default\\u200bAt LangChain, all of us have LangSmith’s tracing running in the background by default. On the Python side, this is achieved by setting environment variables, which we establish whenever we launch a virtual environment or open our bash shell and leave them set. The same principle applies to most JavaScript', metadata={'source': 'https://docs.smith.langchain.com/overview', 'title': 'LangSmith Overview and User Guide | 🦜️🛠️ LangSmith', 'description': 'Building reliable LLM applications can be challenging. LangChain simplifies the initial setup, but there is still work needed to bring the performance of prompts, chains and agents up the level where they are reliable enough to be used in production.', 'language': 'en'}), Document(page_content='You can also quickly edit examples and add them to datasets to expand the surface area of your evaluation sets or to fine-tune a model for improved quality or reduced costs.Monitoring\\u200bAfter all this, your app might finally ready to go in production. LangSmith can also be used to monitor your application in much the same way that you used for debugging. You can log all traces, visualize latency and token usage statistics, and troubleshoot specific issues as they arise. Each run can also be assigned string tags or key-value metadata, allowing you to attach correlation ids or AB test variants, and filter runs accordingly.We’ve also made it possible to associate feedback programmatically with runs. This means that if your application has a thumbs up/down button on it, you can use that to log feedback back to LangSmith. This can be used to track performance over time and pinpoint under performing data points, which you can subsequently add to a dataset for future testing — mirroring the', metadata={'source': 'https://docs.smith.langchain.com/overview', 'title': 'LangSmith Overview and User Guide | 🦜️🛠️ LangSmith', 'description': 'Building reliable LLM applications can be challenging. LangChain simplifies the initial setup, but there is still work needed to bring the performance of prompts, chains and agents up the level where they are reliable enough to be used in production.', 'language': 'en'}), Document(page_content='inputs, and see what happens. At some point though, our application is performing\\nwell and we want to be more rigorous about testing changes. We can use a dataset\\nthat we’ve constructed along the way (see above). Alternatively, we could spend some\\ntime constructing a small dataset by hand. For these situations, LangSmith simplifies', metadata={'source': 'https://docs.smith.langchain.com/overview', 'title': 'LangSmith Overview and User Guide | 🦜️🛠️ LangSmith', 'description': 'Building reliable LLM applications can be challenging. LangChain simplifies the initial setup, but there is still work needed to bring the performance of prompts, chains and agents up the level where they are reliable enough to be used in production.', 'language': 'en'})]\u001b[0m\u001b[32;1m\u001b[1;3mLangSmith can help with testing in several ways. Here are some ways LangSmith can assist with testing:\n",
+      "\u001b[0m\u001b[33;1m\u001b[1;3mGetting started with LangSmith | 🦜️🛠️ LangSmith\n",
       "\n",
-      "1. Tracing: LangSmith provides tracing capabilities that can be used to monitor and debug your application during testing. You can log all traces, visualize latency and token usage statistics, and troubleshoot specific issues as they arise.\n",
+      "Skip to main contentLangSmith API DocsSearchGo to AppQuick StartUser GuideTracingEvaluationProduction Monitoring & AutomationsPrompt HubProxyPricingSelf-HostingCookbookQuick StartOn this pageGetting started with LangSmithIntroduction​LangSmith is a platform for building production-grade LLM applications. It allows you to closely monitor and evaluate your application, so you can ship quickly and with confidence. Use of LangChain is not necessary - LangSmith works on its own!Install LangSmith​We offer Python and Typescript SDKs for all your LangSmith needs.PythonTypeScriptpip install -U langsmithyarn add langchain langsmithCreate an API key​To create an API key head to the setting pages. Then click Create API Key.Setup your environment​Shellexport LANGCHAIN_TRACING_V2=trueexport LANGCHAIN_API_KEY=<your-api-key># The below examples use the OpenAI API, though it's not necessary in generalexport OPENAI_API_KEY=<your-openai-api-key>Log your first trace​We provide multiple ways to log traces\n",
       "\n",
-      "2. Evaluation: LangSmith allows you to quickly edit examples and add them to datasets to expand the surface area of your evaluation sets. This can help you test and fine-tune your models for improved quality or reduced costs.\n",
+      "Learn about the workflows LangSmith supports at each stage of the LLM application lifecycle.Pricing: Learn about the pricing model for LangSmith.Self-Hosting: Learn about self-hosting options for LangSmith.Proxy: Learn about the proxy capabilities of LangSmith.Tracing: Learn about the tracing capabilities of LangSmith.Evaluation: Learn about the evaluation capabilities of LangSmith.Prompt Hub Learn about the Prompt Hub, a prompt management tool built into LangSmith.Additional Resources​LangSmith Cookbook: A collection of tutorials and end-to-end walkthroughs using LangSmith.LangChain Python: Docs for the Python LangChain library.LangChain Python API Reference: documentation to review the core APIs of LangChain.LangChain JS: Docs for the TypeScript LangChain libraryDiscord: Join us on our Discord to discuss all things LangChain!FAQ​How do I migrate projects between organizations?​Currently we do not support project migration betwen organizations. While you can manually imitate this by\n",
       "\n",
-      "3. Monitoring: Once your application is ready for production, LangSmith can be used to monitor your application. You can log feedback programmatically with runs, track performance over time, and pinpoint underperforming data points. This information can be used to improve your application and add to datasets for future testing.\n",
+      "team deals with sensitive data that cannot be logged. How can I ensure that only my team can access it?​If you are interested in a private deployment of LangSmith or if you need to self-host, please reach out to us at sales@langchain.dev. Self-hosting LangSmith requires an annual enterprise license that also comes with support and formalized access to the LangChain team.Was this page helpful?NextUser GuideIntroductionInstall LangSmithCreate an API keySetup your environmentLog your first traceCreate your first evaluationNext StepsAdditional ResourcesFAQHow do I migrate projects between organizations?Why aren't my runs aren't showing up in my project?My team deals with sensitive data that cannot be logged. How can I ensure that only my team can access it?CommunityDiscordTwitterGitHubDocs CodeLangSmith SDKPythonJS/TSMoreHomepageBlogLangChain Python DocsLangChain JS/TS DocsCopyright © 2024 LangChain, Inc.\u001b[0m\u001b[32;1m\u001b[1;3mLangSmith is a platform for building production-grade LLM applications that can help with testing in the following ways:\n",
       "\n",
-      "4. Rigorous Testing: When your application is performing well and you want to be more rigorous about testing changes, LangSmith can simplify the process. You can use existing datasets or construct small datasets by hand to test different scenarios and evaluate the performance of your application.\n",
+      "1. **Tracing**: LangSmith provides tracing capabilities that allow you to closely monitor and evaluate your application during testing. You can log traces to track the behavior of your application and identify any issues.\n",
       "\n",
-      "For more detailed information on how to use LangSmith for testing, you can refer to the [LangSmith Overview and User Guide](https://docs.smith.langchain.com/overview).\u001b[0m\n",
+      "2. **Evaluation**: LangSmith offers evaluation capabilities that enable you to assess the performance of your application during testing. This helps you ensure that your application functions as expected and meets the required standards.\n",
+      "\n",
+      "3. **Production Monitoring & Automations**: LangSmith allows you to monitor your application in production and automate certain processes, which can be beneficial for testing different scenarios and ensuring the stability of your application.\n",
+      "\n",
+      "4. **Prompt Hub**: LangSmith includes a Prompt Hub, a prompt management tool that can streamline the testing process by providing a centralized location for managing prompts and inputs for your application.\n",
+      "\n",
+      "Overall, LangSmith can assist with testing by providing tools for monitoring, evaluating, and automating processes to ensure the reliability and performance of your application during testing phases.\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -389,7 +401,7 @@
      "data": {
       "text/plain": [
        "{'input': 'how can langsmith help with testing?',\n",
-       " 'output': 'LangSmith can help with testing in several ways. Here are some ways LangSmith can assist with testing:\\n\\n1. Tracing: LangSmith provides tracing capabilities that can be used to monitor and debug your application during testing. You can log all traces, visualize latency and token usage statistics, and troubleshoot specific issues as they arise.\\n\\n2. Evaluation: LangSmith allows you to quickly edit examples and add them to datasets to expand the surface area of your evaluation sets. This can help you test and fine-tune your models for improved quality or reduced costs.\\n\\n3. Monitoring: Once your application is ready for production, LangSmith can be used to monitor your application. You can log feedback programmatically with runs, track performance over time, and pinpoint underperforming data points. This information can be used to improve your application and add to datasets for future testing.\\n\\n4. Rigorous Testing: When your application is performing well and you want to be more rigorous about testing changes, LangSmith can simplify the process. You can use existing datasets or construct small datasets by hand to test different scenarios and evaluate the performance of your application.\\n\\nFor more detailed information on how to use LangSmith for testing, you can refer to the [LangSmith Overview and User Guide](https://docs.smith.langchain.com/overview).'}"
+       " 'output': 'LangSmith is a platform for building production-grade LLM applications that can help with testing in the following ways:\\n\\n1. **Tracing**: LangSmith provides tracing capabilities that allow you to closely monitor and evaluate your application during testing. You can log traces to track the behavior of your application and identify any issues.\\n\\n2. **Evaluation**: LangSmith offers evaluation capabilities that enable you to assess the performance of your application during testing. This helps you ensure that your application functions as expected and meets the required standards.\\n\\n3. **Production Monitoring & Automations**: LangSmith allows you to monitor your application in production and automate certain processes, which can be beneficial for testing different scenarios and ensuring the stability of your application.\\n\\n4. **Prompt Hub**: LangSmith includes a Prompt Hub, a prompt management tool that can streamline the testing process by providing a centralized location for managing prompts and inputs for your application.\\n\\nOverall, LangSmith can assist with testing by providing tools for monitoring, evaluating, and automating processes to ensure the reliability and performance of your application during testing phases.'}"
       ]
      },
      "execution_count": 14,
@@ -418,7 +430,7 @@
       "Invoking: `tavily_search_results_json` with `{'query': 'weather in San Francisco'}`\n",
       "\n",
       "\n",
-      "\u001b[0m\u001b[36;1m\u001b[1;3m[{'url': 'https://www.whereandwhen.net/when/north-america/california/san-francisco-ca/january/', 'content': 'Best time to go to San Francisco? Weather in San Francisco in january 2024  How was the weather last january? Here is the day by day recorded weather in San Francisco in january 2023:  Seasonal average climate and temperature of San Francisco in january  8% 46% 29% 12% 8% Evolution of daily average temperature and precipitation in San Francisco in januaryWeather in San Francisco in january 2024. The weather in San Francisco in january comes from statistical datas on the past years. You can view the weather statistics the entire month, but also by using the tabs for the beginning, the middle and the end of the month. ... 11-01-2023 50°F to 54°F. 12-01-2023 50°F to 59°F. 13-01-2023 54°F to ...'}, {'url': 'https://www.latimes.com/travel/story/2024-01-11/east-brother-light-station-lighthouse-california', 'content': \"May 18, 2023  Jan. 4, 2024 Subscribe for unlimited accessSite Map Follow Us MORE FROM THE L.A. TIMES  Jan. 8, 2024 Travel & Experiences This must be Elysian Valley (a.k.a. Frogtown) Jan. 5, 2024 Food  June 30, 2023The East Brother Light Station in the San Francisco Bay is not a destination for everyone. ... Jan. 11, 2024 3 AM PT ... Champagne and hors d'oeuvres are served in late afternoon — outdoors if ...\"}]\u001b[0m\u001b[32;1m\u001b[1;3mI'm sorry, I couldn't find the current weather in San Francisco. However, you can check the weather in San Francisco by visiting a reliable weather website or using a weather app on your phone.\u001b[0m\n",
+      "\u001b[0m\u001b[36;1m\u001b[1;3m[{'url': 'https://www.weatherapi.com/', 'content': \"{'location': {'name': 'San Francisco', 'region': 'California', 'country': 'United States of America', 'lat': 37.78, 'lon': -122.42, 'tz_id': 'America/Los_Angeles', 'localtime_epoch': 1712847697, 'localtime': '2024-04-11 8:01'}, 'current': {'last_updated_epoch': 1712847600, 'last_updated': '2024-04-11 08:00', 'temp_c': 11.1, 'temp_f': 52.0, 'is_day': 1, 'condition': {'text': 'Partly cloudy', 'icon': '//cdn.weatherapi.com/weather/64x64/day/116.png', 'code': 1003}, 'wind_mph': 2.2, 'wind_kph': 3.6, 'wind_degree': 10, 'wind_dir': 'N', 'pressure_mb': 1015.0, 'pressure_in': 29.98, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 97, 'cloud': 25, 'feelslike_c': 11.5, 'feelslike_f': 52.6, 'vis_km': 14.0, 'vis_miles': 8.0, 'uv': 4.0, 'gust_mph': 2.8, 'gust_kph': 4.4}}\"}, {'url': 'https://www.yahoo.com/news/april-11-2024-san-francisco-122026435.html', 'content': \"2024 NBA Mock Draft 6.0: Projections for every pick following March Madness With the NCAA tournament behind us, here's an updated look at Yahoo Sports' first- and second-round projections for the ...\"}, {'url': 'https://www.weathertab.com/en/c/e/04/united-states/california/san-francisco/', 'content': 'Explore comprehensive April 2024 weather forecasts for San Francisco, including daily high and low temperatures, precipitation risks, and monthly temperature trends. Featuring detailed day-by-day forecasts, dynamic graphs of daily rain probabilities, and temperature trends to help you plan ahead. ... 11 65°F 49°F 18°C 9°C 29% 12 64°F 49°F ...'}, {'url': 'https://weatherspark.com/h/y/557/2024/Historical-Weather-during-2024-in-San-Francisco-California-United-States', 'content': 'San Francisco Temperature History 2024\\nHourly Temperature in 2024 in San Francisco\\nCompare San Francisco to another city:\\nCloud Cover in 2024 in San Francisco\\nDaily Precipitation in 2024 in San Francisco\\nObserved Weather in 2024 in San Francisco\\nHours of Daylight and Twilight in 2024 in San Francisco\\nSunrise & Sunset with Twilight and Daylight Saving Time in 2024 in San Francisco\\nSolar Elevation and Azimuth in 2024 in San Francisco\\nMoon Rise, Set & Phases in 2024 in San Francisco\\nHumidity Comfort Levels in 2024 in San Francisco\\nWind Speed in 2024 in San Francisco\\nHourly Wind Speed in 2024 in San Francisco\\nHourly Wind Direction in 2024 in San Francisco\\nAtmospheric Pressure in 2024 in San Francisco\\nData Sources\\n See all nearby weather stations\\nLatest Report — 3:56 PM\\nWed, Jan 24, 2024\\xa0\\xa0\\xa0\\xa013 min ago\\xa0\\xa0\\xa0\\xa0UTC 23:56\\nCall Sign KSFO\\nTemp.\\n60.1°F\\nPrecipitation\\nNo Report\\nWind\\n6.9 mph\\nCloud Cover\\nMostly Cloudy\\n1,800 ft\\nRaw: KSFO 242356Z 18006G19KT 10SM FEW015 BKN018 BKN039 16/12 A3004 RMK AO2 SLP171 T01560122 10156 20122 55001\\n While having the tremendous advantages of temporal and spatial completeness, these reconstructions: (1) are based on computer models that may have model-based errors, (2) are coarsely sampled on a 50 km grid and are therefore unable to reconstruct the local variations of many microclimates, and (3) have particular difficulty with the weather in some coastal areas, especially small islands.\\n We further caution that our travel scores are only as good as the data that underpin them, that weather conditions at any given location and time are unpredictable and variable, and that the definition of the scores reflects a particular set of preferences that may not agree with those of any particular reader.\\n 2024 Weather History in San Francisco California, United States\\nThe data for this report comes from the San Francisco International Airport.'}, {'url': 'https://www.msn.com/en-us/weather/topstories/april-11-2024-san-francisco-bay-area-weather-forecast/vi-BB1lrXDb', 'content': 'April 11, 2024 San Francisco Bay Area weather forecast. Posted: April 11, 2024 | Last updated: April 11, 2024 ...'}]\u001b[0m\u001b[32;1m\u001b[1;3mThe current weather in San Francisco is partly cloudy with a temperature of 52.0°F (11.1°C). The wind speed is 3.6 kph coming from the north, and the humidity is at 97%.\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -427,7 +439,7 @@
