Movatterモバイル変換

[0]ホーム
URL:

Skip to main content
OurBuilding Ambient Agents with LangGraph course is now available on LangChain Academy!
Open on GitHub

How-to guides

Here you’ll find answers to “How do I….?” types of questions.These guides aregoal-oriented andconcrete; they're meant to help you complete a specific task.For conceptual explanations see theConceptual guide.For end-to-end walkthroughs seeTutorials.For comprehensive descriptions of every class and function see theAPI Reference.

Installation​

Key features​

This highlights functionality that is core to using LangChain.

Components​

These are the core building blocks you can use when building applications.

Chat models​

Chat Models are newer forms of language models that take messages in and output a message.Seesupported integrations for details on getting started with chat models from a specific provider.

Messages​

Messages are the input and output of chat models. They have somecontent and arole, which describes the source of the message.

Prompt templates​

Prompt Templates are responsible for formatting user input into a format that can be passed to a language model.

Example selectors​

Example Selectors are responsible for selecting the correct few shot examples to pass to the prompt.

LLMs​

What LangChain callsLLMs are older forms of language models that take a string in and output a string.

Output parsers​

Output Parsers are responsible for taking the output of an LLM and parsing into more structured format.

Document loaders​

Document Loaders are responsible for loading documents from a variety of sources.

Text splitters​

Text Splitters take a document and split into chunks that can be used for retrieval.

Embedding models​

Embedding Models take a piece of text and create a numerical representation of it.Seesupported integrations for details on getting started with embedding models from a specific provider.

Vector stores​

Vector stores are databases that can efficiently store and retrieve embeddings.Seesupported integrations for details on getting started with vector stores from a specific provider.

Retrievers​

Retrievers are responsible for taking a query and returning relevant documents.

Indexing​

Indexing is the process of keeping your vectorstore in-sync with the underlying data source.

Tools​

LangChainTools contain a description of the tool (to pass to the language model) as well as the implementation of the function to call. Referhere for a list of pre-built tools.

Multimodal​

Agents​

note

For in depth how-to guides for agents, please check outLangGraph documentation.

Callbacks​

Callbacks allow you to hook into the various stages of your LLM application's execution.

Custom​

All of LangChain components can easily be extended to support your own versions.

Serialization​

Use cases​

These guides cover use-case specific details.

Q&A with RAG​

Retrieval Augmented Generation (RAG) is a way to connect LLMs to external sources of data.For a high-level tutorial on RAG, check outthis guide.

Extraction​

Extraction is when you use LLMs to extract structured information from unstructured text.For a high level tutorial on extraction, check outthis guide.

Chatbots​

Chatbots involve using an LLM to have a conversation.For a high-level tutorial on building chatbots, check outthis guide.

Query analysis​

Query Analysis is the task of using an LLM to generate a query to send to a retriever.For a high-level tutorial on query analysis, check outthis guide.

Q&A over SQL + CSV​

You can use LLMs to do question answering over tabular data.For a high-level tutorial, check outthis guide.

Q&A over graph databases​

You can use an LLM to do question answering over graph databases.For a high-level tutorial, check outthis guide.

Summarization​

LLMs can summarize and otherwise distill desired information from text, includinglarge volumes of text. For a high-level tutorial, check outthis guide.

LangChain Expression Language (LCEL)​

Should I use LCEL?

LCEL is an orchestration solution. See ourconcepts page for recommendations on when touse LCEL.

LangChain Expression Language is a way to create arbitrary custom chains. It is built on theRunnable protocol.

LCEL cheatsheet: For a quick overview of how to use the main LCEL primitives.

Migration guide: For migrating legacy chain abstractions to LCEL.

LangGraph​

LangGraph is an extension of LangChain aimed atbuilding robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.

LangGraph documentation is currently hosted on a separate site.You can peruseLangGraph how-to guides here.

LangSmith​

LangSmith allows you to closely trace, monitor and evaluate your LLM application.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.

LangSmith documentation is hosted on a separate site.You can peruseLangSmith how-to guides here, but we'll highlight a few sections that are particularlyrelevant to LangChain below:

Evaluation​

Evaluating performance is a vital part of building LLM-powered applications.LangSmith helps with every step of the process from creating a dataset to defining metrics to running evaluators.

To learn more, check out theLangSmith evaluation how-to guides.

Tracing​

Tracing gives you observability inside your chains and agents, and is vital in diagnosing issues.

You can see general tracing-related how-tosin this section of the LangSmith docs.

[8]ページ先頭
©2009-2025 Movatter.jp