Langchain documentation In Agents, a language model is used as a reasoning engine to determine which actions to take and in which order. Components Integrations Guides API Reference from langchain_community. Section Navigation. transformers. The universal invocation protocol (Runnables) along with a syntax for combining components (LangChain Expression Language) are also defined here. Amazon DocumentDB (with MongoDB Compatibility) makes it easy to set up, operate, and scale MongoDB-compatible databases in the cloud. output_parsers import StrOutputParser from langchain_core. loading. Tools are classes that an Agent uses to interact with the world. Integration packages: Third-party packages that integrate with LangChain. This will still result in the correct end state of the index, but will unfortunately not be 100% efficient. New in version 0. 1, LangChain is a framework for developing applications powered by language models. May 2, 2025 · Documentation; End-to-end Example: Chat LangChain and repo; 🧱 Extracting structured output. com , this comprehensive resource serves as the primary user-facing documentation. LangChain's products work seamlessly together to provide an integrated solution for every step of the application development journey. These providers have standalone langchain-{provider} packages for improved versioning, dependency management and testing. Philosophy LangChain's documentation follows the Diataxis framework. combined. Document [source] # Bases: BaseMedia. The LangChain community in Seoul is excited to announce the LangChain OpenTutorial, a brand-new resource designed for everyone. configurable_alternatives (ConfigurableField (id = "llm"), default_key = "anthropic", openai = ChatOpenAI ()) # uses the default model Use document loaders to load data from a source as Document's. These are the core chains for working with Documents. , a tool to run). This is a reference for all langchain-x packages. The Docusaurus configuration supports multiple content types including MDX files, Jupyter notebooks, and automatically generated API documentation. As LangChain continues to grow, the amount of documentation required to cover the various concepts and integrations continues to grow too. Examples using RecursiveCharacterTextSplitter. chain_extract. 🗃️ Retrievers. Feb 6, 2025 · Why is LangChain Important? LangChain helps manage complex workflows, making it easier to integrate LLMs into various applications like chatbots and document analysis. LangChain is a library that helps you combine large language models (LLMs) with other sources of computation or knowledge. HumanMessage: Represents a message from a human user. ) agents #. documents ¶ Document module is a collection of classes that handle documents and their transformations. ReadOnlySharedMemory. How to load PDFs. 5. Check out the docs for the latest version here . For example, if a given document is split into 15 chunks, and we index them using a batch size of 5, we’ll have 3 batches all with the same source id. Dec 9, 2024 · An optional identifier for the document. Now that we have this data indexed in a vectorstore, we will create a retrieval chain. Partner packages (e. Chat; ChatCompletion from langchain_anthropic import ChatAnthropic from langchain_core. Parameters: documents (Sequence) – kwargs (Any) – Return type: Sequence. Agents use language models to choose a sequence of actions to take. Learn how to use its modules, chains, agents, memory, and more for various use cases such as question answering, chatbots, and data augmented generation. See full list on github. Combining multiple memories' data together. com LangChain is an open-source framework for building with GenAI using flexible abstractions and AI-first toolkit. 87 items. Explore tutorials, how-to guides, conceptual introductions, API reference, and more. load_prompt (path[, encoding]) Unified method for loading a prompt from LangChainHub or local fs. Apache Cassandra. __call__ expects a single input dictionary with all the inputs The LangChain vectorstore class will automatically prepare each raw document using the embeddings model. This tutorial builds upon the foundation of the existing tutorial available here: link written in Korean. 🗃️ Vector stores. Documentation is a vital part of LangChain. Get setup with LangChain, LangSmith and LangServe; Use the most basic and common components of LangChain: prompt templates, models, and output parsers; Use LangChain Expression Language, the protocol that LangChain is built on and which facilitates component chaining; Build a simple application with LangChain; Trace your application with LangSmith LangChain Python API Reference; langchain-core: 0. prompt. You can peruse LangSmith tutorials here . It covers a wide array of topics, including tutorials, use cases, integrations, and more, offering extensive guidance on building with LangChain. LangChain documentation consists of two components: Main Documentation: Hosted at python. For example, there are document loaders for loading a simple . Documentation; End-to-end Example: Web LangChain (web researcher chatbot) and repo; 📖 Documentation. Document# class langchain_core. Developer's guide @langchain/community: Third party integrations. Head to the reference section for full documentation of all classes and methods in the LangChain and LangChain Experimental Python packages. Bases: StringPromptTemplate Prompt template for a language model. aformat_document (doc, prompt) Async format a document into a string based on a prompt template. Learn how to build and deploy applications powered by large language models (LLMs) using LangChain's open-source libraries and tools. They are useful for summarizing documents, answering questions over documents, extracting information from documents, and more. 