      "data": {
       "text/plain": [
        "{'input': 'whats the weather in sf?',\n",
-       " 'output': \"I'm sorry, I couldn't find the current weather in San Francisco. However, you can check the weather in San Francisco by visiting a reliable weather website or using a weather app on your phone.\"}"
+       " 'output': 'The current weather in San Francisco is partly cloudy with a temperature of 52.0°F (11.1°C). The wind speed is 3.6 kph coming from the north, and the humidity is at 97%.'}"
       ]
      },
      "execution_count": 15,
@@ -508,7 +520,7 @@
       "\n",
       "\n",
       "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mYour name is Bob.\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mYour name is Bob. How can I assist you, Bob?\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -519,7 +531,7 @@
        "{'chat_history': [HumanMessage(content='hi! my name is bob'),\n",
        "  AIMessage(content='Hello Bob! How can I assist you today?')],\n",
        " 'input': \"what's my name?\",\n",
-       " 'output': 'Your name is Bob.'}"
+       " 'output': 'Your name is Bob. How can I assist you, Bob?'}"
       ]
      },
      "execution_count": 18,
@@ -549,7 +561,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 20,
    "id": "8edd96e6",
    "metadata": {},
    "outputs": [],
@@ -560,7 +572,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 21,
    "id": "6e76552a",
    "metadata": {},
    "outputs": [],
@@ -570,7 +582,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 22,
    "id": "828d1e95",
    "metadata": {},
    "outputs": [],
@@ -587,7 +599,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 23,
    "id": "1f5932b6",
    "metadata": {},
    "outputs": [
@@ -611,7 +623,7 @@
        " 'output': 'Hello Bob! How can I assist you today?'}"
       ]
      },
-     "execution_count": 22,
+     "execution_count": 23,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -627,7 +639,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 24,
    "id": "ae627966",
    "metadata": {},
    "outputs": [
@@ -638,7 +650,7 @@
       "\n",
       "\n",
       "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mYour name is Bob.\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mYour name is Bob! How can I help you, Bob?\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -649,10 +661,10 @@
        "{'input': \"what's my name?\",\n",
        " 'chat_history': [HumanMessage(content=\"hi! I'm bob\"),\n",
        "  AIMessage(content='Hello Bob! How can I assist you today?')],\n",
-       " 'output': 'Your name is Bob.'}"
+       " 'output': 'Your name is Bob! How can I help you, Bob?'}"
       ]
      },
-     "execution_count": 23,
+     "execution_count": 24,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -693,7 +705,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/modules/data_connection/document_transformers/code_splitter.ipynb

@@ -612,6 +612,63 @@
     "haskell_docs = haskell_splitter.create_documents([HASKELL_CODE])\n",
     "haskell_docs"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4a11f7cd-cd85-430c-b307-5b5b5f07f8db",
+   "metadata": {},
+   "source": [
+    "## PHP\n",
+    "Here's an example using the PHP text splitter:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "90c66e7e-87a5-4a81-bece-7949aabf2369",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='<?php\\nnamespace foo;'),\n",
+       " Document(page_content='class Hello {'),\n",
+       " Document(page_content='public function __construct() { }\\n}'),\n",
+       " Document(page_content='function hello() {\\n    echo \"Hello World!\";\\n}'),\n",
+       " Document(page_content='interface Human {\\n    public function breath();\\n}'),\n",
+       " Document(page_content='trait Foo { }\\nenum Color\\n{\\n    case Red;'),\n",
+       " Document(page_content='case Blue;\\n}')]"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "PHP_CODE = \"\"\"<?php\n",
+    "namespace foo;\n",
+    "class Hello {\n",
+    "    public function __construct() { }\n",
+    "}\n",
+    "function hello() {\n",
+    "    echo \"Hello World!\";\n",
+    "}\n",
+    "interface Human {\n",
+    "    public function breath();\n",
+    "}\n",
+    "trait Foo { }\n",
+    "enum Color\n",
+    "{\n",
+    "    case Red;\n",
+    "    case Blue;\n",
+    "}\"\"\"\n",
+    "php_splitter = RecursiveCharacterTextSplitter.from_language(\n",
+    "    language=Language.PHP, chunk_size=50, chunk_overlap=0\n",
+    ")\n",
+    "haskell_docs = php_splitter.create_documents([PHP_CODE])\n",
+    "haskell_docs"
+   ]
   }
  ],
  "metadata": {
@@ -630,7 +687,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/modules/data_connection/indexing.ipynb

@@ -60,8 +60,7 @@
     "   * document addition by id (`add_documents` method with `ids` argument)\n",
     "   * delete by id (`delete` method with `ids` argument)\n",
     "\n",
-
-    "Compatible Vectorstores: `AnalyticDB`, `AstraDB`, `AwaDB`, `Bagel`, `Cassandra`, `Chroma`, `CouchbaseVectorStore`, `DashVector`, `DatabricksVectorSearch`, `DeepLake`, `Dingo`, `ElasticVectorSearch`, `ElasticsearchStore`, `FAISS`, `HanaDB`, `Milvus`, `MyScale`, `OpenSearchVectorSearch`, `PGVector`, `Pinecone`, `Qdrant`, `Redis`, `Rockset`, `ScaNN`, `SupabaseVectorStore`, `SurrealDBStore`, `TimescaleVector`, `Vald`, `VDMS`, `Vearch`, `VespaStore`, `Weaviate`, `ZepVectorStore`, `OpenSearchVectorSearch`.\n",
+    "Compatible Vectorstores: `AnalyticDB`, `AstraDB`, `AwaDB`, `Bagel`, `Cassandra`, `Chroma`, `CouchbaseVectorStore`, `DashVector`, `DatabricksVectorSearch`, `DeepLake`, `Dingo`, `ElasticVectorSearch`, `ElasticsearchStore`, `FAISS`, `HanaDB`, `Milvus`, `MyScale`, `OpenSearchVectorSearch`, `PGVector`, `Pinecone`, `Qdrant`, `Redis`, `Rockset`, `ScaNN`, `SupabaseVectorStore`, `SurrealDBStore`, `TimescaleVector`, `Vald`, `VDMS`, `Vearch`, `VespaStore`, `Weaviate`, `ZepVectorStore`, `TencentVectorDB`, `OpenSearchVectorSearch`.\n",
     "  \n",
     "## Caution\n",
     "\n",

docs/docs/modules/data_connection/text_embedding/index.mdx

@@ -35,12 +35,12 @@ Accessing the API requires an API key, which you can get by creating an account
 export OPENAI_API_KEY="..."
 ```
 
-If you'd prefer not to set an environment variable you can pass the key in directly via the `openai_api_key` named parameter when initiating the OpenAI LLM class:
+If you'd prefer not to set an environment variable you can pass the key in directly via the `api_key` named parameter when initiating the OpenAI LLM class:
 
 ```python
 from langchain_openai import OpenAIEmbeddings
 
-embeddings_model = OpenAIEmbeddings(openai_api_key="...")
+embeddings_model = OpenAIEmbeddings(api_key="...")
 ```
 
 Otherwise you can initialize without any params:

docs/docs/modules/model_io/chat/function_calling.ipynb

@@ -0,0 +1,707 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "a413ade7-48f0-4d43-a1f3-d87f550a8018",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 2\n",
+    "title: Tool/function calling\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "50d59b14-c434-4359-be8e-4a21378e762f",
+   "metadata": {},
+   "source": [
+    "# Tool calling\n",
+    "\n",
+    "```{=mdx}\n",
+    ":::info\n",
+    "We use the term tool calling interchangeably with function calling. Although\n",
+    "function calling is sometimes meant to refer to invocations of a single function,\n",
+    "we treat all models as though they can return multiple tool or function calls in \n",
+    "each message.\n",
+    ":::\n",
+    "```\n",
+    "\n",
+    "Tool calling allows a model to respond to a given prompt by generating output that \n",
+    "matches a user-defined schema. While the name implies that the model is performing \n",
+    "some action, this is actually not the case! The model is coming up with the \n",
+    "arguments to a tool, and actually running the tool (or not) is up to the user - \n",
+    "for example, if you want to [extract output matching some schema](/docs/use_cases/extraction/) \n",
+    "from unstructured text, you could give the model an \"extraction\" tool that takes \n",
+    "parameters matching the desired schema, then treat the generated output as your final \n",
+    "result.\n",
+    "\n",
+    "A tool call includes a name, arguments dict, and an optional identifier. The \n",
+    "arguments dict is structured `{argument_name: argument_value}`.\n",
+    "\n",
+    "Many LLM providers, including [Anthropic](https://www.anthropic.com/), \n",
+    "[Cohere](https://cohere.com/), [Google](https://cloud.google.com/vertex-ai), \n",
+    "[Mistral](https://mistral.ai/), [OpenAI](https://openai.com/), and others, \n",
+    "support variants of a tool calling feature. These features typically allow requests \n",
+    "to the LLM to include available tools and their schemas, and for responses to include \n",
+    "calls to these tools. For instance, given a search engine tool, an LLM might handle a \n",
+    "query by first issuing a call to the search engine. The system calling the LLM can \n",
+    "receive the tool call, execute it, and return the output to the LLM to inform its \n",
+    "response. LangChain includes a suite of [built-in tools](/docs/integrations/tools/) \n",
+    "and supports several methods for defining your own [custom tools](/docs/modules/tools/custom_tools). \n",
+    "Tool-calling is extremely useful for building [tool-using chains and agents](/docs/use_cases/tool_use), \n",
+    "and for getting structured outputs from models more generally.\n",
+    "\n",
+    "Providers adopt different conventions for formatting tool schemas and tool calls. \n",
+    "For instance, Anthropic returns tool calls as parsed structures within a larger content block:\n",
+    "```python\n",
+    "[\n",
+    "  {\n",
+    "    \"text\": \"<thinking>\\nI should use a tool.\\n</thinking>\",\n",
+    "    \"type\": \"text\"\n",
+    "  },\n",
+    "  {\n",
+    "    \"id\": \"id_value\",\n",
+    "    \"input\": {\"arg_name\": \"arg_value\"},\n",
+    "    \"name\": \"tool_name\",\n",
+    "    \"type\": \"tool_use\"\n",
+    "  }\n",
+    "]\n",
+    "```\n",
+    "whereas OpenAI separates tool calls into a distinct parameter, with arguments as JSON strings:\n",
+    "```python\n",
+    "{\n",
+    "  \"tool_calls\": [\n",
+    "    {\n",
+    "      \"id\": \"id_value\",\n",
+    "      \"function\": {\n",
+    "        \"arguments\": '{\"arg_name\": \"arg_value\"}',\n",
+    "        \"name\": \"tool_name\"\n",
+    "      },\n",
+    "      \"type\": \"function\"\n",
+    "    }\n",
+    "  ]\n",
+    "}\n",
+    "```\n",
+    "LangChain implements standard interfaces for defining tools, passing them to LLMs, \n",
+    "and representing tool calls.\n",
+    "\n",
+    "## Passing tools to LLMs\n",
+    "\n",
+    "Chat models supporting tool calling features implement a `.bind_tools` method, which \n",
+    "receives a list of LangChain [tool objects](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.BaseTool.html#langchain_core.tools.BaseTool) \n",
+    "and binds them to the chat model in its expected format. Subsequent invocations of the \n",
+    "chat model will include tool schemas in its calls to the LLM.\n",
+    "\n",
+    "For example, we can define the schema for custom tools using the `@tool` decorator \n",
+    "on Python functions:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "841dca72-1b57-4a42-8e22-da4835c4cfe0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def add(a: int, b: int) -> int:\n",
+    "    \"\"\"Adds a and b.\"\"\"\n",
+    "    return a + b\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def multiply(a: int, b: int) -> int:\n",
+    "    \"\"\"Multiplies a and b.\"\"\"\n",
+    "    return a * b\n",
+    "\n",
+    "\n",
+    "tools = [add, multiply]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "48058b7d-048d-48e6-a272-3931ad7ad146",
+   "metadata": {},
+   "source": [
+    "Or below, we define the schema using Pydantic:\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "fca56328-85e4-4839-97b7-b5dc55920602",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "# Note that the docstrings here are crucial, as they will be passed along\n",
+    "# to the model along with the class name.\n",
+    "class Add(BaseModel):\n",
+    "    \"\"\"Add two integers together.\"\"\"\n",
+    "\n",
+    "    a: int = Field(..., description=\"First integer\")\n",
+    "    b: int = Field(..., description=\"Second integer\")\n",
+    "\n",
+    "\n",
+    "class Multiply(BaseModel):\n",
+    "    \"\"\"Multiply two integers together.\"\"\"\n",
+    "\n",
+    "    a: int = Field(..., description=\"First integer\")\n",
+    "    b: int = Field(..., description=\"Second integer\")\n",
+    "\n",
+    "\n",
+    "tools = [Add, Multiply]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ead9068d-11f6-42f3-a508-3c1830189947",
+   "metadata": {},
+   "source": [
+    "We can bind them to chat models as follows:\n",
+    "\n",
+    "```{=mdx}\n",
+    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
+    "\n",
+    "<ChatModelTabs\n",
+    "  customVarName=\"llm\"\n",
+    "  fireworksParams={`model=\"accounts/fireworks/models/firefunction-v1\", temperature=0`}\n",
+    "/>\n",
+    "```\n",
+    "\n",
+    "We can use the `bind_tools()` method to handle converting\n",
+    "`Multiply` to a \"tool\" and binding it to the model (i.e.,\n",
+    "passing it in each time the model is invoked)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "id": "44eb8327-a03d-4c7c-945e-30f13f455346",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# | echo: false\n",
+    "# | output: false\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "id": "af2a83ac-e43f-43ce-b107-9ed8376bfb75",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm_with_tools = llm.bind_tools(tools)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "16208230-f64f-4935-9aa1-280a91f34ba3",
+   "metadata": {},
+   "source": [
+    "## Tool calls\n",
+    "\n",
+    "If tool calls are included in a LLM response, they are attached to the corresponding \n",
+    "[message](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessage.html#langchain_core.messages.ai.AIMessage) \n",
+    "or [message chunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html#langchain_core.messages.ai.AIMessageChunk) \n",
+    "as a list of [tool call](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.tool.ToolCall.html#langchain_core.messages.tool.ToolCall) \n",
+    "objects in the `.tool_calls` attribute. A `ToolCall` is a typed dict that includes a \n",
+    "tool name, dict of argument values, and (optionally) an identifier. Messages with no \n",
+    "tool calls default to an empty list for this attribute.\n",
+    "\n",
+    "Example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "1640a4b4-c201-4b23-b257-738d854fb9fd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'Multiply',\n",
+       "  'args': {'a': 3, 'b': 12},\n",
+       "  'id': 'call_1Tdp5wUXbYQzpkBoagGXqUTo'},\n",
+       " {'name': 'Add',\n",
+       "  'args': {'a': 11, 'b': 49},\n",
+       "  'id': 'call_k9v09vYioS3X0Qg35zESuUKI'}]"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "query = \"What is 3 * 12? Also, what is 11 + 49?\"\n",
+    "\n",
+    "llm_with_tools.invoke(query).tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ac3ff0fe-5119-46b8-a578-530245bff23f",
+   "metadata": {},
+   "source": [
