LangChain is a powerful framework designed to help developers build end-to-end applications using language models. It provides a set of tools, components, and interfaces that simplify the process of creating applications powered by large language models (LLMs) and chat models. LangChain can easily manage interactions with language models, link multiple components together, and integrate additional resources such as APIs and databases.

Components and Chains

Prompt Templates and Values

Example Selectors

Output Parsers

Indexes and Retrievers

Chat Message History

Agents and Toolkits

LangChain Agent is the entity in the framework that drives decision making. It has access to a set of tools and can decide which tool to call based on user input. Agents help build complex applications that require adaptive and context-specific responses. They are particularly useful when there are unknown chains of interactions that depend on user input and other factors.

To use LangChain, developers first import the necessary components and tools, such as LLMs, chat models, agents, chains, and memory functions. These components combine to create an application that understands, processes, and responds to user input. LangChain provides multiple components for specific use cases, such as personal assistants, document Q&A, chatbots, querying tabular data, interacting with APIs, extraction, evaluation, and aggregation.

LangChain model is an abstraction that represents the different types of models used in the framework.

LLM (Large Scale Language Model): These models take text strings as input and return text strings as output. They are the backbone of many language model applications.

Chat Model: The Chat Model is powered by a language model but has a more structured API. They take a list of chat messages as input and return chat messages. This makes it easy to manage conversation history and maintain context.

Text Embedding Models: These models take text as input and return a list of floats representing text embeddings. These embeddings can be used for tasks such as document retrieval, clustering, and similarity comparison.

LLMs and Prompts: LangChain makes it easy to manage prompts, optimize them, and create a common interface for all LLMs. Additionally, it includes some handy utilities for working with LLMs.

Chain: These are sequences of calls to LLM or other utilities. LangChain provides a standard interface for the chain, integrates with various tools, and provides an end-to-end chain for popular applications.

Data-augmented generation: LangChain enables the chain to interact with external data sources to collect data for the generation step. For example, it can help summarize long texts or answer questions using specific data sources.

Agents: Agents let the LLM make decisions about actions, take those actions, check the results, and move forward until the work is completed. LangChain provides a standard interface for brokers, a variety of brokers to choose from, and end-to-end broker examples.

Memory: LangChain has a standard memory interface that helps maintain state between chain or proxy calls. It also provides a series of examples of memory implementations and chains or proxies that use memory.

Evaluation: Generative models are difficult to evaluate using traditional metrics. That’s why LangChain provides tips and chains to help developers themselves evaluate their models using LLM.

Document-specific Q&A: Answer a question based on given documents, using information from those documents to create the answer.

Chatbots: Build chatbots that can leverage the power of LLM to generate text.

Agents: Develop agents that can decide on actions, take those actions, observe the results, and continue execution until completion.