Merge branch 'master' into wip-v0.4

CLAUDE.md

@@ -0,0 +1,325 @@
+# Global Development Guidelines for LangChain Projects
+
+## Core Development Principles
+
+### 1. Maintain Stable Public Interfaces ⚠️ CRITICAL
+
+**Always attempt to preserve function signatures, argument positions, and names for exported/public methods.**
+
+❌ **Bad - Breaking Change:**
+
+```python
+def get_user(id, verbose=False):  # Changed from `user_id`
+    pass
+```
+
+✅ **Good - Stable Interface:**
+
+```python
+def get_user(user_id: str, verbose: bool = False) -> User:
+    """Retrieve user by ID with optional verbose output."""
+    pass
+```
+
+**Before making ANY changes to public APIs:**
+
+- Check if the function/class is exported in `__init__.py`
+- Look for existing usage patterns in tests and examples
+- Use keyword-only arguments for new parameters: `*, new_param: str = "default"`
+- Mark experimental features clearly with docstring warnings (using reStructuredText, like `.. warning::`)
+
+🧠 *Ask yourself:* "Would this change break someone's code if they used it last week?"
+
+### 2. Code Quality Standards
+
+**All Python code MUST include type hints and return types.**
+
+❌ **Bad:**
+
+```python
+def p(u, d):
+    return [x for x in u if x not in d]
+```
+
+✅ **Good:**
+
+```python
+def filter_unknown_users(users: list[str], known_users: set[str]) -> list[str]:
+    """Filter out users that are not in the known users set.
+
+    Args:
+        users: List of user identifiers to filter.
+        known_users: Set of known/valid user identifiers.
+
+    Returns:
+        List of users that are not in the known_users set.
+    """
+    return [user for user in users if user not in known_users]
+```
+
+**Style Requirements:**
+
+- Use descriptive, **self-explanatory variable names**. Avoid overly short or cryptic identifiers.
+- Attempt to break up complex functions (>20 lines) into smaller, focused functions where it makes sense
+- Avoid unnecessary abstraction or premature optimization
+- Follow existing patterns in the codebase you're modifying
+
+### 3. Testing Requirements
+
+**Every new feature or bugfix MUST be covered by unit tests.**
+
+**Test Organization:**
+
+- Unit tests: `tests/unit_tests/` (no network calls allowed)
+- Integration tests: `tests/integration_tests/` (network calls permitted)
+- Use `pytest` as the testing framework
+
+**Test Quality Checklist:**
+
+- [ ] Tests fail when your new logic is broken
+- [ ] Happy path is covered
+- [ ] Edge cases and error conditions are tested
+- [ ] Use fixtures/mocks for external dependencies
+- [ ] Tests are deterministic (no flaky tests)
+
+Checklist questions:
+
+- [ ] Does the test suite fail if your new logic is broken?
+- [ ] Are all expected behaviors exercised (happy path, invalid input, etc)?
+- [ ] Do tests use fixtures or mocks where needed?
+
+```python
+def test_filter_unknown_users():
+    """Test filtering unknown users from a list."""
+    users = ["alice", "bob", "charlie"]
+    known_users = {"alice", "bob"}
+
+    result = filter_unknown_users(users, known_users)
+
+    assert result == ["charlie"]
+    assert len(result) == 1
+```
+
+### 4. Security and Risk Assessment
+
+**Security Checklist:**
+
+- No `eval()`, `exec()`, or `pickle` on user-controlled input
+- Proper exception handling (no bare `except:`) and use a `msg` variable for error messages
+- Remove unreachable/commented code before committing
+- Race conditions or resource leaks (file handles, sockets, threads).
+- Ensure proper resource cleanup (file handles, connections)
+
+❌ **Bad:**
+
+```python
+def load_config(path):
+    with open(path) as f:
+        return eval(f.read())  # ⚠️ Never eval config
+```
+
+✅ **Good:**
+
+```python
+import json
+
+def load_config(path: str) -> dict:
+    with open(path) as f:
+        return json.load(f)
+```
+
+### 5. Documentation Standards
+
+**Use Google-style docstrings with Args section for all public functions.**
+
+❌ **Insufficient Documentation:**
+
+```python
+def send_email(to, msg):
+    """Send an email to a recipient."""