+    "The `.tool_calls` attribute should contain valid tool calls. Note that on occasion, \n",
+    "model providers may output malformed tool calls (e.g., arguments that are not \n",
+    "valid JSON). When parsing fails in these cases, instances \n",
+    "of [InvalidToolCall](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.tool.InvalidToolCall.html#langchain_core.messages.tool.InvalidToolCall) \n",
+    "are populated in the `.invalid_tool_calls` attribute. An `InvalidToolCall` can have \n",
+    "a name, string arguments, identifier, and error message.\n",
+    "\n",
+    "If desired, [output parsers](/docs/modules/model_io/output_parsers) can further \n",
+    "process the output. For example, we can convert back to the original Pydantic class:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "ca15fcad-74fe-4109-a1b1-346c3eefe238",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Multiply(a=3, b=12), Add(a=11, b=49)]"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.output_parsers.openai_tools import PydanticToolsParser\n",
+    "\n",
+    "chain = llm_with_tools | PydanticToolsParser(tools=[Multiply, Add])\n",
+    "chain.invoke(query)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0ba3505d-f405-43ba-93c4-7fbd84f6464b",
+   "metadata": {},
+   "source": [
+    "### Streaming\n",
+    "\n",
+    "When tools are called in a streaming context, \n",
+    "[message chunks](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html#langchain_core.messages.ai.AIMessageChunk) \n",
+    "will be populated with [tool call chunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.tool.ToolCallChunk.html#langchain_core.messages.tool.ToolCallChunk) \n",
+    "objects in a list via the `.tool_call_chunks` attribute. A `ToolCallChunk` includes \n",
+    "optional string fields for the tool `name`, `args`, and `id`, and includes an optional \n",
+    "integer field `index` that can be used to join chunks together. Fields are optional \n",
+    "because portions of a tool call may be streamed across different chunks (e.g., a chunk \n",
+    "that includes a substring of the arguments may have null values for the tool name and id).\n",
+    "\n",
+    "Because message chunks inherit from their parent message class, an \n",
+    "[AIMessageChunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html#langchain_core.messages.ai.AIMessageChunk) \n",
+    "with tool call chunks will also include `.tool_calls` and `.invalid_tool_calls` fields. \n",
+    "These fields are parsed best-effort from the message's tool call chunks.\n",
+    "\n",
+    "Note that not all providers currently support streaming for tool calls.\n",
+    "\n",
+    "Example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "4f54a0de-74c7-4f2d-86c5-660aed23840d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[]\n",
+      "[{'name': 'Multiply', 'args': '', 'id': 'call_d39MsxKM5cmeGJOoYKdGBgzc', 'index': 0}]\n",
+      "[{'name': None, 'args': '{\"a\"', 'id': None, 'index': 0}]\n",
+      "[{'name': None, 'args': ': 3, ', 'id': None, 'index': 0}]\n",
+      "[{'name': None, 'args': '\"b\": 1', 'id': None, 'index': 0}]\n",
+      "[{'name': None, 'args': '2}', 'id': None, 'index': 0}]\n",
+      "[{'name': 'Add', 'args': '', 'id': 'call_QJpdxD9AehKbdXzMHxgDMMhs', 'index': 1}]\n",
+      "[{'name': None, 'args': '{\"a\"', 'id': None, 'index': 1}]\n",
+      "[{'name': None, 'args': ': 11,', 'id': None, 'index': 1}]\n",
+      "[{'name': None, 'args': ' \"b\": ', 'id': None, 'index': 1}]\n",
+      "[{'name': None, 'args': '49}', 'id': None, 'index': 1}]\n",
+      "[]\n"
+     ]
+    }
+   ],
+   "source": [
+    "async for chunk in llm_with_tools.astream(query):\n",
+    "    print(chunk.tool_call_chunks)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "55046320-3466-4ec1-a1f8-336234ba9019",
+   "metadata": {},
+   "source": [
+    "Note that adding message chunks will merge their corresponding tool call chunks. This is the principle by which LangChain's various [tool output parsers](/docs/modules/model_io/output_parsers/types/openai_tools/) support streaming.\n",
+    "\n",
+    "For example, below we accumulate tool call chunks:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "0a944af0-eedd-43c8-8ff3-f4301f129d9b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[]\n",
+      "[{'name': 'Multiply', 'args': '', 'id': 'call_erKtz8z3e681cmxYKbRof0NS', 'index': 0}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\"', 'id': 'call_erKtz8z3e681cmxYKbRof0NS', 'index': 0}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, ', 'id': 'call_erKtz8z3e681cmxYKbRof0NS', 'index': 0}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 1', 'id': 'call_erKtz8z3e681cmxYKbRof0NS', 'index': 0}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_erKtz8z3e681cmxYKbRof0NS', 'index': 0}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_erKtz8z3e681cmxYKbRof0NS', 'index': 0}, {'name': 'Add', 'args': '', 'id': 'call_tYHYdEV2YBvzDcSCiFCExNvw', 'index': 1}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_erKtz8z3e681cmxYKbRof0NS', 'index': 0}, {'name': 'Add', 'args': '{\"a\"', 'id': 'call_tYHYdEV2YBvzDcSCiFCExNvw', 'index': 1}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_erKtz8z3e681cmxYKbRof0NS', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11,', 'id': 'call_tYHYdEV2YBvzDcSCiFCExNvw', 'index': 1}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_erKtz8z3e681cmxYKbRof0NS', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11, \"b\": ', 'id': 'call_tYHYdEV2YBvzDcSCiFCExNvw', 'index': 1}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_erKtz8z3e681cmxYKbRof0NS', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11, \"b\": 49}', 'id': 'call_tYHYdEV2YBvzDcSCiFCExNvw', 'index': 1}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_erKtz8z3e681cmxYKbRof0NS', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11, \"b\": 49}', 'id': 'call_tYHYdEV2YBvzDcSCiFCExNvw', 'index': 1}]\n"
+     ]
+    }
+   ],
+   "source": [
+    "first = True\n",
+    "async for chunk in llm_with_tools.astream(query):\n",
+    "    if first:\n",
+    "        gathered = chunk\n",
+    "        first = False\n",
+    "    else:\n",
+    "        gathered = gathered + chunk\n",
+    "\n",
+    "    print(gathered.tool_call_chunks)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "db4e3e3a-3553-44dc-bd31-149c0981a06a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'str'>\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(type(gathered.tool_call_chunks[0][\"args\"]))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "95e92826-6e55-4684-9498-556f357f73ac",
+   "metadata": {},
+   "source": [
+    "And below we accumulate tool calls to demonstrate partial parsing:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "e9402bde-d4b5-4564-a99e-f88c9b46b28a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[]\n",
+      "[]\n",
+      "[{'name': 'Multiply', 'args': {}, 'id': 'call_BXqUtt6jYCwR1DguqpS2ehP0'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3}, 'id': 'call_BXqUtt6jYCwR1DguqpS2ehP0'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 1}, 'id': 'call_BXqUtt6jYCwR1DguqpS2ehP0'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_BXqUtt6jYCwR1DguqpS2ehP0'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_BXqUtt6jYCwR1DguqpS2ehP0'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_BXqUtt6jYCwR1DguqpS2ehP0'}, {'name': 'Add', 'args': {}, 'id': 'call_UjSHJKROSAw2BDc8cp9cSv4i'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_BXqUtt6jYCwR1DguqpS2ehP0'}, {'name': 'Add', 'args': {'a': 11}, 'id': 'call_UjSHJKROSAw2BDc8cp9cSv4i'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_BXqUtt6jYCwR1DguqpS2ehP0'}, {'name': 'Add', 'args': {'a': 11}, 'id': 'call_UjSHJKROSAw2BDc8cp9cSv4i'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_BXqUtt6jYCwR1DguqpS2ehP0'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_UjSHJKROSAw2BDc8cp9cSv4i'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_BXqUtt6jYCwR1DguqpS2ehP0'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_UjSHJKROSAw2BDc8cp9cSv4i'}]\n"
+     ]
+    }
+   ],
+   "source": [
+    "first = True\n",
+    "async for chunk in llm_with_tools.astream(query):\n",
+    "    if first:\n",
+    "        gathered = chunk\n",
+    "        first = False\n",
+    "    else:\n",
+    "        gathered = gathered + chunk\n",
+    "\n",
+    "    print(gathered.tool_calls)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "8c2f21cc-0c6d-416a-871f-e854621c96e2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'dict'>\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(type(gathered.tool_calls[0][\"args\"]))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "97a0c977-0c3c-4011-b49b-db98c609d0ce",
+   "metadata": {},
+   "source": [
+    "## Passing tool outputs to model\n",
+    "\n",
+    "If we're using the model-generated tool invocations to actually call tools and want to pass the tool results back to the model, we can do so using `ToolMessage`s."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 117,
+   "id": "48049192-be28-42ab-9a44-d897924e67cd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='What is 3 * 12? Also, what is 11 + 49?'),\n",
+       " AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_K5DsWEmgt6D08EI9AFu9NaL1', 'function': {'arguments': '{\"a\": 3, \"b\": 12}', 'name': 'Multiply'}, 'type': 'function'}, {'id': 'call_qywVrsplg0ZMv7LHYYMjyG81', 'function': {'arguments': '{\"a\": 11, \"b\": 49}', 'name': 'Add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 50, 'prompt_tokens': 105, 'total_tokens': 155}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-1a0b8cdd-9221-4d94-b2ed-5701f67ce9fe-0', tool_calls=[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_K5DsWEmgt6D08EI9AFu9NaL1'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_qywVrsplg0ZMv7LHYYMjyG81'}]),\n",
+       " ToolMessage(content='36', tool_call_id='call_K5DsWEmgt6D08EI9AFu9NaL1'),\n",
+       " ToolMessage(content='60', tool_call_id='call_qywVrsplg0ZMv7LHYYMjyG81')]"
+      ]
+     },
+     "execution_count": 117,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import HumanMessage, ToolMessage\n",
+    "\n",
+    "messages = [HumanMessage(query)]\n",
+    "ai_msg = llm_with_tools.invoke(messages)\n",
+    "messages.append(ai_msg)\n",
+    "for tool_call in ai_msg.tool_calls:\n",
+    "    selected_tool = {\"add\": add, \"multiply\": multiply}[tool_call[\"name\"].lower()]\n",
+    "    tool_output = selected_tool.invoke(tool_call[\"args\"])\n",
+    "    messages.append(ToolMessage(tool_output, tool_call_id=tool_call[\"id\"]))\n",
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 118,
+   "id": "611e0f36-d736-48d1-bca1-1cec51d223f3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='3 * 12 is 36 and 11 + 49 is 60.', response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 171, 'total_tokens': 189}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'stop', 'logprobs': None}, id='run-a6c8093c-b16a-4c92-8308-7c9ac998118c-0')"
+      ]
+     },
+     "execution_count": 118,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm_with_tools.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a5937498-d6fe-400a-b192-ef35c314168e",
+   "metadata": {},
+   "source": [
+    "## Few-shot prompting\n",
+    "\n",
+    "For more complex tool use it's very useful to add few-shot examples to the prompt. We can do this by adding `AIMessage`s with `ToolCall`s and corresponding `ToolMessage`s to our prompt.\n",
+    "\n",
+    "For example, even with some special instructions our model can get tripped up by order of operations:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 112,
+   "id": "5ef2e7c3-0925-49da-ab8f-e42c4fa40f29",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'Multiply',\n",
+       "  'args': {'a': 119, 'b': 8},\n",
+       "  'id': 'call_Dl3FXRVkQCFW4sUNYOe4rFr7'},\n",
+       " {'name': 'Add',\n",
+       "  'args': {'a': 952, 'b': -20},\n",
+       "  'id': 'call_n03l4hmka7VZTCiP387Wud2C'}]"
+      ]
+     },
+     "execution_count": 112,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm_with_tools.invoke(\n",
+    "    \"Whats 119 times 8 minus 20. Don't do any math yourself, only use tools for math. Respect order of operations\"\n",
+    ").tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a5249069-b5f8-40ac-ae74-30d67c4e9168",
+   "metadata": {},
+   "source": [
+    "The model shouldn't be trying to add anything yet, since it technically can't know the results of 119 * 8 yet.\n",
+    "\n",
+    "By adding a prompt with some examples we can correct this behavior:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 107,
+   "id": "7b2e8b19-270f-4e1a-8be7-7aad704c1cf4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'Multiply',\n",
+       "  'args': {'a': 119, 'b': 8},\n",
+       "  'id': 'call_MoSgwzIhPxhclfygkYaKIsGZ'}]"
+      ]
+     },
+     "execution_count": 107,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import AIMessage\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "\n",
+    "examples = [\n",
+    "    HumanMessage(\n",
+    "        \"What's the product of 317253 and 128472 plus four\", name=\"example_user\"\n",
+    "    ),\n",
+    "    AIMessage(\n",
+    "        \"\",\n",
+    "        name=\"example_assistant\",\n",
+    "        tool_calls=[\n",
+    "            {\"name\": \"Multiply\", \"args\": {\"x\": 317253, \"y\": 128472}, \"id\": \"1\"}\n",
+    "        ],\n",
+    "    ),\n",
+    "    ToolMessage(\"16505054784\", tool_call_id=\"1\"),\n",
+    "    AIMessage(\n",
+    "        \"\",\n",
+    "        name=\"example_assistant\",\n",
+    "        tool_calls=[{\"name\": \"Add\", \"args\": {\"x\": 16505054784, \"y\": 4}, \"id\": \"2\"}],\n",
+    "    ),\n",
+    "    ToolMessage(\"16505054788\", tool_call_id=\"2\"),\n",
+    "    AIMessage(\n",
+    "        \"The product of 317253 and 128472 plus four is 16505054788\",\n",
+    "        name=\"example_assistant\",\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "system = \"\"\"You are bad at math but are an expert at using a calculator. \n",
+    "\n",
+    "Use past tool usage as an example of how to correctly use the tools.\"\"\"\n",
+    "few_shot_prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", system),\n",
+    "        *examples,\n",
+    "        (\"human\", \"{query}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = {\"query\": RunnablePassthrough()} | few_shot_prompt | llm_with_tools\n",
+    "chain.invoke(\"Whats 119 times 8 minus 20\").tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "19160e3e-3eb5-4e9a-ae56-74a2dce0af32",
+   "metadata": {},
+   "source": [
+    "Seems like we get the correct output this time.\n",
+    "\n",
+    "Here's what the [LangSmith trace](https://smith.langchain.com/public/f70550a1-585f-4c9d-a643-13148ab1616f/r) looks like."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "020cfd3b-0838-49d0-96bb-7cd919921833",
+   "metadata": {},
+   "source": [
+    "## Next steps\n",
+    "\n",
+    "- **Output parsing**: See [OpenAI Tools output\n",
+    "    parsers](/docs/modules/model_io/output_parsers/types/openai_tools/)\n",
+    "    and [OpenAI Functions output\n",
+    "    parsers](/docs/modules/model_io/output_parsers/types/openai_functions/)\n",
+    "    to learn about extracting the function calling API responses into\n",
+    "    various formats.\n",
+    "- **Structured output chains**: [Some models have constructors](/docs/modules/model_io/chat/structured_output/) that\n",
+    "    handle creating a structured output chain for you.\n",
+    "- **Tool use**: See how to construct chains and agents that\n",
+    "    call the invoked tools in [these\n",
+    "    guides](/docs/use_cases/tool_use/)."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv-2",
+   "language": "python",
+   "name": "poetry-venv-2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/modules/model_io/chat/function_calling.mdx

@@ -1,311 +0,0 @@
----
-sidebar_position: 2
-title: Function calling
----
-
-# Function calling
-
-A growing number of chat models, like
-[OpenAI](https://platform.openai.com/docs/guides/function-calling),
-[Gemini](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/function-calling),
-etc., have a function-calling API that lets you describe functions and
-their arguments, and have the model return a JSON object with a function
-to invoke and the inputs to that function. Function-calling is extremely
-useful for building [tool-using chains and
-agents](/docs/use_cases/tool_use/), and for getting
-structured outputs from models more generally.
