LangChain

An open-source framework, in Python and JavaScript, for building applications and agentsAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done. on language modelslarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code., and the company that maintains it. Its integrations put several hundred third-party services, from model vendors and embeddingembedding, n.: A list of numbers that stands for a word, picture or other item, arranged so that similar items get similar lists. It lets a computer measure similarity of meaning as distance. services to vector storesvector database, n.: A database built to store embeddings — lists of numbers that represent meaning — and to quickly find the stored items most similar to a new one. It is the memory behind many AI search tools., document loaders and toolstool, n.: Any outside capability an AI model is allowed to use — a web search, a calculator, a code runner, a database or an app — described to the model so it can ask for it by name., behind shared programming interfaces, alongside components for prompts, output parsing, memory and retrievalretrieval-augmented generation, n.: Giving an AI an open-book exam: before answering, it looks up relevant passages in a set of documents and bases its reply on them, often citing where each point came from.. Early versions centered on 'chains' — fixed sequences of model calls and processing steps — composed from 2023 with the LangChain Expression Language. Version 1.0 (October 2025) recentered the library on a single agent abstraction that runs a tool-calling agent loopagent loop, n.: The repeating cycle at the heart of an AI agent: the model decides what to do next, software carries it out, the result is shown to the model, and the cycle repeats until the task is finished. on the LangGraphLangGraph, prop. n.: A free software library for building AI agents as flowcharts of steps that share a memory, so developers control exactly how an agent moves between steps, pauses and resumes. runtime, with middleware hooks for features such as human approval, summarization and personal-data redaction, and moved legacy chains to a separate package. The company also sells LangSmith, a platform for tracingLLM observability, n.: Recording and inspecting what an AI application actually did on each request — prompts sent, documents found, tools used, answers given, time and cost — so problems can be found and fixed., evaluation and deployment. LangChain was the most widely adopted framework of the 2023 boom and drew sustained criticism for heavy abstraction and frequent breaking changes.

We used LangChain for the prototype because it already had loaders for every document format we needed.