🗃️ Document loaders. retrievers. For the legacy API reference hosted on ReadTheDocs see https: Documents. ChatBedrockConverse Bedrock chat model integration built on the Bedrock converse API. AINetworkToolkit. Document: LangChain's representation of a document. Please read the resources below before getting started: Documentation style guide; Setup prompts. Documentation; End-to-end Example: SQL Llama2 Template; 🤖 Chatbots. Dec 9, 2024 · langchain_core. amadeus. ApertureDB. document_loaders import WebBaseLoader from langchain_chroma import Chroma from langchain_core. We welcome both new documentation for new features and community improvements to our current documentation. This chain will take an incoming question, look up relevant documents, then pass those documents along with the original question into an LLM and ask it from langchain. NoOutputParser Adapter class to prepare the inputs from Langchain to prompt format that Chat model expects. Contributing Check out the developer's guide for guidelines on contributing and help getting your dev environment set up. Integration Packages . runnables. LLMChainExtractor. ” langchain-core defines the base abstractions for the LangChain ecosystem. With Amazon DocumentDB, you can run the same application code and use the same drivers and tools that you use with MongoDB. 1, which is Amazon Document DB. It seamlessly integrates with LangChain and LangGraph. configurable_alternatives (ConfigurableField (id = "llm"), default_key = "anthropic", openai = ChatOpenAI ()) # uses the default model LangChain provides a standard interface to interact with models and other components, useful for straight-forward chains and retrieval flows. html2text As LangChain continues to grow, the surface area of documentation required to cover it continues to grow too. Activeloop Deep Memory. document_transformers. 3 days ago · The documentation website is built using Docusaurus 3. LangSmith documentation is hosted on a separate site. The main difference between this method and Chain. 1, which is no longer actively maintained. base. Azure Cosmos DB No SQL. langchain. utils import ConfigurableField from langchain_openai import ChatOpenAI model = ChatAnthropic (model_name = "claude-3-sonnet-20240229"). document_compressors. This page provides guidelines for anyone writing documentation for LangChain, as well as some of our philosophies around organization and structure. Dec 9, 2024 · langchain 0. __call__ is that this method expects inputs to be passed directly in as positional arguments or keyword arguments, whereas Chain. Learn how to use langchain, a library for building language applications with LLMs and tools. agent_toolkits. It enables applications that: Are context-aware: connect a language model to sources of context (prompt instructions, few shot examples, content to ground its response in, etc. 🗃️ Embedding models from langchain_anthropic import ChatAnthropic from langchain_core. chains import (StuffDocumentsChain, LLMChain, ReduceDocumentsChain, MapReduceDocumentsChain,) from langchain_core. DocumentCompressorPipeline. You can peruse LangSmith how-to guides here, but we'll highlight a few sections that are particularly relevant to LangChain below: Evaluation LangChain is part of a rich ecosystem of tools that integrate with our framework and build on top of it. ): Some integrations have been further split into their own lightweight packages that only depend on @langchain/core. readonly. LangChain provides the smoothest path to high quality agents. compressor. input and output types: Types used for input and output in Runnables. js, and you can use it to inspect and debug individual steps of your chains as you build. llms import OpenAI # This controls how each document will be formatted. graph import START, StateGraph from typing_extensions import List, TypedDict # Load and chunk contents of the blog loader = WebBaseLoader This is a reference for all langchain-x packages. Chains are easily reusable components linked together. Learn how to use LangChain's components, integrations, and orchestration framework with tutorials, guides, and API reference. @langchain/openai, @langchain/anthropic, etc. InjectedStore: A store that can be injected into a tool for data persistence. chains #. documents. It seamlessly integrates with LangChain and LangGraph, and you can use it to inspect and debug individual steps of your chains and agents as you build. The interfaces for core components like chat models, LLMs, vector stores, retrievers, and more are defined here. memory. Core; Langchain; Text Splitters; Community. 65 items. Classes LangChain integrates with many providers. g. Portable Document Format (PDF), standardized as ISO 32000, is a file format developed by Adobe in 1992 to present documents, including text formatting and images, in a manner independent of application software, hardware, and operating systems. Embedding models: Models that generate vector embeddings for various data types. For the legacy API reference hosted on ReadTheDocs see https: This is a reference for all langchain-x packages. adapters. Please see here for full documentation on: “LangChain is streets ahead with what they've put forward with LangGraph. embeddings_redundant_filter langchain_community. This page provides guidelines for anyone writing documentation for LangChain and outlines some of our philosophies around organization and structure. 