-
-LangChain comes with a number of utilities to make function-calling
-easy. Namely, it comes with:
-
-- simple syntax for binding functions to models
-- converters for formatting various types of objects to the expected
-  function schemas
-- output parsers for extracting the function invocations from API
-  responses
-- chains for getting structured outputs from a model, built on top of
-  function calling
-
-We’ll focus here on the first two points. For a detailed guide on output
-parsing check out the [OpenAI Tools output
-parsers](/docs/modules/model_io/output_parsers/types/openai_tools/)
-and to see the structured output chains check out the [Structured output
-guide](/docs/modules/model_io/chat/structured_output/).
-
-Before getting started make sure you have `langchain-core` installed.
-
-```python
-%pip install -qU langchain-core langchain-openai
-```
-
-```python
-import getpass
-import os
-```
-
-## Binding functions
-
-A number of models implement helper methods that will take care of
-formatting and binding different function-like objects to the model.
-Let’s take a look at how we might take the following Pydantic function
-schema and get different models to invoke it:
-
-```python
-from langchain_core.pydantic_v1 import BaseModel, Field
-
-
-# Note that the docstrings here are crucial, as they will be passed along
-# to the model along with the class name.
-class Multiply(BaseModel):
-    """Multiply two integers together."""
-
-    a: int = Field(..., description="First integer")
-    b: int = Field(..., description="Second integer")
-```
-
-import Tabs from "@theme/Tabs";
-import TabItem from "@theme/TabItem";
-
-import ChatModelTabs from "@theme/ChatModelTabs";
-
-<ChatModelTabs
-  customVarName="llm"
-  fireworksParams={`model="accounts/fireworks/models/firefunction-v1", temperature=0`}
-  hideGoogle={true}
-  hideAnthropic={true}
-/>
-
-We can use the `bind_tools()` method to handle converting
-`Multiply` to a "function" and binding it to the model (i.e.,
-passing it in each time the model is invoked).
-
-```python
-llm_with_tools = llm.bind_tools([Multiply])
-llm_with_tools.invoke("what's 3 * 12")
-```
-
-```text
-AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_Q8ZQ97Qrj5zalugSkYMGV1Uo', 'function': {'arguments': '{"a":3,"b":12}', 'name': 'Multiply'}, 'type': 'function'}]})
-```
-
-We can add a tool parser to extract the tool calls from the generated
-message to JSON:
-
-```python
-from langchain_core.output_parsers.openai_tools import JsonOutputToolsParser
-
-tool_chain = llm_with_tools | JsonOutputToolsParser()
-tool_chain.invoke("what's 3 * 12")
-```
-
-```text
-[{'type': 'Multiply', 'args': {'a': 3, 'b': 12}}]
-```
-
-Or back to the original Pydantic class:
-
-```python
-from langchain_core.output_parsers.openai_tools import PydanticToolsParser
-
-tool_chain = llm_with_tools | PydanticToolsParser(tools=[Multiply])
-tool_chain.invoke("what's 3 * 12")
-```
-
-```text
-[Multiply(a=3, b=12)]
-```
-
-If our model isn’t using the tool, as is the case here, we can force
-tool usage by specifying `tool_choice="any"` or by specifying the name
-of the specific tool we want used:
-
-```python
-llm_with_tools = llm.bind_tools([Multiply], tool_choice="Multiply")
-llm_with_tools.invoke("what's 3 * 12")
-```
-
-```text
-AIMessage(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_qIP2bJugb67LGvc6Zhwkvfqc', 'type': 'function', 'function': {'name': 'Multiply', 'arguments': '{"a": 3, "b": 12}'}}]})
-```
-
-If we wanted to force that a tool is used (and that it is used only
-once), we can set the `tool_choice` argument to the name of the tool:
-
-```python
-llm_with_multiply = llm.bind_tools([Multiply], tool_choice="Multiply")
-llm_with_multiply.invoke(
-    "make up some numbers if you really want but I'm not forcing you"
-)
-```
-
-```text
-AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_f3DApOzb60iYjTfOhVFhDRMI', 'function': {'arguments': '{"a":5,"b":10}', 'name': 'Multiply'}, 'type': 'function'}]})
-```
-
-For more see the [ChatOpenAI API
-reference](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html#langchain_openai.chat_models.base.ChatOpenAI.bind_tools).
-
-## Defining functions schemas
-
-In case you need to access function schemas directly, LangChain has a built-in converter that can turn
-Python functions, Pydantic classes, and LangChain Tools into the OpenAI format JSON schema:
-
-### Python function
-
-```python
-import json
-
-from langchain_core.utils.function_calling import convert_to_openai_tool
-
-
-def multiply(a: int, b: int) -> int:
-    """Multiply two integers together.
-
-    Args:
-        a: First integer
-        b: Second integer
-    """
-    return a * b
-
-
-print(json.dumps(convert_to_openai_tool(multiply), indent=2))
-```
-
-```text
-{
-  "type": "function",
-  "function": {
-    "name": "multiply",
-    "description": "Multiply two integers together.",
-    "parameters": {
-      "type": "object",
-      "properties": {
-        "a": {
-          "type": "integer",
-          "description": "First integer"
-        },
-        "b": {
-          "type": "integer",
-          "description": "Second integer"
-        }
-      },
-      "required": [
-        "a",
-        "b"
-      ]
-    }
-  }
-}
-```
-
-### Pydantic class
-
-```python
-from langchain_core.pydantic_v1 import BaseModel, Field
-
-
-class multiply(BaseModel):
-    """Multiply two integers together."""
-
-    a: int = Field(..., description="First integer")
-    b: int = Field(..., description="Second integer")
-
-
-print(json.dumps(convert_to_openai_tool(multiply), indent=2))
-```
-
-```text
-{
-  "type": "function",
-  "function": {
-    "name": "multiply",
-    "description": "Multiply two integers together.",
-    "parameters": {
-      "type": "object",
-      "properties": {
-        "a": {
-          "description": "First integer",
-          "type": "integer"
-        },
-        "b": {
-          "description": "Second integer",
-          "type": "integer"
-        }
-      },
-      "required": [
-        "a",
-        "b"
-      ]
-    }
-  }
-}
-```
-
-### LangChain Tool
-
-```python
-from typing import Any, Type
-
-from langchain_core.tools import BaseTool
-
-
-class MultiplySchema(BaseModel):
-    """Multiply tool schema."""
-
-    a: int = Field(..., description="First integer")
-    b: int = Field(..., description="Second integer")
-
-
-class Multiply(BaseTool):
-    args_schema: Type[BaseModel] = MultiplySchema
-    name: str = "multiply"
-    description: str = "Multiply two integers together."
-
-    def _run(self, a: int, b: int, **kwargs: Any) -> Any:
-        return a * b
-
-
-# Note: we're passing in a Multiply object not the class itself.
-print(json.dumps(convert_to_openai_tool(Multiply()), indent=2))
-```
-
-```text
-{
-  "type": "function",
-  "function": {
-    "name": "multiply",
-    "description": "Multiply two integers together.",
-    "parameters": {
-      "type": "object",
-      "properties": {
-        "a": {
-          "description": "First integer",
-          "type": "integer"
-        },
-        "b": {
-          "description": "Second integer",
-          "type": "integer"
-        }
-      },
-      "required": [
-        "a",
-        "b"
-      ]
-    }
-  }
-}
-```
-
-## Next steps
-
-- **Output parsing**: See [OpenAI Tools output
-    parsers](/docs/modules/model_io/output_parsers/types/openai_tools/)
-    and [OpenAI Functions output
-    parsers](/docs/modules/model_io/output_parsers/types/openai_functions/)
-    to learn about extracting the function calling API responses into
-    various formats.
-- **Structured output chains**: [Some models have constructors](/docs/modules/model_io/chat/structured_output/) that
-    handle creating a structured output chain for you.
-- **Tool use**: See how to construct chains and agents that actually
-    call the invoked tools in [these
-    guides](/docs/use_cases/tool_use/).

docs/docs/modules/model_io/chat/quick_start.ipynb

@@ -52,10 +52,10 @@
    "source": [
     "```{=mdx}\n",
     "<ChatModelTabs\n",
-    "  openaiParams={`model=\"gpt-3.5-turbo-0125\", openai_api_key=\"...\"`}\n",
-    "  anthropicParams={`model=\"claude-3-sonnet-20240229\", anthropic_api_key=\"...\"`}\n",
-    "  fireworksParams={`model=\"accounts/fireworks/models/mixtral-8x7b-instruct\", fireworks_api_key=\"...\"`}\n",
-    "  mistralParams={`model=\"mistral-large-latest\", mistral_api_key=\"...\"`}\n",
+    "  anthropicParams={`model=\"claude-3-sonnet-20240229\", api_key=\"...\"`}\n",
+    "  openaiParams={`model=\"gpt-3.5-turbo-0125\", api_key=\"...\"`}\n",
+    "  mistralParams={`model=\"mistral-large-latest\", api_key=\"...\"`}\n",
+    "  fireworksParams={`model=\"accounts/fireworks/models/mixtral-8x7b-instruct\", api_key=\"...\"`}\n",
     "  googleParams={`model=\"gemini-pro\", google_api_key=\"...\"`}\n",
     "  togetherParams={`, together_api_key=\"...\"`}\n",
     "  customVarName=\"chat\"\n",

docs/docs/modules/model_io/chat/structured_output.ipynb

@@ -66,7 +66,9 @@
    "source": [
     "## OpenAI\n",
     "\n",
-    "OpenAI exposes a few different ways to get structured outputs."
+    "OpenAI exposes a few different ways to get structured outputs. \n",
+    "\n",
+    "[API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html#langchain_openai.chat_models.base.ChatOpenAI.with_structured_output)"
    ]
   },
   {
@@ -96,8 +98,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model = ChatOpenAI()\n",
-    "model_with_structure = model.with_structured_output(Joke)"
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "structured_llm = model.with_structured_output(Joke)"
    ]
   },
   {
@@ -118,7 +120,7 @@
     }
    ],
    "source": [
-    "model_with_structure.invoke(\"Tell me a joke about cats\")"
+    "structured_llm.invoke(\"Tell me a joke about cats\")"
    ]
   },
   {
@@ -138,7 +140,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model_with_structure = model.with_structured_output(Joke, method=\"json_mode\")"
+    "structured_llm = model.with_structured_output(Joke, method=\"json_mode\")"
    ]
   },
   {
@@ -159,7 +161,7 @@
     }
    ],
    "source": [
-    "model_with_structure.invoke(\n",
+    "structured_llm.invoke(\n",
     "    \"Tell me a joke about cats, respond in JSON with `setup` and `punchline` keys\"\n",
     ")"
    ]
@@ -171,7 +173,9 @@
    "source": [
     "## Fireworks\n",
     "\n",
-    "[Fireworks](https://fireworks.ai/) similarly supports function calling and JSON mode for select models."
+    "[Fireworks](https://fireworks.ai/) similarly supports function calling and JSON mode for select models.\n",
+    "\n",
+    "[API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_fireworks.chat_models.ChatFireworks.html#langchain_fireworks.chat_models.ChatFireworks.with_structured_output)"
    ]
   },
   {
@@ -202,7 +206,7 @@
    "outputs": [],
    "source": [
     "model = ChatFireworks(model=\"accounts/fireworks/models/firefunction-v1\")\n",
-    "model_with_structure = model.with_structured_output(Joke)"
+    "structured_llm = model.with_structured_output(Joke)"
    ]
   },
   {
@@ -223,7 +227,7 @@
     }
    ],
    "source": [
-    "model_with_structure.invoke(\"Tell me a joke about cats\")"
+    "structured_llm.invoke(\"Tell me a joke about cats\")"
    ]
   },
   {
@@ -243,7 +247,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model_with_structure = model.with_structured_output(Joke, method=\"json_mode\")"
+    "structured_llm = model.with_structured_output(Joke, method=\"json_mode\")"
    ]
   },
   {
@@ -264,7 +268,7 @@
     }
    ],
    "source": [
-    "model_with_structure.invoke(\n",
+    "structured_llm.invoke(\n",
     "    \"Tell me a joke about dogs, respond in JSON with `setup` and `punchline` keys\"\n",
     ")"
    ]
@@ -276,7 +280,9 @@
    "source": [
     "## Mistral\n",
     "\n",
-    "We also support structured output with Mistral models, although we only support function calling."
+    "We also support structured output with Mistral models, although we only support function calling.\n",
+    "\n",
+    "[API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_mistralai.chat_models.ChatMistralAI.html#langchain_mistralai.chat_models.ChatMistralAI.with_structured_output)"
    ]
   },
   {
@@ -297,7 +303,7 @@
    "outputs": [],
    "source": [
     "model = ChatMistralAI(model=\"mistral-large-latest\")\n",
-    "model_with_structure = model.with_structured_output(Joke)"
+    "structured_llm = model.with_structured_output(Joke)"
    ]
   },
   {
@@ -307,7 +313,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model_with_structure.invoke(\"Tell me a joke about cats\")"
+    "structured_llm.invoke(\"Tell me a joke about cats\")"
    ]
   },
   {
@@ -344,7 +350,7 @@
     "    api_key=os.environ[\"TOGETHER_API_KEY\"],\n",
     "    model=\"mistralai/Mixtral-8x7B-Instruct-v0.1\",\n",
     ")\n",
-    "model_with_structure = model.with_structured_output(Joke)"
+    "structured_llm = model.with_structured_output(Joke)"
    ]
   },
   {
@@ -365,7 +371,7 @@
     }
    ],
    "source": [
-    "model_with_structure.invoke(\"Tell me a joke about cats\")"
+    "structured_llm.invoke(\"Tell me a joke about cats\")"
    ]
   },
   {
@@ -375,7 +381,9 @@
    "source": [
     "## Groq\n",
     "\n",
-    "Groq provides an OpenAI-compatible function calling API"
+    "Groq provides an OpenAI-compatible function calling API.\n",
+    "\n",
+    "[API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_groq.chat_models.ChatGroq.html#langchain_groq.chat_models.ChatGroq.with_structured_output)"
    ]
   },
   {
@@ -415,7 +423,7 @@
    ],
    "source": [
     "model = ChatGroq()\n",
-    "model_with_structure = model.with_structured_output(Joke)"
+    "structured_llm = model.with_structured_output(Joke)"
    ]
   },
   {
@@ -436,7 +444,7 @@
     }
    ],
    "source": [
-    "model_with_structure.invoke(\"Tell me a joke about cats\")"
+    "structured_llm.invoke(\"Tell me a joke about cats\")"
    ]
   },
   {
@@ -456,7 +464,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model_with_structure = model.with_structured_output(Joke, method=\"json_mode\")"
+    "structured_llm = model.with_structured_output(Joke, method=\"json_mode\")"
    ]
   },
   {
@@ -477,7 +485,7 @@
     }
    ],
    "source": [
-    "model_with_structure.invoke(\n",
+    "structured_llm.invoke(\n",
     "    \"Tell me a joke about cats, respond in JSON with `setup` and `punchline` keys\"\n",
     ")"
    ]
@@ -489,7 +497,9 @@
    "source": [
     "## Anthropic\n",
     "\n",
-    "Anthropic's tool-calling API can be used for structuring outputs. Note that there is currently no way to force a tool-call via the API, so prompting the model correctly is still important."