+```
+
+✅ **Complete Documentation:**
+
+```python
+def send_email(to: str, msg: str, *, priority: str = "normal") -> bool:
+    """
+    Send an email to a recipient with specified priority.
+
+    Args:
+        to: The email address of the recipient.
+        msg: The message body to send.
+        priority: Email priority level (``'low'``, ``'normal'``, ``'high'``).
+
+    Returns:
+        True if email was sent successfully, False otherwise.
+
+    Raises:
+        InvalidEmailError: If the email address format is invalid.
+        SMTPConnectionError: If unable to connect to email server.
+    """
+```
+
+**Documentation Guidelines:**
+
+- Types go in function signatures, NOT in docstrings
+- Focus on "why" rather than "what" in descriptions
+- Document all parameters, return values, and exceptions
+- Keep descriptions concise but clear
+- Use reStructuredText for docstrings to enable rich formatting
+
+📌 *Tip:* Keep descriptions concise but clear. Only document return values if non-obvious.
+
+### 6. Architectural Improvements
+
+**When you encounter code that could be improved, suggest better designs:**
+
+❌ **Poor Design:**
+
+```python
+def process_data(data, db_conn, email_client, logger):
+    # Function doing too many things
+    validated = validate_data(data)
+    result = db_conn.save(validated)
+    email_client.send_notification(result)
+    logger.log(f"Processed {len(data)} items")
+    return result
+```
+
+✅ **Better Design:**
+
+```python
+@dataclass
+class ProcessingResult:
+    """Result of data processing operation."""
+    items_processed: int
+    success: bool
+    errors: List[str] = field(default_factory=list)
+
+class DataProcessor:
+    """Handles data validation, storage, and notification."""
+
+    def __init__(self, db_conn: Database, email_client: EmailClient):
+        self.db = db_conn
+        self.email = email_client
+
+    def process(self, data: List[dict]) -> ProcessingResult:
+        """Process and store data with notifications."""
+        validated = self._validate_data(data)
+        result = self.db.save(validated)
+        self._notify_completion(result)
+        return result
+```
+
+**Design Improvement Areas:**
+
+If there's a **cleaner**, **more scalable**, or **simpler** design, highlight it and suggest improvements that would:
+
+- Reduce code duplication through shared utilities
+- Make unit testing easier
+- Improve separation of concerns (single responsibility)
+- Make unit testing easier through dependency injection
+- Add clarity without adding complexity
+- Prefer dataclasses for structured data
+
+## Development Tools & Commands
+
+### Package Management
+
+```bash
+# Add package
+uv add package-name
+
+# Sync project dependencies
+uv sync
+uv lock
+```
+
+### Testing
+
+```bash
+# Run unit tests (no network)
+make test
+
+# Don't run integration tests, as API keys must be set
+
+# Run specific test file
+uv run --group test pytest tests/unit_tests/test_specific.py
+```
+
+### Code Quality
+
+```bash
+# Lint code
+make lint
+
+# Format code
+make format
+
+# Type checking
+uv run --group lint mypy .
+```
+
+### Dependency Management Patterns
+
+**Local Development Dependencies:**
+
+```toml
+[tool.uv.sources]
+langchain-core = { path = "../core", editable = true }
+langchain-tests = { path = "../standard-tests", editable = true }
+```
+
+**For tools, use the `@tool` decorator from `langchain_core.tools`:**
+
+```python
+from langchain_core.tools import tool
+
+@tool
+def search_database(query: str) -> str:
+    """Search the database for relevant information.
+
+    Args:
+        query: The search query string.
+    """
+    # Implementation here
+    return results
+```
+
+## Commit Standards
+
+**Use Conventional Commits format for PR titles:**
+
+- `feat(core): add multi-tenant support`
+- `fix(cli): resolve flag parsing error`
+- `docs: update API usage examples`
+- `docs(openai): update API usage examples`
+
+## Framework-Specific Guidelines
+
+- Follow the existing patterns in `langchain-core` for base abstractions
+- Use `langchain_core.callbacks` for execution tracking
+- Implement proper streaming support where applicable
+- Avoid deprecated components like legacy `LLMChain`
+
+### Partner Integrations
+
+- Follow the established patterns in existing partner libraries
+- Implement standard interfaces (`BaseChatModel`, `BaseEmbeddings`, etc.)