2. Class for storing a piece of text and associated metadata. . AmadeusToolkit Documentation Style Guide. prompts import PromptTemplate from langchain_community. Chains encode a sequence of calls to components like models, document retrievers, other Chains, etc. bedrock_converse. A basic agent works in the following manner: Given a prompt an agent uses an LLM to request an action to take (e. documents. InjectedState: A state injected into a tool function. PromptTemplate [source] #. The Chain interface makes it easy to create apps that are: This tutorial delves into LangChain, starting from an overview then providing practical examples. 118 items. google_translate langchain_community. BaseDocumentCompressor. 🗃️ Tools/Toolkits. document_loaders import WebBaseLoader from langchain_core. Contribute Documentation. Agent is a class that uses an LLM to choose a sequence of actions to take. configurable_alternatives (ConfigurableField (id = "llm"), default_key = "anthropic", openai = ChatOpenAI ()) # uses the default model LangChain provides standard, extendable interfaces and external integrations for the following main components: This is documentation for LangChain v0. Philosophy tools #. langchain: Chains, agents, and retrieval strategies that make up an application's cognitive architecture. Each tool has a description. In Chains, a sequence of actions is hardcoded. ainetwork. The next chapter in building complex production-ready features with LLMs is agentic, and with LangGraph and LangSmith, LangChain delivers an out-of-the-box solution to iterate quickly, debug immediately, and scale effortlessly. toolkit. agents ¶. Browse the classes, functions, and methods for agents, tools, output parsers, and more. Document. , and provide a simple interface to this sequence. Document compressor that uses a pipeline of Transformers. com. 197 items. This is documentation for LangChain v0. Document compressor that uses an LLM chain to extract the relevant parts of documents. 35; documents # Document module is a collection of classes that handle documents and their transformations. Toolkit for interacting with AINetwork Blockchain. Memory wrapper that is read-only and cannot be changed. LangChain is a Python library that simplifies every stage of the LLM application lifecycle: development, productionization, and deployment. Example. Agent uses the description to choose the right tool for the job. BaseDocumentTransformer Abstract base class for document transformation. Learn how to use LangChain's Python and JavaScript libraries, integrations, methods, and tools to create end-to-end applications with LLMs. transform_documents (documents: Sequence [Document], ** kwargs: Any) → Sequence [Document] # Transform sequence of documents by splitting them. Components 🗃️ Chat models. Check out our growing list of integrations. 136 items. langchain_community. 11. API reference Head to the reference section for full documentation of all classes and methods in the LangChain and LangChain Experimental packages. txt file, for loading the text contents of any web page, or even for loading a transcript of a YouTube video. runnables import RunnablePassthrough from langchain_openai import OpenAIEmbeddings from langchain_text_splitters import RecursiveCharacterTextSplitter LangChain is a framework for developing applications powered by language models. In general, to avoid doing too much redundant work select as big a batch size as from langchain_community. Classes. Class hierarchy: PromptTemplate# class langchain_core. prompts. A prompt template consists of a string template. 2, configured for the LangChain Python ecosystem with custom themes, plugins, and content processing capabilities. Key benefits include: Modular Workflow: Simplifies chaining LLMs together for reusable and efficient workflows. CombinedMemory. It enables applications that: from langchain_anthropic import ChatAnthropic from langchain_core. Ideally this should be unique across the document collection and formatted as a UUID, but this will not be enforced. prompts. format_document (doc, prompt) Format a document into a string based on a prompt template. For the legacy API reference hosted on ReadTheDocs see https: Convenience method for executing chain. documents import Document from langchain_text_splitters import RecursiveCharacterTextSplitter from langgraph. 17¶ langchain. Base class for document compressors. When you use all LangChain products, you'll build better, get to production quicker, and grow visibility -- all with less set up and friction. For user guides see https://python. How are LangGraph and LangGraph Platform different? LangGraph is a stateful, orchestration framework that brings added control to agent workflows. You can peruse LangSmith how-to guides here, but we'll highlight a few sections that are particularly relevant to LangChain below: Evaluation It seamlessly integrates with LangChain, and you can use it to inspect and debug individual steps of your chains as you build. A Document is a piece of text and associated metadata. chat_models. Base packages.
xclvvghj vwu gnqx fuztp wokpmpod eauuk iayarr ljgl hlexjli ixyxxt