+    "Anthropic's tool-calling API can be used for structuring outputs. Note that there is currently no way to force a tool-call via the API, so prompting the model correctly is still important.\n",
+    "\n",
+    "[API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_anthropic.chat_models.ChatAnthropic.html#langchain_anthropic.chat_models.ChatAnthropic.with_structured_output)"
    ]
   },
   {
@@ -512,19 +522,54 @@
    "source": [
     "from langchain_anthropic import ChatAnthropic\n",
     "\n",
-    "model = ChatAnthropic(\n",
-    "    model=\"claude-3-opus-20240229\",\n",
-    ")\n",
-    "model_with_structure = model.with_structured_output(Joke)\n",
-    "model_with_structure.invoke(\"Tell me a joke about cats\")"
+    "model = ChatAnthropic(model=\"claude-3-opus-20240229\", temperature=0)\n",
+    "structured_llm = model.with_structured_output(Joke)\n",
+    "structured_llm.invoke(\"Tell me a joke about cats. Make sure to call the Joke function.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6c797e2d-3115-4ca2-9c2f-e853bdc7956d",
+   "metadata": {},
+   "source": [
+    "# Vertex AI\n",
+    "\n",
+    "Google's Gemini models support [function-calling](https://ai.google.dev/docs/function_calling), which we can access via Vertex AI and use for structuring outputs.\n",
+    "\n",
+    "[API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_google_vertexai.chat_models.ChatVertexAI.html#langchain_google_vertexai.chat_models.ChatVertexAI.with_structured_output)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "24421189-02bf-4589-a91a-197584c4a696",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Joke(setup='A cat-ch', punchline='What do you call a cat that loves to play fetch?')"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_google_vertexai import ChatVertexAI\n",
+    "\n",
+    "llm = ChatVertexAI(model=\"gemini-pro\", temperature=0)\n",
+    "structured_llm = llm.with_structured_output(Joke)\n",
+    "structured_llm.invoke(\"Tell me a joke about cats\")"
    ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "poetry-venv-2",
    "language": "python",
-   "name": "python3"
+   "name": "poetry-venv-2"
   },
   "language_info": {
    "codemirror_mode": {

docs/docs/modules/model_io/chat/token_usage_tracking.ipynb

@@ -30,7 +30,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm = ChatOpenAI(model_name=\"gpt-4\")"
+    "llm = ChatOpenAI(model=\"gpt-4\")"
    ]
   },
   {

docs/docs/modules/model_io/index.mdx

@@ -63,11 +63,11 @@ llm = OpenAI()
 chat_model = ChatOpenAI(model="gpt-3.5-turbo-0125")
 ```
 
-If you'd prefer not to set an environment variable you can pass the key in directly via the `openai_api_key` named parameter when initiating the OpenAI LLM class:
+If you'd prefer not to set an environment variable you can pass the key in directly via the `api_key` named parameter when initiating the OpenAI LLM class:
 
 ```python
 from langchain_openai import ChatOpenAI
-llm = ChatOpenAI(openai_api_key="...")
+llm = ChatOpenAI(api_key="...")
 ```
 
 Both `llm` and `chat_model` are objects that represent configuration for a particular model. 
@@ -158,10 +158,10 @@ from langchain_anthropic import ChatAnthropic
 chat_model = ChatAnthropic(model="claude-3-sonnet-20240229", temperature=0.2, max_tokens=1024)
 ```
 
-If you'd prefer not to set an environment variable you can pass the key in directly via the `anthropic_api_key` named parameter when initiating the Anthropic Chat Model class:
+If you'd prefer not to set an environment variable you can pass the key in directly via the `api_key` named parameter when initiating the Anthropic Chat Model class:
 
 ```python
-chat_model = ChatAnthropic(anthropic_api_key="...")
+chat_model = ChatAnthropic(api_key="...")
 ```
 
   </TabItem>

docs/docs/modules/model_io/llms/custom_llm.ipynb

@@ -9,44 +9,73 @@
     "\n",
     "This notebook goes over how to create a custom LLM wrapper, in case you want to use your own LLM or a different wrapper than one that is supported in LangChain.\n",
     "\n",
+    "Wrapping your LLM with the standard `LLM` interface allow you to use your LLM in existing LangChain programs with minimal code modifications!\n",
+    "\n",
+    "As an bonus, your LLM will automatically become a LangChain `Runnable` and will benefit from some optimizations out of the box, async support, the `astream_events` API, etc.\n",
+    "\n",
+    "## Implementation\n",
+    "\n",
     "There are only two required things that a custom LLM needs to implement:\n",
     "\n",
-    "- A `_call` method that takes in a string, some optional stop words, and returns a string.\n",
-    "- A `_llm_type` property that returns a string. Used for logging purposes only.\n",
     "\n",
-    "There is a second optional thing it can implement:\n",
+    "| Method        | Description                                                               |\n",
+    "|---------------|---------------------------------------------------------------------------|\n",
+    "| `_call`       | Takes in a string and some optional stop words, and returns a string. Used by `invoke`. |\n",
+    "| `_llm_type`   | A property that returns a string, used for logging purposes only.        \n",
     "\n",
-    "- An `_identifying_params` property that is used to help with printing of this class. Should return a dictionary.\n",
     "\n",
-    "Let's implement a very simple custom LLM that just returns the first n characters of the input."
+    "\n",
+    "Optional implementations: \n",
+    "\n",
+    "\n",
+    "| Method    | Description                                                                                               |\n",
+    "|----------------------|-----------------------------------------------------------------------------------------------------------|\n",
+    "| `_identifying_params` | Used to help with identifying the model and printing the LLM; should return a dictionary. This is a **@property**.                 |\n",
+    "| `_acall`              | Provides an async native implementation of `_call`, used by `ainvoke`.                                    |\n",
+    "| `_stream`             | Method to stream the output token by token.                                                               |\n",
+    "| `_astream`            | Provides an async native implementation of `_stream`; in newer LangChain versions, defaults to `_stream`. |\n",
+    "\n",
+    "\n",
+    "\n",
+    "Let's implement a simple custom LLM that just returns the first n characters of the input."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "id": "a65696a0",
-   "metadata": {},
+   "execution_count": 1,
+   "id": "2e9bb32f-6fd1-46ac-b32f-d175663710c0",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
-    "from typing import Any, List, Mapping, Optional\n",
+    "from typing import Any, Dict, Iterator, List, Mapping, Optional\n",
     "\n",
     "from langchain_core.callbacks.manager import CallbackManagerForLLMRun\n",
-    "from langchain_core.language_models.llms import LLM"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "d5ceff02",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "class CustomLLM(LLM):\n",
-    "    n: int\n",
+    "from langchain_core.language_models.llms import LLM\n",
+    "from langchain_core.outputs import GenerationChunk\n",
     "\n",
-    "    @property\n",
-    "    def _llm_type(self) -> str:\n",
-    "        return \"custom\"\n",
+    "\n",
+    "class CustomLLM(LLM):\n",
+    "    \"\"\"A custom chat model that echoes the first `n` characters of the input.\n",
+    "\n",
+    "    When contributing an implementation to LangChain, carefully document\n",
+    "    the model including the initialization parameters, include\n",
+    "    an example of how to initialize the model and include any relevant\n",
+    "    links to the underlying models documentation or API.\n",
+    "\n",
+    "    Example:\n",
+    "\n",
+    "        .. code-block:: python\n",
+    "\n",
+    "            model = CustomChatModel(n=2)\n",
+    "            result = model.invoke([HumanMessage(content=\"hello\")])\n",
+    "            result = model.batch([[HumanMessage(content=\"hello\")],\n",
+    "                                 [HumanMessage(content=\"world\")]])\n",
+    "    \"\"\"\n",
+    "\n",
+    "    n: int\n",
+    "    \"\"\"The number of characters from the last message of the prompt to be echoed.\"\"\"\n",
     "\n",
     "    def _call(\n",
     "        self,\n",
@@ -55,47 +84,133 @@
     "        run_manager: Optional[CallbackManagerForLLMRun] = None,\n",
     "        **kwargs: Any,\n",
     "    ) -> str:\n",
+    "        \"\"\"Run the LLM on the given input.\n",
+    "\n",
+    "        Override this method to implement the LLM logic.\n",
+    "\n",
+    "        Args:\n",
+    "            prompt: The prompt to generate from.\n",
+    "            stop: Stop words to use when generating. Model output is cut off at the\n",
+    "                first occurrence of any of the stop substrings.\n",
+    "                If stop tokens are not supported consider raising NotImplementedError.\n",
+    "            run_manager: Callback manager for the run.\n",
+    "            **kwargs: Arbitrary additional keyword arguments. These are usually passed\n",
+    "                to the model provider API call.\n",
+    "\n",
+    "        Returns:\n",
+    "            The model output as a string. Actual completions SHOULD NOT include the prompt.\n",
+    "        \"\"\"\n",
     "        if stop is not None:\n",
     "            raise ValueError(\"stop kwargs are not permitted.\")\n",
     "        return prompt[: self.n]\n",
     "\n",
+    "    def _stream(\n",
+    "        self,\n",
+    "        prompt: str,\n",
+    "        stop: Optional[List[str]] = None,\n",
+    "        run_manager: Optional[CallbackManagerForLLMRun] = None,\n",
+    "        **kwargs: Any,\n",
+    "    ) -> Iterator[GenerationChunk]:\n",
+    "        \"\"\"Stream the LLM on the given prompt.\n",
+    "\n",
+    "        This method should be overridden by subclasses that support streaming.\n",
+    "\n",
+    "        If not implemented, the default behavior of calls to stream will be to\n",
+    "        fallback to the non-streaming version of the model and return\n",
+    "        the output as a single chunk.\n",
+    "\n",
+    "        Args:\n",
+    "            prompt: The prompt to generate from.\n",
+    "            stop: Stop words to use when generating. Model output is cut off at the\n",
+    "                first occurrence of any of these substrings.\n",
+    "            run_manager: Callback manager for the run.\n",
+    "            **kwargs: Arbitrary additional keyword arguments. These are usually passed\n",
+    "                to the model provider API call.\n",
+    "\n",
+    "        Returns:\n",
+    "            An iterator of GenerationChunks.\n",
+    "        \"\"\"\n",
+    "        for char in prompt[: self.n]:\n",
+    "            chunk = GenerationChunk(text=char)\n",
+    "            if run_manager:\n",
+    "                run_manager.on_llm_new_token(chunk.text, chunk=chunk)\n",
+    "\n",
+    "            yield chunk\n",
+    "\n",
     "    @property\n",
-    "    def _identifying_params(self) -> Mapping[str, Any]:\n",
-    "        \"\"\"Get the identifying parameters.\"\"\"\n",
-    "        return {\"n\": self.n}"
+    "    def _identifying_params(self) -> Dict[str, Any]:\n",
+    "        \"\"\"Return a dictionary of identifying parameters.\"\"\"\n",
+    "        return {\n",
+    "            # The model name allows users to specify custom token counting\n",
+    "            # rules in LLM monitoring applications (e.g., in LangSmith users\n",
+    "            # can provide per token pricing for their model and monitor\n",
+    "            # costs for the given LLM.)\n",
+    "            \"model_name\": \"CustomChatModel\",\n",
+    "        }\n",
+    "\n",
+    "    @property\n",
+    "    def _llm_type(self) -> str:\n",
+    "        \"\"\"Get the type of language model used by this chat model. Used for logging purposes only.\"\"\"\n",
+    "        return \"custom\""
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "714dede0",
-   "metadata": {},
+   "id": "f614fb7b-e476-4d81-821b-57a2ebebe21c",
+   "metadata": {
+    "tags": []
+   },
    "source": [
-    "We can now use this as an any other LLM."
+    "### Let's test it 🧪"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e3feae15-4afc-49f4-8542-93867d4ea769",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "This LLM will implement the standard `Runnable` interface of LangChain which many of the LangChain abstractions support!"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
-   "id": "10e5ece6",
-   "metadata": {},
-   "outputs": [],
+   "execution_count": 2,
+   "id": "dfff4a95-99b2-4dba-b80d-9c3855046ef1",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1mCustomLLM\u001b[0m\n",
+      "Params: {'model_name': 'CustomChatModel'}\n"
+     ]
+    }
+   ],
    "source": [
-    "llm = CustomLLM(n=10)"
+    "llm = CustomLLM(n=5)\n",
+    "print(llm)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 3,
    "id": "8cd49199",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'This is a '"
+       "'This '"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -105,39 +220,209 @@
    ]
   },
   {
-   "cell_type": "markdown",
-   "id": "bbfebea1",
-   "metadata": {},
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "511b3cb1-9c6f-49b6-9002-a2ec490632b0",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'world'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "We can also print the LLM and see its custom print."
+    "await llm.ainvoke(\"world\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "d9d5bec2-d60a-4ebd-a97d-ac32c98ab02f",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['woof ', 'meow ']"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm.batch([\"woof woof woof\", \"meow meow meow\"])"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 6,
-   "id": "9c33fa19",
-   "metadata": {},
+   "id": "fe246b29-7a93-4bef-8861-389445598c25",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['woof ', 'meow ']"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "await llm.abatch([\"woof woof woof\", \"meow meow meow\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "3a67c38f-b83b-4eb9-a231-441c55ee8c82",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1mCustomLLM\u001b[0m\n",
-      "Params: {'n': 10}\n"
+      "h|e|l|l|o|"
      ]
     }
    ],
    "source": [
-    "print(llm)"
+    "async for token in llm.astream(\"hello\"):\n",
+    "    print(token, end=\"|\", flush=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b62c282b-3a35-4529-aac4-2c2f0916790e",
+   "metadata": {},
+   "source": [
+    "Let's confirm that in integrates nicely with other `LangChain` APIs."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "6dac3f47",
-   "metadata": {},
+   "execution_count": 15,
+   "id": "d5578e74-7fa8-4673-afee-7a59d442aaff",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
-   "source": []
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "672ff664-8673-4832-9f4f-335253880141",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [(\"system\", \"you are a bot\"), (\"human\", \"{input}\")]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "c400538a-9146-4c93-9fac-293d8f9ca6bf",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "llm = CustomLLM(n=7)\n",
+    "chain = prompt | llm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "080964af-3e2d-4573-85cb-0d7cc58a6f42",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'event': 'on_chain_start', 'run_id': '05f24b4f-7ea3-4fb6-8417-3aa21633462f', 'name': 'RunnableSequence', 'tags': [], 'metadata': {}, 'data': {'input': {'input': 'hello there!'}}}\n",
+      "{'event': 'on_prompt_start', 'name': 'ChatPromptTemplate', 'run_id': '7e996251-a926-4344-809e-c425a9846d21', 'tags': ['seq:step:1'], 'metadata': {}, 'data': {'input': {'input': 'hello there!'}}}\n",
+      "{'event': 'on_prompt_end', 'name': 'ChatPromptTemplate', 'run_id': '7e996251-a926-4344-809e-c425a9846d21', 'tags': ['seq:step:1'], 'metadata': {}, 'data': {'input': {'input': 'hello there!'}, 'output': ChatPromptValue(messages=[SystemMessage(content='you are a bot'), HumanMessage(content='hello there!')])}}\n",
+      "{'event': 'on_llm_start', 'name': 'CustomLLM', 'run_id': 'a8766beb-10f4-41de-8750-3ea7cf0ca7e2', 'tags': ['seq:step:2'], 'metadata': {}, 'data': {'input': {'prompts': ['System: you are a bot\\nHuman: hello there!']}}}\n",
+      "{'event': 'on_llm_stream', 'name': 'CustomLLM', 'run_id': 'a8766beb-10f4-41de-8750-3ea7cf0ca7e2', 'tags': ['seq:step:2'], 'metadata': {}, 'data': {'chunk': 'S'}}\n",
+      "{'event': 'on_chain_stream', 'run_id': '05f24b4f-7ea3-4fb6-8417-3aa21633462f', 'tags': [], 'metadata': {}, 'name': 'RunnableSequence', 'data': {'chunk': 'S'}}\n",
+      "{'event': 'on_llm_stream', 'name': 'CustomLLM', 'run_id': 'a8766beb-10f4-41de-8750-3ea7cf0ca7e2', 'tags': ['seq:step:2'], 'metadata': {}, 'data': {'chunk': 'y'}}\n",
+      "{'event': 'on_chain_stream', 'run_id': '05f24b4f-7ea3-4fb6-8417-3aa21633462f', 'tags': [], 'metadata': {}, 'name': 'RunnableSequence', 'data': {'chunk': 'y'}}\n"
+     ]
+    }
+   ],
+   "source": [
+    "idx = 0\n",
+    "async for event in chain.astream_events({\"input\": \"hello there!\"}, version=\"v1\"):\n",
+    "    print(event)\n",
+    "    idx += 1\n",
+    "    if idx > 7:\n",
+    "        # Truncate\n",
+    "        break"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a85e848a-5316-4318-b770-3f8fd34f4231",
+   "metadata": {},
+   "source": [
+    "## Contributing\n",
+    "\n",
+    "We appreciate all chat model integration contributions. \n",
+    "\n",
+    "Here's a checklist to help make sure your contribution gets added to LangChain:\n",
+    "\n",
+    "Documentation:\n",
+    "\n",
+    "* The model contains doc-strings for all initialization arguments, as these will be surfaced in the [APIReference](https://api.python.langchain.com/en/stable/langchain_api_reference.html).\n",
+    "* The class doc-string for the model contains a link to the model API if the model is powered by a service.\n",
+    "\n",
+    "Tests:\n",
+    "\n",
+    "* [ ] Add unit or integration tests to the overridden methods. Verify that `invoke`, `ainvoke`, `batch`, `stream` work if you've over-ridden the corresponding code.\n",
+    "\n",
+    "Streaming (if you're implementing it):\n",
+    "\n",
+    "* [ ] Make sure to invoke the `on_llm_new_token` callback\n",
+    "* [ ] `on_llm_new_token` is invoked BEFORE yielding the chunk\n",
+    "\n",
+    "Stop Token Behavior:\n",
+    "\n",
+    "* [ ] Stop token should be respected\n",
+    "* [ ] Stop token should be INCLUDED as part of the response\n",
+    "\n",
+    "Secret API Keys:\n",
+    "\n",
+    "* [ ] If your model connects to an API it will likely accept API keys as part of its initialization. Use Pydantic's `SecretStr` type for secrets, so they don't get accidentally printed out when folks print the model."