+- Include comprehensive integration tests
+- Document API key requirements and authentication
+
+---
+
+## Quick Reference Checklist
+
+Before submitting code changes:
+
+- [ ] **Breaking Changes**: Verified no public API changes
+- [ ] **Type Hints**: All functions have complete type annotations
+- [ ] **Tests**: New functionality is fully tested
+- [ ] **Security**: No dangerous patterns (eval, silent failures, etc.)
+- [ ] **Documentation**: Google-style docstrings for public functions
+- [ ] **Code Quality**: `make lint` and `make format` pass
+- [ ] **Architecture**: Suggested improvements where applicable
+- [ ] **Commit Message**: Follows Conventional Commits format

docs/docs/concepts/tools.mdx

@@ -89,7 +89,7 @@ Please see the [API reference for @tool](https://python.langchain.com/api_refere
 
 ## Tool artifacts
 
-**Tools** are utilities that can be called by a model, and whose outputs are designed to be fed back to a model. Sometimes, however, there are artifacts of a tool's execution that we want to make accessible to downstream components in our chain or agent, but that we don't want to expose to the model itself. For example if a tool returns a custom object, a dataframe or an image, we may want to pass some metadata about this output to the model without passing the actual output to the model. At the same time, we may want to be able to access this full output elsewhere, for example in downstream tools.
+**Tools** are utilities that can be called by a model, and whose outputs are designed to be fed back to a model. Sometimes, however, there are artifacts of a tool's execution that we want to make accessible to downstream components in our chain or agent, but that we don't want to expose to the model itself. For example if a tool returns a custom object, a dataframe or an image, we may want to pass some metadata about this output to the model without passing the actual output. At the same time, we may want to be able to access this full output elsewhere, for example in downstream tools.
 
 ```python
 @tool(response_format="content_and_artifact")

docs/docs/integrations/chat/google_vertex_ai_palm.ipynb

@@ -45,7 +45,7 @@
     "\n",
     "### Credentials\n",
     "\n",
-    "To use the integration you must:\n",
+    "To use the integration you must either:\n",
     "- Have credentials configured for your environment (gcloud, workload identity, etc...)\n",
     "- Store the path to a service account JSON file as the GOOGLE_APPLICATION_CREDENTIALS environment variable\n",
     "\n",

docs/docs/integrations/chat/gradientai.ipynb

@@ -0,0 +1,298 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "afaf8039",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "---\n",
+    "sidebar_label: DigitalOcean Gradient\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e49f1e0d",
+   "metadata": {},
+   "source": [
+    "# ChatGradient\n",
+    "\n",
+    "This will help you getting started with DigitalOcean Gradient Chat Models.\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |\n",
+    "| [DigitalOcean Gradient](https://python.langchain.com/docs/api_reference/llms/langchain_gradient.llms.LangchainGradient/) | [langchain-gradient](https://python.langchain.com/docs/api_reference/langchain-gradient_api_reference/) | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-gradient?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-gradient?style=flat-square&label=%20) |\n",
+    "\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "langchain-gradient uses DigitalOcean Gradient Platform.  \n",
+    "\n",
+    "Create an account on DigitalOcean, acquire a `DIGITALOCEAN_INFERENCE_KEY` API key from the Gradient Platform, and install the `langchain-gradient` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "Head to [DigitalOcean Login](https://cloud.digitalocean.com/login) \n",
+    "\n",
+    "1. Sign up/Login to DigitalOcean Cloud Console\n",
+    "2. Go to the Gradient Platform and navigate to Serverless Inference.\n",
+    "3. Click on Create model access key, enter a name, and create the key.\n",
+    "\n",
+    "Once you've done this set the `DIGITALOCEAN_INFERENCE_KEY` environment variable:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "if not os.getenv(\"DIGITALOCEAN_INFERENCE_KEY\"):\n",
+    "    os.environ[\"DIGITALOCEAN_INFERENCE_KEY\"] = getpass.getpass(\n",
+    "        \"Enter your DIGITALOCEAN_INFERENCE_KEY API key: \"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\"\n",
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The DigitalOcean Gradient integration lives in the `langchain-gradient` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m24.0\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m25.1.1\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip3.12 install --upgrade pip\u001b[0m\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "%pip install -qU langchain-gradient"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_gradient import ChatGradient\n",