+   ]
   }
  ],
  "metadata": {
@@ -156,7 +441,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,

docs/docs/modules/model_io/llms/quick_start.ipynb

@@ -40,7 +40,7 @@
     "export OPENAI_API_KEY=\"...\"\n",
     "```\n",
     "\n",
-    "If you'd prefer not to set an environment variable you can pass the key in directly via the `openai_api_key` named parameter when initiating the OpenAI LLM class:\n",
+    "If you'd prefer not to set an environment variable you can pass the key in directly via the `api_key` named parameter when initiating the OpenAI LLM class:\n",
     "\n"
    ]
   },
@@ -53,7 +53,7 @@
    "source": [
     "from langchain_openai import OpenAI\n",
     "\n",
-    "llm = OpenAI(openai_api_key=\"...\")"
+    "llm = OpenAI(api_key=\"...\")"
    ]
   },
   {

docs/docs/modules/model_io/output_parsers/types/openai_functions.ipynb

@@ -9,10 +9,10 @@
     "\n",
     "These output parsers use OpenAI function calling to structure its outputs. This means they are only usable with models that support function calling. There are a few different variants:\n",
     "\n",
-    "- JsonOutputFunctionsParser: Returns the arguments of the function call as JSON\n",
-    "- PydanticOutputFunctionsParser: Returns the arguments of the function call as a Pydantic Model\n",
-    "- JsonKeyOutputFunctionsParser: Returns the value of specific key in the function call as JSON\n",
-    "- PydanticAttrOutputFunctionsParser: Returns the value of specific key in the function call as a Pydantic Model\n"
+    "- [JsonOutputFunctionsParser](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.openai_functions.JsonOutputFunctionsParser.html#langchain_core.output_parsers.openai_functions.JsonOutputFunctionsParser): Returns the arguments of the function call as JSON\n",
+    "- [PydanticOutputFunctionsParser](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.openai_functions.PydanticOutputFunctionsParser.html#langchain_core.output_parsers.openai_functions.PydanticOutputFunctionsParser): Returns the arguments of the function call as a Pydantic Model\n",
+    "- [JsonKeyOutputFunctionsParser](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.openai_functions.JsonKeyOutputFunctionsParser.html#langchain_core.output_parsers.openai_functions.JsonKeyOutputFunctionsParser): Returns the value of specific key in the function call as JSON\n",
+    "- [PydanticAttrOutputFunctionsParser](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.openai_functions.PydanticAttrOutputFunctionsParser.html#langchain_core.output_parsers.openai_functions.PydanticAttrOutputFunctionsParser): Returns the value of specific key in the function call as a Pydantic Model\n"
    ]
   },
   {

docs/docs/modules/model_io/output_parsers/types/openai_tools.ipynb

@@ -11,9 +11,9 @@
     "\n",
     "There are a few different variants of output parsers:\n",
     "\n",
-    "- [JsonOutputToolsParser](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.openai_tools.JsonOutputToolsParser.html#langchain.output_parsers.openai_tools.JsonOutputToolsParser): Returns the arguments of the function call as JSON\n",
-    "- [JsonOutputKeyToolsParser](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.openai_tools.JsonOutputKeyToolsParser.html#langchain.output_parsers.openai_tools.JsonOutputKeyToolsParser): Returns the value of specific key in the function call as JSON\n",
-    "- [PydanticToolsParser](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.openai_tools.PydanticToolsParser.html#langchain.output_parsers.openai_tools.PydanticToolsParser): Returns the arguments of the function call as a Pydantic Model"
+    "- [JsonOutputToolsParser](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.openai_tools.JsonOutputToolsParser.html#langchain_core.output_parsers.openai_tools.JsonOutputToolsParser): Returns the arguments of the function call as JSON\n",
+    "- [JsonOutputKeyToolsParser](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.openai_tools.JsonOutputKeyToolsParser.html#langchain_core.output_parsers.openai_tools.JsonOutputKeyToolsParser): Returns the value of specific key in the function call as JSON\n",
+    "- [PydanticToolsParser](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.openai_tools.PydanticToolsParser.html#langchain_core.output_parsers.openai_tools.PydanticToolsParser): Returns the arguments of the function call as a Pydantic Model"
    ]
   },
   {

docs/docs/modules/model_io/quick_start.mdx

@@ -38,11 +38,11 @@ llm = OpenAI()
 chat_model = ChatOpenAI(model="gpt-3.5-turbo-0125")
 ```
 
-If you'd prefer not to set an environment variable you can pass the key in directly via the `openai_api_key` named parameter when initiating the OpenAI LLM class:
+If you'd prefer not to set an environment variable you can pass the key in directly via the `api_key` named parameter when initiating the OpenAI LLM class:
 
 ```python
 from langchain_openai import ChatOpenAI
-llm = ChatOpenAI(openai_api_key="...")
+llm = ChatOpenAI(api_key="...")
 ```
 
   </TabItem>
@@ -87,10 +87,10 @@ from langchain_anthropic import ChatAnthropic
 chat_model = ChatAnthropic(model="claude-3-sonnet-20240229", temperature=0.2, max_tokens=1024)
 ```
 
-If you'd prefer not to set an environment variable you can pass the key in directly via the `anthropic_api_key` named parameter when initiating the Anthropic Chat Model class:
+If you'd prefer not to set an environment variable you can pass the key in directly via the `api_key` named parameter when initiating the Anthropic Chat Model class:
 
 ```python
-chat_model = ChatAnthropic(anthropic_api_key="...")
+chat_model = ChatAnthropic(api_key="...")
 ```
 
   </TabItem>

docs/docs/use_cases/code_understanding.ipynb

@@ -237,7 +237,7 @@
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "llm = ChatOpenAI(model_name=\"gpt-4\")\n",
+    "llm = ChatOpenAI(model=\"gpt-4\")\n",
     "\n",
     "# First we need a prompt that we can pass into an LLM to generate this search query\n",
     "\n",

docs/docs/use_cases/data_generation.ipynb

@@ -269,7 +269,7 @@
    "outputs": [],
    "source": [
     "# LLM\n",
-    "model = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0.7)\n",
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0.7)\n",
     "chain = create_data_generation_chain(model)"
    ]
   },

docs/docs/use_cases/question_answering/chat_history.ipynb

@@ -151,7 +151,7 @@
     "# Retrieve and generate using the relevant snippets of the blog.\n",
     "retriever = vectorstore.as_retriever()\n",
     "prompt = hub.pull(\"rlm/rag-prompt\")\n",
-    "llm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)\n",
     "\n",
     "\n",
     "def format_docs(docs):\n",
@@ -417,7 +417,7 @@
     "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
     "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
-    "llm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)\n",
     "\n",
     "\n",
     "### Construct retriever ###\n",

docs/docs/use_cases/question_answering/citations.ipynb

@@ -184,7 +184,7 @@
     "## Function-calling\n",
     "\n",
     "### Cite documents\n",
-    "Let's try using [OpenAI function-calling](/docs/modules/model_io/chat/function_calling) to make the model specify which of the provided documents it's actually referencing when answering. LangChain has some utils for converting Pydantic ojbects to the JSONSchema format expected by OpenAI, so we'll use that to define our functions:"
+    "Let's try using [OpenAI function-calling](/docs/modules/model_io/chat/function_calling) to make the model specify which of the provided documents it's actually referencing when answering. LangChain has some utils for converting Pydantic objects to the JSONSchema format expected by OpenAI, so we'll use that to define our functions:"
    ]
   },
   {

docs/docs/use_cases/question_answering/sources.ipynb

@@ -143,7 +143,7 @@
     "# Retrieve and generate using the relevant snippets of the blog.\n",
     "retriever = vectorstore.as_retriever()\n",
     "prompt = hub.pull(\"rlm/rag-prompt\")\n",
-    "llm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)\n",
     "\n",
     "\n",
     "def format_docs(docs):\n",

docs/docs/use_cases/question_answering/streaming.ipynb

@@ -143,7 +143,7 @@
     "# Retrieve and generate using the relevant snippets of the blog.\n",
     "retriever = vectorstore.as_retriever()\n",
     "prompt = hub.pull(\"rlm/rag-prompt\")\n",
-    "llm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)\n",
     "\n",
     "\n",
     "def format_docs(docs):\n",

docs/scripts/model_feat_table.py

@@ -15,12 +15,21 @@ LLM_FEAT_TABLE_CORRECTION = {
     "PromptLayerOpenAI": {"batch_generate": False, "batch_agenerate": False},
 }
 CHAT_MODEL_IGNORE = ("FakeListChatModel", "HumanInputChatModel")
+
 CHAT_MODEL_FEAT_TABLE_CORRECTION = {
     "ChatMLflowAIGateway": {"_agenerate": False},
     "PromptLayerChatOpenAI": {"_stream": False, "_astream": False},
     "ChatKonko": {"_astream": False, "_agenerate": False},
+    "ChatAnthropic": {"tool_calling": True, "package": "langchain-anthropic"},
+    "ChatMistralAI": {"tool_calling": True, "package": "langchain-mistralai"},
+    "ChatFireworks": {"tool_calling": True, "package": "langchain-fireworks"},
+    "ChatOpenAI": {"tool_calling": True, "package": "langchain-openai"},
+    "ChatVertexAI": {"tool_calling": True, "package": "langchain-google-vertexai"},
+    "ChatGroq": {"tool_calling": "partial", "package": "langchain-groq"},
+    "ChatCohere": {"tool_calling": "partial", "package": "langchain-cohere"},
 }
 
+
 LLM_TEMPLATE = """\
 ---
 sidebar_position: 1
@@ -56,7 +65,8 @@ All ChatModels implement the Runnable interface, which comes with default implem
 - *Batch* support defaults to calling the underlying ChatModel in parallel for each input by making use of a thread pool executor (in the sync batch case) or `asyncio.gather` (in the async batch case). The concurrency can be controlled with the `max_concurrency` key in `RunnableConfig`.
 
 Each ChatModel integration can optionally provide native implementations to truly enable async or streaming.
-The table shows, for each integration, which features have been implemented with native support.
+The table shows, for each integration, which features have been implemented with native support. 
+Yellow circles (🟡) indicates partial support - for example, if the model supports tool calling but not tool messages for agents.
 
 {table}
 
@@ -101,6 +111,7 @@ def get_llm_table():
         "_astream",
         "batch_generate",
         "batch_agenerate",
+        "tool_calling",
     ]
     title = [
         "Model",
@@ -110,6 +121,7 @@ def get_llm_table():
         "Async stream",
         "Batch",
         "Async batch",
+        "Tool calling",
     ]
     rows = [title, [":-"] + [":-:"] * (len(title) - 1)]
     for llm, feats in sorted(final_feats.items()):
@@ -117,7 +129,8 @@ def get_llm_table():
     return "\n".join(["|".join(row) for row in rows])
 
 
-def get_chat_model_table():
+def get_chat_model_table() -> str:
+    """Get the table of chat models."""
     feat_table = {}
     for cm in chat_models.__all__:
         feat_table[cm] = {}
@@ -133,11 +146,40 @@ def get_chat_model_table():
         for k, v in {**feat_table, **CHAT_MODEL_FEAT_TABLE_CORRECTION}.items()
         if k not in CHAT_MODEL_IGNORE
     }
-    header = ["model", "_agenerate", "_stream", "_astream"]
-    title = ["Model", "Invoke", "Async invoke", "Stream", "Async stream"]
+    header = [
+        "model",
+        "_agenerate",
+        "_stream",
+        "_astream",
+        "tool_calling",
+        "package",
+    ]
+    title = [
+        "Model",
+        "Invoke",
+        "Async invoke",
+        "Stream",
+        "Async stream",
+        "Tool calling",
+        "Python Package",
+    ]
     rows = [title, [":-"] + [":-:"] * (len(title) - 1)]
     for llm, feats in sorted(final_feats.items()):
-        rows += [[llm, "✅"] + ["✅" if feats.get(h) else "❌" for h in header[1:]]]
+        # Fields are in the order of the header
+        row = [llm, "✅"]
+        for h in header[1:]:
+            value = feats.get(h)
+            index = header.index(h)
+            if h == "package":
+                row.append(value or "langchain-community")
+            else:
+                if value == "partial":
+                    row.append("🟡")
+                elif value is True:
+                    row.append("✅")
+                else:
+                    row.append("❌")
+        rows.append(row)
     return "\n".join(["|".join(row) for row in rows])
 
 

docs/src/theme/ChatModelTabs.js

@@ -23,15 +23,17 @@ os.environ["${apiKeyName}"] = getpass.getpass()`;
  * @typedef {Object} ChatModelTabsProps - Component props.