+    "\n",
+    "llm = ChatGradient(\n",
+    "    model=\"llama3.3-70b-instruct\",\n",
+    "    # other params...\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2b4f3e15",
+   "metadata": {},
+   "source": [
+    "## Invocation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "62e0dbc3",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"...that had been hidden away for centuries, nestled amongst the twisted roots of an ancient tree. As soon as Mira's fingers made contact with the stone, she felt an sudden surge of energy course through her veins, like a river bursting its banks. The stone, which had been dull and lifeless just moments before, now pulsed with a soft, ethereal light, as if it had been awakened by Mira's touch.\\n\\nIntrigued, Mira turned the stone over in her hand, studying it from every angle. The light emanating from it cast eerie shadows on the trees around her, making her feel as though she was standing at the threshold of a secret world. As she gazed deeper into the stone, she began to notice that the glow was not just a random color, but a deep, rich blue that seemed to be calling to her.\\n\\nWithout thinking, Mira felt an overwhelming urge to follow the stone's gentle glow, which seemed to be leading her deeper into the mysterious forest. The trees loomed above her, their branches creaking and swaying in the wind, as if they too were urging her onward. The air was filled with the sweet scent of wildflowers and the soft hooting of owls, creating a sense of enchantment that was both exhilarating and unsettling.\\n\\nAs Mira wandered deeper into the forest, the stone's light grew brighter, illuminating a winding path that was all but invisible in the fading light of day. The trees grew taller and closer together here, forming a tunnel of foliage that seemed to be guiding her towards a hidden destination. Mira's heart pounded with excitement and a hint of fear, as she realized that she was being drawn into a world that was both magical and unknown.\\n\\nSuddenly, the trees parted, and Mira found herself standing at the edge of a clearing, surrounded by a ring of towering mushrooms that glowed with a soft, luminescent light. The air was filled with a faint humming noise, like the buzzing of a thousand bees, and the stone in her hand pulsed with an otherworldly energy. In the center of the clearing stood an enormous tree, its trunk twisted and gnarled with age, its branches reaching up towards the stars like a Nature's own cathedral.\\n\\nMira felt a sense of awe wash over her, as she approached the tree, the stone still clutched in her hand. She could feel the magic of the forest pulsing through her, calling to her, drawing her closer to the heart of the mystery. And as she reached out to touch the trunk of the tree, the stone's glow surged to a brilliant intensity, illuminating a doorway that had been hidden in the trunk all along...\", additional_kwargs={}, response_metadata={'finish_reason': 'stop'}, id='run--593a6940-4c76-413b-bed9-1fd94f91c6c1-0', usage_metadata={'input_tokens': 82, 'output_tokens': 555, 'total_tokens': 637})"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = [\n",
+    "    (\n",
+    "        \"system\",\n",
+    "        \"You are a creative storyteller. Continue any story prompt you receive in an engaging and imaginative way.\",\n",
+    "    ),\n",
+    "    (\n",
+    "        \"human\",\n",
+    "        \"Once upon a time, in a village at the edge of a mysterious forest, a young girl named Mira found a glowing stone...\",\n",
+    "    ),\n",
+    "]\n",
+    "ai_msg = llm.invoke(messages)\n",
+    "ai_msg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "...that had been hidden away for centuries, nestled amongst the twisted roots of an ancient tree. As soon as Mira's fingers made contact with the stone, she felt an sudden surge of energy course through her veins, like a river bursting its banks. The stone, which had been dull and lifeless just moments before, now pulsed with a soft, ethereal light, as if it had been awakened by Mira's touch.\n",
+      "\n",
+      "Intrigued, Mira turned the stone over in her hand, studying it from every angle. The light emanating from it cast eerie shadows on the trees around her, making her feel as though she was standing at the threshold of a secret world. As she gazed deeper into the stone, she began to notice that the glow was not just a random color, but a deep, rich blue that seemed to be calling to her.\n",
+      "\n",
+      "Without thinking, Mira felt an overwhelming urge to follow the stone's gentle glow, which seemed to be leading her deeper into the mysterious forest. The trees loomed above her, their branches creaking and swaying in the wind, as if they too were urging her onward. The air was filled with the sweet scent of wildflowers and the soft hooting of owls, creating a sense of enchantment that was both exhilarating and unsettling.\n",
+      "\n",
+      "As Mira wandered deeper into the forest, the stone's light grew brighter, illuminating a winding path that was all but invisible in the fading light of day. The trees grew taller and closer together here, forming a tunnel of foliage that seemed to be guiding her towards a hidden destination. Mira's heart pounded with excitement and a hint of fear, as she realized that she was being drawn into a world that was both magical and unknown.\n",
+      "\n",
+      "Suddenly, the trees parted, and Mira found herself standing at the edge of a clearing, surrounded by a ring of towering mushrooms that glowed with a soft, luminescent light. The air was filled with a faint humming noise, like the buzzing of a thousand bees, and the stone in her hand pulsed with an otherworldly energy. In the center of the clearing stood an enormous tree, its trunk twisted and gnarled with age, its branches reaching up towards the stars like a Nature's own cathedral.\n",
+      "\n",
+      "Mira felt a sense of awe wash over her, as she approached the tree, the stone still clutched in her hand. She could feel the magic of the forest pulsing through her, calling to her, drawing her closer to the heart of the mystery. And as she reached out to touch the trunk of the tree, the stone's glow surged to a brilliant intensity, illuminating a doorway that had been hidden in the trunk all along...\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(ai_msg.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "We can chain our model with a prompt template like so:\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='The Eiffel Tower was designed by Gustave Eiffel\\'s engineering company and was completed in 1889. (Sentence: \"It was designed by Gustave Eiffel\\'s engineering company. The tower is one of the most recognizable structures in the world. ...  The Eiffel Tower is located in Paris and was completed in 1889.\")', additional_kwargs={}, response_metadata={'finish_reason': 'stop'}, id='run--c23ffab6-06ae-4130-87b1-d5b2e7744906-0', usage_metadata={'input_tokens': 153, 'output_tokens': 74, 'total_tokens': 227})"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            'You are a knowledgeable assistant. Carefully read the provided context and answer the user\\'s question. If the answer is present in the context, cite the relevant sentence. If not, reply with \"Not found in context.\"',\n",
+    "        ),\n",
+    "        (\"human\", \"Context: {context}\\nQuestion: {question}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"context\": (\n",
+    "            \"The Eiffel Tower is located in Paris and was completed in 1889. \"\n",
+    "            \"It was designed by Gustave Eiffel's engineering company. \"\n",
+    "            \"The tower is one of the most recognizable structures in the world. \"\n",
+    "            \"The Statue of Liberty was a gift from France to the United States.\"\n",
+    "        ),\n",
+    "        \"question\": \"Who designed the Eiffel Tower and when was it completed?\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8a6660e4",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all ChatGradient features and configurations head to the API reference."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/providers/gradientai.mdx

@@ -0,0 +1,95 @@
+# ChatGradient
+
+This will help you getting started with DigitalOcean Gradient [chat models](/docs/concepts/chat_models).
+
+## Overview
+### Integration details
+
+| Class | Package | Package downloads | Package latest |
+| :--- | :--- | :---: | :---: |
+| [ChatGradient](https://python.langchain.com/api_reference/langchain-gradient/chat_models/langchain_gradient.chat_models.ChatGradient.html) | [langchain-gradient](https://python.langchain.com/api_reference/langchain-gradient/) | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-gradient?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-gradient?style=flat-square&label=%20) |
+
+
+## Setup
+
+langchain-gradient uses DigitalOcean Gradient Platform.
+
+Create an account on DigitalOcean, acquire a `DIGITALOCEAN_INFERENCE_KEY` API key from the Gradient Platform, and install the `langchain-gradient` integration package.
+
+### Credentials
+
+Head to [DigitalOcean Gradient](https://www.digitalocean.com/products/gradient)
+
+1. Sign up/Login to DigitalOcean Cloud Console
+2. Go to the Gradient Platform and navigate to Serverless Inference.
+3. Click on Create model access key, enter a name, and create the key.