  * @property {string} [openaiParams] - Parameters for OpenAI chat model. Defaults to `model="gpt-3.5-turbo-0125"`
  * @property {string} [anthropicParams] - Parameters for Anthropic chat model. Defaults to `model="claude-3-sonnet-20240229"`
+ * @property {string} [cohereParams] - Parameters for Cohere chat model. Defaults to `model="command-r"`
  * @property {string} [fireworksParams] - Parameters for Fireworks chat model. Defaults to `model="accounts/fireworks/models/mixtral-8x7b-instruct"`
  * @property {string} [mistralParams] - Parameters for Mistral chat model. Defaults to `model="mistral-large-latest"`
  * @property {string} [googleParams] - Parameters for Google chat model. Defaults to `model="gemini-pro"`
  * @property {string} [togetherParams] - Parameters for Together chat model. Defaults to `model="mistralai/Mixtral-8x7B-Instruct-v0.1"`
  * @property {boolean} [hideOpenai] - Whether or not to hide OpenAI chat model.
  * @property {boolean} [hideAnthropic] - Whether or not to hide Anthropic chat model.
+ * @property {boolean} [hideCohere] - Whether or not to hide Cohere chat model.
  * @property {boolean} [hideFireworks] - Whether or not to hide Fireworks chat model.
  * @property {boolean} [hideMistral] - Whether or not to hide Mistral chat model.
- * @property {boolean} [hideGoogle] - Whether or not to hide Google chat model.
+ * @property {boolean} [hideGoogle] - Whether or not to hide Google VertexAI chat model.
  * @property {boolean} [hideTogether] - Whether or not to hide Together chat model.
  * @property {string} [customVarName] - Custom variable name for the model. Defaults to `model`.
  */
@@ -43,12 +45,14 @@ export default function ChatModelTabs(props) {
   const {
     openaiParams,
     anthropicParams,
+    cohereParams,
     fireworksParams,
     mistralParams,
     googleParams,
     togetherParams,
     hideOpenai,
     hideAnthropic,
+    hideCohere,
     hideFireworks,
     hideMistral,
     hideGoogle,
@@ -59,6 +63,7 @@ export default function ChatModelTabs(props) {
   const openAIParamsOrDefault = openaiParams ?? `model="gpt-3.5-turbo-0125"`;
   const anthropicParamsOrDefault =
     anthropicParams ?? `model="claude-3-sonnet-20240229"`;
+  const cohereParamsOrDefault = cohereParams ?? `model="command-r"`;
   const fireworksParamsOrDefault =
     fireworksParams ??
     `model="accounts/fireworks/models/mixtral-8x7b-instruct"`;
@@ -90,6 +95,24 @@ export default function ChatModelTabs(props) {
       default: false,
       shouldHide: hideAnthropic,
     },
+    {
+      value: "Google",
+      label: "Google",
+      text: `from langchain_google_vertexai import ChatVertexAI\n\n${llmVarName} = ChatVertexAI(${googleParamsOrDefault})`,
+      apiKeyName: "GOOGLE_API_KEY",
+      packageName: "langchain-google-vertexai",
+      default: false,
+      shouldHide: hideGoogle,
+    },
+    {
+      value: "Cohere",
+      label: "Cohere",
+      text: `from langchain_cohere import ChatCohere\n\n${llmVarName} = ChatCohere(${cohereParamsOrDefault})`,
+      apiKeyName: "COHERE_API_KEY",
+      packageName: "langchain-cohere",
+      default: false,
+      shouldHide: hideCohere,
+    },
     {
       value: "FireworksAI",
       label: "FireworksAI",
@@ -108,19 +131,10 @@ export default function ChatModelTabs(props) {
       default: false,
       shouldHide: hideMistral,
     },
-    {
-      value: "Google",
-      label: "Google",
-      text: `from langchain_google_genai import ChatGoogleGenerativeAI\n\n${llmVarName} = ChatGoogleGenerativeAI(${googleParamsOrDefault})`,
-      apiKeyName: "GOOGLE_API_KEY",
-      packageName: "langchain-google-genai",
-      default: false,
-      shouldHide: hideGoogle,
-    },
     {
       value: "TogetherAI",
       label: "TogetherAI",
-      text: `from langchain_openai import ChatOpenAI\n\n${llmVarName} = Together(${togetherParamsOrDefault})`,
+      text: `from langchain_openai import ChatOpenAI\n\n${llmVarName} = ChatOpenAI(${togetherParamsOrDefault})`,
       apiKeyName: "TOGETHER_API_KEY",
       packageName: "langchain-openai",
       default: false,

libs/community/langchain_community/agent_toolkits/__init__.py

@@ -3,7 +3,129 @@ various services and APIs.
 """
 
 import importlib
-from typing import Any
+from typing import TYPE_CHECKING, Any
+
+if TYPE_CHECKING:
+    from langchain_community.agent_toolkits.ainetwork.toolkit import (
+        AINetworkToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.amadeus.toolkit import (
+        AmadeusToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.azure_ai_services import (
+        AzureAiServicesToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.azure_cognitive_services import (
+        AzureCognitiveServicesToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.cogniswitch.toolkit import (
+        CogniswitchToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.connery import (
+        ConneryToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.file_management.toolkit import (
+        FileManagementToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.gmail.toolkit import (
+        GmailToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.jira.toolkit import (
+        JiraToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.json.base import (
+        create_json_agent,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.json.toolkit import (
+        JsonToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.multion.toolkit import (
+        MultionToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.nasa.toolkit import (
+        NasaToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.nla.toolkit import (
+        NLAToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.office365.toolkit import (
+        O365Toolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.openapi.base import (
+        create_openapi_agent,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.openapi.toolkit import (
+        OpenAPIToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.playwright.toolkit import (
+        PlayWrightBrowserToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.polygon.toolkit import (
+        PolygonToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.powerbi.base import (
+        create_pbi_agent,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.powerbi.chat_base import (
+        create_pbi_chat_agent,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.powerbi.toolkit import (
+        PowerBIToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.slack.toolkit import (
+        SlackToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.spark_sql.base import (
+        create_spark_sql_agent,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.spark_sql.toolkit import (
+        SparkSQLToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.sql.base import (
+        create_sql_agent,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.sql.toolkit import (
+        SQLDatabaseToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.steam.toolkit import (
+        SteamToolkit,  # noqa: F401
+    )
+    from langchain_community.agent_toolkits.zapier.toolkit import (
+        ZapierToolkit,  # noqa: F401
+    )
+
+__all__ = [
+    "AINetworkToolkit",
+    "AmadeusToolkit",
+    "AzureAiServicesToolkit",
+    "AzureCognitiveServicesToolkit",
+    "CogniswitchToolkit",
+    "ConneryToolkit",
+    "FileManagementToolkit",
+    "GmailToolkit",
+    "JiraToolkit",
+    "JsonToolkit",
+    "MultionToolkit",
+    "NLAToolkit",
+    "NasaToolkit",
+    "O365Toolkit",
+    "OpenAPIToolkit",
+    "PlayWrightBrowserToolkit",
+    "PolygonToolkit",
+    "PowerBIToolkit",
+    "SQLDatabaseToolkit",
+    "SlackToolkit",
+    "SparkSQLToolkit",
+    "SteamToolkit",
+    "ZapierToolkit",
+    "create_json_agent",
+    "create_openapi_agent",
+    "create_pbi_agent",
+    "create_pbi_chat_agent",
+    "create_spark_sql_agent",
+    "create_sql_agent",
+]
+
 
 _module_lookup = {
     "AINetworkToolkit": "langchain_community.agent_toolkits.ainetwork.toolkit",

libs/community/langchain_community/agent_toolkits/connery/toolkit.py

@@ -9,7 +9,7 @@ from langchain_community.tools.connery import ConneryService
 
 class ConneryToolkit(BaseToolkit):
     """
-    A LangChain Toolkit with a list of Connery Actions as tools.
+    Toolkit with a list of Connery Actions as tools.
     """
 
     tools: List[BaseTool]

libs/community/langchain_community/agent_toolkits/openapi/planner.py

@@ -1,4 +1,5 @@
 """Agent that interacts with OpenAPI APIs via a hierarchical planning approach."""
+
 import json
 import re
 from functools import partial
@@ -252,6 +253,7 @@ def _create_api_controller_agent(
     api_docs: str,
     requests_wrapper: RequestsWrapper,
     llm: BaseLanguageModel,
+    allow_dangerous_requests: bool,
 ) -> Any:
     from langchain.agents.agent import AgentExecutor
     from langchain.agents.mrkl.base import ZeroShotAgent
@@ -261,10 +263,14 @@ def _create_api_controller_agent(
     post_llm_chain = LLMChain(llm=llm, prompt=PARSING_POST_PROMPT)
     tools: List[BaseTool] = [
         RequestsGetToolWithParsing(
-            requests_wrapper=requests_wrapper, llm_chain=get_llm_chain
+            requests_wrapper=requests_wrapper,
+            llm_chain=get_llm_chain,
+            allow_dangerous_requests=allow_dangerous_requests,
         ),
         RequestsPostToolWithParsing(
-            requests_wrapper=requests_wrapper, llm_chain=post_llm_chain
+            requests_wrapper=requests_wrapper,
+            llm_chain=post_llm_chain,
+            allow_dangerous_requests=allow_dangerous_requests,
         ),
     ]
     prompt = PromptTemplate(
@@ -290,6 +296,7 @@ def _create_api_controller_tool(
     api_spec: ReducedOpenAPISpec,
     requests_wrapper: RequestsWrapper,
     llm: BaseLanguageModel,
+    allow_dangerous_requests: bool,
 ) -> Tool:
     """Expose controller as a tool.
 
@@ -318,7 +325,9 @@ def _create_api_controller_tool(
             if not found_match:
                 raise ValueError(f"{endpoint_name} endpoint does not exist.")
 
-        agent = _create_api_controller_agent(base_url, docs_str, requests_wrapper, llm)
+        agent = _create_api_controller_agent(
+            base_url, docs_str, requests_wrapper, llm, allow_dangerous_requests
+        )
         return agent.run(plan_str)
 
     return Tool(
@@ -336,15 +345,24 @@ def create_openapi_agent(
     callback_manager: Optional[BaseCallbackManager] = None,
     verbose: bool = True,
     agent_executor_kwargs: Optional[Dict[str, Any]] = None,
+    allow_dangerous_requests: bool = False,
     **kwargs: Any,
 ) -> Any:
-    """Instantiate OpenAI API planner and controller for a given spec.
+    """Construct an OpenAI API planner and controller for a given spec.
 
     Inject credentials via requests_wrapper.
 
     We use a top-level "orchestrator" agent to invoke the planner and controller,
     rather than a top-level planner
     that invokes a controller with its plan. This is to keep the planner simple.
+
+    You need to set allow_dangerous_requests to True to use Agent with BaseRequestsTool.
+    Requests can be dangerous and can lead to security vulnerabilities.
+    For example, users can ask a server to make a request to an internal
+    server. It's recommended to use requests through a proxy server
+    and avoid accepting inputs from untrusted sources without proper sandboxing.
+    Please see: https://python.langchain.com/docs/security
+    for further security information.
     """
     from langchain.agents.agent import AgentExecutor
     from langchain.agents.mrkl.base import ZeroShotAgent
@@ -352,7 +370,9 @@ def create_openapi_agent(
 
     tools = [
         _create_api_planner_tool(api_spec, llm),
-        _create_api_controller_tool(api_spec, requests_wrapper, llm),
+        _create_api_controller_tool(
+            api_spec, requests_wrapper, llm, allow_dangerous_requests
+        ),
     ]
     prompt = PromptTemplate(
         template=API_ORCHESTRATOR_PROMPT,

libs/community/langchain_community/agent_toolkits/sql/base.py

@@ -1,7 +1,6 @@
 """SQL agent."""
 from __future__ import annotations
 
-import warnings
 from typing import (
     TYPE_CHECKING,
     Any,
@@ -93,7 +92,7 @@ def create_sql_agent(
             using 'db' and 'llm'. Must provide exactly one of 'db' or 'toolkit'.
         prompt: Complete agent prompt. prompt and {prefix, suffix, format_instructions,
             input_variables} are mutually exclusive.
-        **kwargs: DEPRECATED. Not used, kept for backwards compatibility.
+        **kwargs: Arbitrary additional Agent args.
 
     Returns:
         An AgentExecutor with the specified agent_type agent.
@@ -131,13 +130,6 @@ def create_sql_agent(
         raise ValueError(
             "Must provide exactly one of 'toolkit' or 'db'. Received both."
         )
-    if input_variables:
-        kwargs = kwargs or {}
-        kwargs["input_variables"] = input_variables
-    if kwargs:
-        warnings.warn(
-            f"Received additional kwargs {kwargs} which are no longer supported."
-        )
 
     toolkit = toolkit or SQLDatabaseToolkit(llm=llm, db=db)
     agent_type = agent_type or AgentType.ZERO_SHOT_REACT_DESCRIPTION
@@ -183,6 +175,7 @@ def create_sql_agent(
             runnable=create_react_agent(llm, tools, prompt),
             input_keys_arg=["input"],
             return_keys_arg=["output"],
+            **kwargs,
         )
 
     elif agent_type == AgentType.OPENAI_FUNCTIONS:
@@ -198,6 +191,7 @@ def create_sql_agent(
             runnable=create_openai_functions_agent(llm, tools, prompt),
             input_keys_arg=["input"],
             return_keys_arg=["output"],
+            **kwargs,
         )
     elif agent_type == "openai-tools":
         if prompt is None:
@@ -212,6 +206,7 @@ def create_sql_agent(
             runnable=create_openai_tools_agent(llm, tools, prompt),
             input_keys_arg=["input"],
             return_keys_arg=["output"],
+            **kwargs,
         )
 
     else:

libs/community/langchain_community/cache.py

@@ -1998,7 +1998,7 @@ class AzureCosmosDBSemanticCache(BaseCache):
             k=1,
             kind=self.kind,
             ef_search=self.ef_search,
-            score_threshold=self.score_threshold,
+            score_threshold=self.score_threshold,  # type: ignore[arg-type]
         )
         if results:
             for document in results:

libs/community/langchain_community/callbacks/__init__.py

@@ -7,7 +7,78 @@
     BaseCallbackHandler --> <name>CallbackHandler  # Example: AimCallbackHandler
 """
 import importlib
-from typing import Any
+from typing import TYPE_CHECKING, Any
+
+if TYPE_CHECKING:
+    from langchain_community.callbacks.aim_callback import (
+        AimCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.argilla_callback import (
+        ArgillaCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.arize_callback import (
+        ArizeCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.arthur_callback import (
+        ArthurCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.clearml_callback import (
+        ClearMLCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.comet_ml_callback import (
+        CometCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.context_callback import (
+        ContextCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.fiddler_callback import (
+        FiddlerCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.flyte_callback import (
+        FlyteCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.human import (
+        HumanApprovalCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.infino_callback import (
+        InfinoCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.labelstudio_callback import (
+        LabelStudioCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.llmonitor_callback import (
+        LLMonitorCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.manager import (  # noqa: F401
+        get_openai_callback,
+        wandb_tracing_enabled,
+    )
+    from langchain_community.callbacks.mlflow_callback import (
+        MlflowCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.openai_info import (
+        OpenAICallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.promptlayer_callback import (
+        PromptLayerCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.sagemaker_callback import (
+        SageMakerCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.streamlit import (  # noqa: F401
+        LLMThoughtLabeler,
+        StreamlitCallbackHandler,
+    )
+    from langchain_community.callbacks.trubrics_callback import (
+        TrubricsCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.wandb_callback import (
+        WandbCallbackHandler,  # noqa: F401
+    )
+    from langchain_community.callbacks.whylabs_callback import (
+        WhyLabsCallbackHandler,  # noqa: F401
+    )
+
 
 _module_lookup = {
     "AimCallbackHandler": "langchain_community.callbacks.aim_callback",
@@ -44,4 +115,29 @@ def __getattr__(name: str) -> Any:
     raise AttributeError(f"module {__name__} has no attribute {name}")
 
 
-__all__ = list(_module_lookup.keys())
+__all__ = [
+    "AimCallbackHandler",
+    "ArgillaCallbackHandler",
+    "ArizeCallbackHandler",
+    "ArthurCallbackHandler",
+    "ClearMLCallbackHandler",
+    "CometCallbackHandler",
+    "ContextCallbackHandler",
+    "FiddlerCallbackHandler",
+    "FlyteCallbackHandler",
+    "HumanApprovalCallbackHandler",
+    "InfinoCallbackHandler",
+    "LLMThoughtLabeler",
+    "LLMonitorCallbackHandler",
+    "LabelStudioCallbackHandler",
+    "MlflowCallbackHandler",
+    "OpenAICallbackHandler",
+    "PromptLayerCallbackHandler",
+    "SageMakerCallbackHandler",
+    "StreamlitCallbackHandler",
+    "TrubricsCallbackHandler",
+    "WandbCallbackHandler",
+    "WhyLabsCallbackHandler",
+    "get_openai_callback",
+    "wandb_tracing_enabled",
+]

libs/community/langchain_community/callbacks/bedrock_anthropic_callback.py

@@ -0,0 +1,111 @@
+import threading
+from typing import Any, Dict, List, Union
+
+from langchain_core.callbacks import BaseCallbackHandler
+from langchain_core.outputs import LLMResult
+
+MODEL_COST_PER_1K_INPUT_TOKENS = {
+    "anthropic.claude-instant-v1": 0.0008,
+    "anthropic.claude-v2": 0.008,
+    "anthropic.claude-v2:1": 0.008,
+    "anthropic.claude-3-sonnet-20240229-v1:0": 0.003,
+    "anthropic.claude-3-haiku-20240307-v1:0": 0.00025,
+}
+
+MODEL_COST_PER_1K_OUTPUT_TOKENS = {
+    "anthropic.claude-instant-v1": 0.0024,
+    "anthropic.claude-v2": 0.024,
+    "anthropic.claude-v2:1": 0.024,
+    "anthropic.claude-3-sonnet-20240229-v1:0": 0.015,
+    "anthropic.claude-3-haiku-20240307-v1:0": 0.00125,
+}
+
+
+def _get_anthropic_claude_token_cost(
+    prompt_tokens: int, completion_tokens: int, model_id: Union[str, None]
+) -> float:
+    """Get the cost of tokens for the Claude model."""