+
+Once you've done this set the `DIGITALOCEAN_INFERENCE_KEY` environment variable:
+
+```python
+import os
+os.environ["DIGITALOCEAN_INFERENCE_KEY"] = "your-api-key"
+```
+
+### Installation
+
+The LangChain Gradient integration is in the `langchain-gradient` package:
+
+```bash
+pip install -qU langchain-gradient
+```
+
+## Instantiation
+
+```python
+from langchain_gradient import ChatGradient
+
+llm = ChatGradient(
+    model="llama3.3-70b-instruct",
+    api_key=os.environ.get("DIGITALOCEAN_INFERENCE_KEY")
+)
+```
+
+## Invocation
+
+```python
+messages = [
+    (
+        "system",
+        "You are a creative storyteller. Continue any story prompt you receive in an engaging and imaginative way.",
+    ),
+    ("human", "Once upon a time, in a village at the edge of a mysterious forest, a young girl named Mira found a glowing stone..."),
+]
+ai_msg = llm.invoke(messages)
+ai_msg
+print(ai_msg.content)
+```
+
+## Chaining
+
+```python
+from langchain_core.prompts import ChatPromptTemplate
+
+prompt = ChatPromptTemplate(
+    [
+        (
+            "system",
+            "You are a knowledgeable assistant. Carefully read the provided context and answer the user's question. If the answer is present in the context, cite the relevant sentence. If not, reply with \"Not found in context.\"",
+        ),
+        ("human", "Context: {context}\nQuestion: {question}"),
+    ]
+)
+
+chain = prompt | llm
+chain.invoke(
+    {
+        "context": (
+            "The Eiffel Tower is located in Paris and was completed in 1889. "
+            "It was designed by Gustave Eiffel's engineering company. "
+            "The tower is one of the most recognizable structures in the world. "
+            "The Statue of Liberty was a gift from France to the United States."
+        ),
+        "question": "Who designed the Eiffel Tower and when was it completed?"
+    }
+)
+```

docs/docs/integrations/providers/portkey/logging_tracing_portkey.ipynb

@@ -235,7 +235,7 @@
     "\n",
     "**Retries**\n",
     "\n",
-    "Automatically reprocess any unsuccessful API requests **`upto 5`** times. Uses an **`exponential backoff`** strategy, which spaces out retry attempts to prevent network overload.[Docs](https://portkey.ai/docs/product/ai-gateway-streamline-llm-integrations)\n",
+    "Automatically reprocess any unsuccessful API requests **`upto 5`** times. Uses an **`exponential backoff`** strategy, which spaces out retry attempts to prevent network overload. [Docs](https://portkey.ai/docs/product/ai-gateway-streamline-llm-integrations)\n",
     "\n",
     "**Tagging**\n",
     "\n",

docs/docs/integrations/tools/alpha_vantage.ipynb

@@ -9,7 +9,9 @@
    "source": [
     "# Alpha Vantage\n",
     "\n",
-    ">[Alpha Vantage](https://www.alphavantage.co) Alpha Vantage provides realtime and historical financial market data through a set of powerful and developer-friendly data APIs and spreadsheets. \n",
+    ">[Alpha Vantage](https://www.alphavantage.co) Alpha Vantage provides realtime and historical financial market data through a set of powerful and developer-friendly data APIs and spreadsheets.\n",
+    "\n",
+    "Generate the `ALPHAVANTAGE_API_KEY` [at their website](https://www.alphavantage.co/support/#api-key)\n.",
     "\n",
     "Use the ``AlphaVantageAPIWrapper`` to get currency exchange rates."
    ]

docs/docs/integrations/tools/google_imagen.ipynb

@@ -25,7 +25,7 @@
     "- [VertexAIImageEditorChat](#image-editing) : Edit an entire uploaded or generated image with a text prompt.\n",
     "- [VertexAIImageCaptioning](#image-captioning) : Get text descriptions of images with visual captioning.\n",
     "- [VertexAIVisualQnAChat](#visual-question-answering-vqa) : Get answers to a question about an image with Visual Question Answering (VQA).\n",
-    "    * NOTE : Currently we support only only single-turn chat for Visual QnA (VQA)"
+    "    * NOTE : Currently we support only single-turn chat for Visual QnA (VQA)"
    ]
   },
   {
@@ -48,11 +48,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Create Image Gentation model Object\n",
+    "# Create Image Generation model Object\n",
     "generator = VertexAIImageGeneratorChat()"
    ]
   },
@@ -140,11 +140,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Create Image Gentation model Object\n",
+    "# Create Image Generation model Object\n",
     "generator = VertexAIImageGeneratorChat()\n",
     "\n",
     "# Provide a text input for image\n",
@@ -244,7 +244,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -268,10 +268,10 @@
     }
    ],
    "source": [
-    "# use image egenarted in Image Generation Section\n",
+    "# use image generated in Image Generation Section\n",
     "img_base64 = generated_image[\"image_url\"][\"url\"]\n",
     "response = model.invoke(img_base64)\n",
-    "print(f\"Generated Cpation : {response}\")\n",
+    "print(f\"Generated Caption : {response}\")\n",
     "\n",
     "# Convert base64 string to Image\n",
     "img = Image.open(\n",

docs/scripts/kv_store_feat_table.py

@@ -30,49 +30,50 @@ The following table shows information on all available key-value stores.
 
 KV_STORE_FEAT_TABLE = {
     "AstraDBByteStore": {
-        "class": "[AstraDBByteStore](https://python.langchain.com/api_reference/astradb/storage/langchain_astradb.storage.AstraDBByteStore.html)",
+        "class": "[AstraDBByteStore](https://python.langchain.com/docs/integrations/stores/astradb/)",
         "local": False,
-        "package": "[langchain_astradb](https://python.langchain.com/api_reference/astradb/)",
+        "package": "[langchain-astradb](https://python.langchain.com/api_reference/astradb/storage/langchain_astradb.storage.AstraDBByteStore.html)",
         "downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_astradb?style=flat-square&label=%20)",
     },
     "CassandraByteStore": {
-        "class": "[CassandraByteStore](https://python.langchain.com/api_reference/community/storage/langchain_community.storage.cassandra.CassandraByteStore.html)",
+        "class": "[CassandraByteStore](https://python.langchain.com/docs/integrations/stores/cassandra/)",
         "local": False,
-        "package": "[langchain_community](https://python.langchain.com/api_reference/community/)",
+        "package": "[langchain-community](https://python.langchain.com/api_reference/community/storage/langchain_community.storage.cassandra.CassandraByteStore.html)",
         "downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20)",
     },
     "ElasticsearchEmbeddingsCache": {
-        "class": "[ElasticsearchEmbeddingsCache](https://python.langchain.com/api_reference/elasticsearch/cache/langchain_elasticsearch.cache.ElasticsearchEmbeddingsCache.html)",
+        "class": "[ElasticsearchEmbeddingsCache](https://python.langchain.com/docs/integrations/stores/elasticsearch/)",
         "local": True,
-        "package": "[langchain_elasticsearch](https://python.langchain.com/api_reference/elasticsearch/)",
+        "package": "[langchain-elasticsearch](https://python.langchain.com/api_reference/elasticsearch/cache/langchain_elasticsearch.cache.ElasticsearchEmbeddingsCache.html)",
         "downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_elasticsearch?style=flat-square&label=%20)",
     },
     "LocalFileStore": {
-        "class": "[LocalFileStore](https://python.langchain.com/api_reference/storage/langchain.storage.file_system.LocalFileStore.html)",
+        "class": "[LocalFileStore](https://python.langchain.com/docs/integrations/stores/file_system/)",
         "local": True,
-        "package": "[langchain](https://python.langchain.com/api_reference/langchain/)",
+        "package": "[langchain](https://python.langchain.com/api_reference/langchain/storage/langchain.storage.file_system.LocalFileStore.html)",
         "downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain?style=flat-square&label=%20)",
     },
     "InMemoryByteStore": {
-        "class": "[InMemoryByteStore](https://python.langchain.com/api_reference/core/stores/langchain_core.stores.InMemoryByteStore.html)",
+        "class": "[InMemoryByteStore](https://python.langchain.com/docs/integrations/stores/in_memory/)",
         "local": True,
-        "package": "[langchain_core](https://python.langchain.com/api_reference/core/)",
+        "package": "[langchain-core](https://python.langchain.com/api_reference/core/stores/langchain_core.stores.InMemoryByteStore.html)",
         "downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_core?style=flat-square&label=%20)",
     },
     "RedisStore": {
-        "class": "[RedisStore](https://python.langchain.com/api_reference/community/storage/langchain_community.storage.redis.RedisStore.html)",
+        "class": "[RedisStore](https://python.langchain.com/docs/integrations/stores/redis/)",
         "local": True,
-        "package": "[langchain_community](https://python.langchain.com/api_reference/community/)",
+        "package": "[langchain-community](https://python.langchain.com/api_reference/community/storage/langchain_community.storage.redis.RedisStore.html)",
         "downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20)",
     },
     "UpstashRedisByteStore": {