+    if model_id not in MODEL_COST_PER_1K_INPUT_TOKENS:
+        raise ValueError(
+            f"Unknown model: {model_id}. Please provide a valid Anthropic model name."
+            "Known models are: " + ", ".join(MODEL_COST_PER_1K_INPUT_TOKENS.keys())
+        )
+    return (prompt_tokens / 1000) * MODEL_COST_PER_1K_INPUT_TOKENS[model_id] + (
+        completion_tokens / 1000
+    ) * MODEL_COST_PER_1K_OUTPUT_TOKENS[model_id]
+
+
+class BedrockAnthropicTokenUsageCallbackHandler(BaseCallbackHandler):
+    """Callback Handler that tracks bedrock anthropic info."""
+
+    total_tokens: int = 0
+    prompt_tokens: int = 0
+    completion_tokens: int = 0
+    successful_requests: int = 0
+    total_cost: float = 0.0
+
+    def __init__(self) -> None:
+        super().__init__()
+        self._lock = threading.Lock()
+
+    def __repr__(self) -> str:
+        return (
+            f"Tokens Used: {self.total_tokens}\n"
+            f"\tPrompt Tokens: {self.prompt_tokens}\n"
+            f"\tCompletion Tokens: {self.completion_tokens}\n"
+            f"Successful Requests: {self.successful_requests}\n"
+            f"Total Cost (USD): ${self.total_cost}"
+        )
+
+    @property
+    def always_verbose(self) -> bool:
+        """Whether to call verbose callbacks even if verbose is False."""
+        return True
+
+    def on_llm_start(
+        self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any
+    ) -> None:
+        """Print out the prompts."""
+        pass
+
+    def on_llm_new_token(self, token: str, **kwargs: Any) -> None:
+        """Print out the token."""
+        pass
+
+    def on_llm_end(self, response: LLMResult, **kwargs: Any) -> None:
+        """Collect token usage."""
+        if response.llm_output is None:
+            return None
+
+        if "usage" not in response.llm_output:
+            with self._lock:
+                self.successful_requests += 1
+            return None
+
+        # compute tokens and cost for this request
+        token_usage = response.llm_output["usage"]
+        completion_tokens = token_usage.get("completion_tokens", 0)
+        prompt_tokens = token_usage.get("prompt_tokens", 0)
+        total_tokens = token_usage.get("total_tokens", 0)
+        model_id = response.llm_output.get("model_id", None)
+        total_cost = _get_anthropic_claude_token_cost(
+            prompt_tokens=prompt_tokens,
+            completion_tokens=completion_tokens,
+            model_id=model_id,
+        )
+
+        # update shared state behind lock
+        with self._lock:
+            self.total_cost += total_cost
+            self.total_tokens += total_tokens
+            self.prompt_tokens += prompt_tokens
+            self.completion_tokens += completion_tokens
+            self.successful_requests += 1
+
+    def __copy__(self) -> "BedrockAnthropicTokenUsageCallbackHandler":
+        """Return a copy of the callback handler."""
+        return self
+
+    def __deepcopy__(self, memo: Any) -> "BedrockAnthropicTokenUsageCallbackHandler":
+        """Return a deep copy of the callback handler."""
+        return self

libs/community/langchain_community/callbacks/flyte_callback.py

@@ -91,7 +91,7 @@ def analyze_text(
 
 
 class FlyteCallbackHandler(BaseMetadataCallbackHandler, BaseCallbackHandler):
-    """This callback handler that is used within a Flyte task."""
+    """Callback handler that is used within a Flyte task."""
 
     def __init__(self) -> None:
         """Initialize callback handler."""

libs/community/langchain_community/callbacks/manager.py

@@ -10,6 +10,9 @@ from typing import (
 
 from langchain_core.tracers.context import register_configure_hook
 
+from langchain_community.callbacks.bedrock_anthropic_callback import (
+    BedrockAnthropicTokenUsageCallbackHandler,
+)
 from langchain_community.callbacks.openai_info import OpenAICallbackHandler
 from langchain_community.callbacks.tracers.comet import CometTracer
 from langchain_community.callbacks.tracers.wandb import WandbTracer
@@ -19,7 +22,10 @@ logger = logging.getLogger(__name__)
 openai_callback_var: ContextVar[Optional[OpenAICallbackHandler]] = ContextVar(
     "openai_callback", default=None
 )
-wandb_tracing_callback_var: ContextVar[Optional[WandbTracer]] = ContextVar(  # noqa: E501
+bedrock_anthropic_callback_var: (ContextVar)[
+    Optional[BedrockAnthropicTokenUsageCallbackHandler]
+] = ContextVar("bedrock_anthropic_callback", default=None)
+wandb_tracing_callback_var: ContextVar[Optional[WandbTracer]] = ContextVar(
     "tracing_wandb_callback", default=None
 )
 comet_tracing_callback_var: ContextVar[Optional[CometTracer]] = ContextVar(  # noqa: E501
@@ -27,6 +33,7 @@ comet_tracing_callback_var: ContextVar[Optional[CometTracer]] = ContextVar(  # n
 )
 
 register_configure_hook(openai_callback_var, True)
+register_configure_hook(bedrock_anthropic_callback_var, True)
 register_configure_hook(
     wandb_tracing_callback_var, True, WandbTracer, "LANGCHAIN_WANDB_TRACING"
 )
@@ -53,6 +60,27 @@ def get_openai_callback() -> Generator[OpenAICallbackHandler, None, None]:
     openai_callback_var.set(None)
 
 
+@contextmanager
+def get_bedrock_anthropic_callback() -> (
+    Generator[BedrockAnthropicTokenUsageCallbackHandler, None, None]
+):
+    """Get the Bedrock anthropic callback handler in a context manager.
+    which conveniently exposes token and cost information.
+
+    Returns:
+        BedrockAnthropicTokenUsageCallbackHandler:
+            The Bedrock anthropic callback handler.
+
+    Example:
+        >>> with get_bedrock_anthropic_callback() as cb:
+        ...     # Use the Bedrock anthropic callback handler
+    """
+    cb = BedrockAnthropicTokenUsageCallbackHandler()
+    bedrock_anthropic_callback_var.set(cb)
+    yield cb
+    bedrock_anthropic_callback_var.set(None)
+
+
 @contextmanager
 def wandb_tracing_enabled(
     session_name: str = "default",

libs/community/langchain_community/callbacks/openai_info.py

@@ -17,6 +17,8 @@ MODEL_COST_PER_1K_TOKENS = {
     "gpt-4-1106-preview": 0.01,
     "gpt-4-0125-preview": 0.01,
     "gpt-4-turbo-preview": 0.01,
+    "gpt-4-turbo": 0.01,
+    "gpt-4-turbo-2024-04-09": 0.01,
     # GPT-4 output
     "gpt-4-completion": 0.06,
     "gpt-4-0314-completion": 0.06,
@@ -28,6 +30,8 @@ MODEL_COST_PER_1K_TOKENS = {
     "gpt-4-1106-preview-completion": 0.03,
     "gpt-4-0125-preview-completion": 0.03,
     "gpt-4-turbo-preview-completion": 0.03,
+    "gpt-4-turbo-completion": 0.03,
+    "gpt-4-turbo-2024-04-09-completion": 0.03,
     # GPT-3.5 input
     # gpt-3.5-turbo points at gpt-3.5-turbo-0613 until Feb 16, 2024.
     # Switches to gpt-3.5-turbo-0125 after.

libs/community/langchain_community/callbacks/streamlit/mutable_expander.py

@@ -9,14 +9,14 @@ if TYPE_CHECKING:
 
 
 class ChildType(Enum):
-    """The enumerator of the child type."""
+    """Enumerator of the child type."""
 
     MARKDOWN = "MARKDOWN"
     EXCEPTION = "EXCEPTION"
 
 
 class ChildRecord(NamedTuple):
-    """The child record as a NamedTuple."""
+    """Child record as a NamedTuple."""
 
     type: ChildType
     kwargs: Dict[str, Any]
@@ -24,7 +24,7 @@ class ChildRecord(NamedTuple):
 
 
 class MutableExpander:
-    """A Streamlit expander that can be renamed and dynamically expanded/collapsed."""
+    """Streamlit expander that can be renamed and dynamically expanded/collapsed."""
 
     def __init__(self, parent_container: DeltaGenerator, label: str, expanded: bool):
         """Create a new MutableExpander.
@@ -51,7 +51,7 @@ class MutableExpander:
 
     @property
     def label(self) -> str:
-        """The expander's label string."""
+        """Expander's label string."""
         return self._label
 
     @property

libs/community/langchain_community/callbacks/streamlit/streamlit_callback_handler.py

@@ -40,7 +40,7 @@ class LLMThoughtState(Enum):
 
 
 class ToolRecord(NamedTuple):
-    """The tool record as a NamedTuple."""
+    """Tool record as a NamedTuple."""
 
     name: str
     input_str: str

libs/community/langchain_community/chat_loaders/__init__.py

@@ -19,7 +19,48 @@ WhatsApp. The loaded chat messages can be used for fine-tuning models.
 """  # noqa: E501
 
 import importlib
-from typing import Any
+from typing import TYPE_CHECKING, Any
+
+if TYPE_CHECKING:
+    from langchain_community.chat_loaders.base import (
+        BaseChatLoader,  # noqa: F401
+    )
+    from langchain_community.chat_loaders.facebook_messenger import (
+        FolderFacebookMessengerChatLoader,  # noqa: F401
+        SingleFileFacebookMessengerChatLoader,  # noqa: F401
+    )
+    from langchain_community.chat_loaders.gmail import (
+        GMailLoader,  # noqa: F401
+    )
+    from langchain_community.chat_loaders.imessage import (
+        IMessageChatLoader,  # noqa: F401
+    )
+    from langchain_community.chat_loaders.langsmith import (
+        LangSmithDatasetChatLoader,  # noqa: F401
+        LangSmithRunChatLoader,  # noqa: F401
+    )
+    from langchain_community.chat_loaders.slack import (
+        SlackChatLoader,  # noqa: F401
+    )
+    from langchain_community.chat_loaders.telegram import (
+        TelegramChatLoader,  # noqa: F401
+    )
+    from langchain_community.chat_loaders.whatsapp import (
+        WhatsAppChatLoader,  # noqa: F401
+    )
+
+__all__ = [
+    "BaseChatLoader",
+    "FolderFacebookMessengerChatLoader",
+    "GMailLoader",
+    "IMessageChatLoader",
+    "LangSmithDatasetChatLoader",
+    "LangSmithRunChatLoader",
+    "SingleFileFacebookMessengerChatLoader",
+    "SlackChatLoader",
+    "TelegramChatLoader",
+    "WhatsAppChatLoader",
+]
 
 _module_lookup = {
     "BaseChatLoader": "langchain_community.chat_loaders.base",

libs/community/langchain_community/chat_message_histories/__init__.py

@@ -16,7 +16,96 @@
 """  # noqa: E501
 
 import importlib
-from typing import Any
+from typing import TYPE_CHECKING, Any
+
+if TYPE_CHECKING:
+    from langchain_community.chat_message_histories.astradb import (
+        AstraDBChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.cassandra import (
+        CassandraChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.cosmos_db import (
+        CosmosDBChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.dynamodb import (
+        DynamoDBChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.elasticsearch import (
+        ElasticsearchChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.file import (
+        FileChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.firestore import (
+        FirestoreChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.in_memory import (
+        ChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.momento import (
+        MomentoChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.mongodb import (
+        MongoDBChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.neo4j import (
+        Neo4jChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.postgres import (
+        PostgresChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.redis import (
+        RedisChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.rocksetdb import (
+        RocksetChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.singlestoredb import (
+        SingleStoreDBChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.sql import (
+        SQLChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.streamlit import (
+        StreamlitChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.tidb import (
+        TiDBChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.upstash_redis import (
+        UpstashRedisChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.xata import (
+        XataChatMessageHistory,  # noqa: F401
+    )
+    from langchain_community.chat_message_histories.zep import (
+        ZepChatMessageHistory,  # noqa: F401
+    )
+
+__all__ = [
+    "AstraDBChatMessageHistory",
+    "CassandraChatMessageHistory",
+    "ChatMessageHistory",
+    "CosmosDBChatMessageHistory",
+    "DynamoDBChatMessageHistory",
+    "ElasticsearchChatMessageHistory",
+    "FileChatMessageHistory",
+    "FirestoreChatMessageHistory",
+    "MomentoChatMessageHistory",
+    "MongoDBChatMessageHistory",
+    "Neo4jChatMessageHistory",
+    "PostgresChatMessageHistory",
+    "RedisChatMessageHistory",
+    "RocksetChatMessageHistory",
+    "SQLChatMessageHistory",
+    "SingleStoreDBChatMessageHistory",
+    "StreamlitChatMessageHistory",
+    "TiDBChatMessageHistory",
+    "UpstashRedisChatMessageHistory",
+    "XataChatMessageHistory",
+    "ZepChatMessageHistory",
+]
 
 _module_lookup = {
     "AstraDBChatMessageHistory": "langchain_community.chat_message_histories.astradb",