-        "class": "[UpstashRedisByteStore](https://python.langchain.com/api_reference/community/storage/langchain_community.storage.upstash_redis.UpstashRedisByteStore.html)",
+        "class": "[UpstashRedisByteStore](https://python.langchain.com/docs/integrations/stores/upstash_redis/)",
         "local": False,
-        "package": "[langchain_community](https://python.langchain.com/api_reference/community/)",
+        "package": "[langchain-community](https://python.langchain.com/api_reference/community/storage/langchain_community.storage.upstash_redis.UpstashRedisByteStore.html)",
         "downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20)",
     },
 }
 
+
 DEPRECATED = []
 
 

docs/src/theme/FeatureTables.js

@@ -435,7 +435,7 @@ const FEATURE_TABLES = {
                 selfHost: false,
                 cloudOffering: true,
                 apiLink: "https://python.langchain.com/api_reference/aws/retrievers/langchain_aws.retrievers.bedrock.AmazonKnowledgeBasesRetriever.html",
-                package: "langchain_aws"
+                package: "langchain-aws"
             },
             {
                 name: "AzureAISearchRetriever",
@@ -443,7 +443,7 @@ const FEATURE_TABLES = {
                 selfHost: false,
                 cloudOffering: true,
                 apiLink: "https://python.langchain.com/api_reference/community/retrievers/langchain_community.retrievers.azure_ai_search.AzureAISearchRetriever.html",
-                package: "langchain_community"
+                package: "langchain-community"
             },
             {
                 name: "ElasticsearchRetriever",
@@ -451,7 +451,7 @@ const FEATURE_TABLES = {
                 selfHost: true,
                 cloudOffering: true,
                 apiLink: "https://python.langchain.com/api_reference/elasticsearch/retrievers/langchain_elasticsearch.retrievers.ElasticsearchRetriever.html",
-                package: "langchain_elasticsearch"
+                package: "langchain-elasticsearch"
             },
             {
                 name: "VertexAISearchRetriever",
@@ -459,7 +459,7 @@ const FEATURE_TABLES = {
                 selfHost: false,
                 cloudOffering: true,
                 apiLink: "https://python.langchain.com/api_reference/google_community/vertex_ai_search/langchain_google_community.vertex_ai_search.VertexAISearchRetriever.html",
-                package: "langchain_google_community"
+                package: "langchain-google-community"
             }
         ],
     },
@@ -484,21 +484,21 @@ const FEATURE_TABLES = {
                 link: "arxiv",
                 source: (<>Scholarly articles on <a href="https://arxiv.org/">arxiv.org</a></>),
                 apiLink: "https://python.langchain.com/api_reference/community/retrievers/langchain_community.retrievers.arxiv.ArxivRetriever.html",
-                package: "langchain_community"
+                package: "langchain-community"
             },
             {
                 name: "TavilySearchAPIRetriever",
                 link: "tavily",
                 source: "Internet search",
                 apiLink: "https://python.langchain.com/api_reference/community/retrievers/langchain_community.retrievers.tavily_search_api.TavilySearchAPIRetriever.html",
-                package: "langchain_community"
+                package: "langchain-community"
             },
             {
                 name: "WikipediaRetriever",
                 link: "wikipedia",
                 source: (<><a href="https://www.wikipedia.org/">Wikipedia</a> articles</>),
                 apiLink: "https://python.langchain.com/api_reference/community/retrievers/langchain_community.retrievers.wikipedia.WikipediaRetriever.html",
-                package: "langchain_community"
+                package: "langchain-community"
             }
         ]
 

libs/packages.yml

@@ -696,3 +696,6 @@ packages:
 - name: langchain-tensorlake
   path: .
   repo: tensorlakeai/langchain-tensorlake
+- name: langchain-gradient
+  path: .
+  repo: digitalocean/langchain-gradient