Jump to content

LangChain

From Wikipedia, the free encyclopedia

This is an old revision of this page, as edited by Vitreology (talk | contribs) at 04:38, 30 January 2024 (Creating a much needed table to provide a overview of the available LangChain tools). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

LangChain
Developer(s)Harrison Chase
Initial releaseOctober 2022
Stable release
0.1.16[1] / 11 April 2024; 4 months ago (11 April 2024)
Repositorygithub.com/langchain-ai/langchain
Written inPython and JavaScript
TypeSoftware framework for large language model application development
LicenseMIT License
WebsiteLangChain.com

LangChain is a framework designed to simplify the creation of applications using large language models (LLMs). As a language model integration framework, LangChain's use-cases largely overlap with those of language models in general, including document analysis and summarization, chatbots, and code analysis.[2]

History

LangChain was launched in October 2022 as an open source project by Harrison Chase, while working at machine learning startup Robust Intelligence. The project quickly garnered popularity,[3] with improvements from hundreds of contributors on GitHub, trending discussions on Twitter, lively activity on the project's Discord server, many YouTube tutorials, and meetups in San Francisco and London. In April 2023, LangChain had incorporated and the new startup raised over $20 million in funding at a valuation of at least $200 million from venture firm Sequoia Capital, a week after announcing a $10 million seed investment from Benchmark.[4][5]

In October 2023 LangChain introduced LangServe, a deployment tool designed to facilitate the transition from LCEL (LangChain Expression Language) prototypes to production-ready applications.[6]

Capabilities

LangChain's developers highlight the framework's applicability to use-cases including chatbots,[7] retrieval-augmented generation,[8] document summarization,[9] and synthetic data generation.[10]

As of March 2023, LangChain included integrations with systems including Amazon, Google, and Microsoft Azure cloud storage; API wrappers for news, movie information, and weather; Bash for summarization, syntax and semantics checking, and execution of shell scripts; multiple web scraping subsystems and templates; few-shot learning prompt generation support; finding and summarizing "todo" tasks in code; Google Drive documents, spreadsheets, and presentations summarization, extraction, and creation; Google Search and Microsoft Bing web search; OpenAI, Anthropic, and Hugging Face language models; iFixit repair guides and wikis search and summarization; MapReduce for question answering, combining documents, and question generation; N-gram overlap scoring; PyPDF, pdfminer, fitz, and pymupdf for PDF file text extraction and manipulation; Python and JavaScript code generation, analysis, and debugging; Milvus vector database[11] to store and retrieve vector embeddings; Weaviate vector database[12] to cache embedding and data objects; Redis cache database storage; Python RequestsWrapper and other methods for API requests; SQL and NoSQL databases including JSON support; Streamlit, including for logging; text mapping for k-nearest neighbors search; time zone conversion and calendar operations; tracing and recording stack symbols in threaded and asynchronous subprocess runs; and the Wolfram Alpha website and SDK.[13] As of April 2023, it can read from more than 50 document types and data sources.[14]

LangChain tools

Tool name URL Description Account required? API key required API limits Current version Dependencies
Alpha Vantage
Apify
ArXiv
AWS Lambda
Shell (bash)
Bearly Code Interpreter
Bing Search
Brave Search
ChatGPT Plugins
Connery Action Tool
Dall-E Image Generator
DataForSEO
DuckDuckGo Search
E2B Data Analysis
Eden AI
Eleven Labs Text2Speech
Exa Search
File System
Golden Query
Google Cloud Text-to-Speech
Google Drive
Google Finance
Google Jobs
Google Lens
Google Places
Google Scholar
Google Trends
Gradio
GraphQL
HuggingFace Hub Tools
Human as a tool

References

  1. ^ "Release 0.1.16". 11 April 2024. Retrieved 23 April 2024.
  2. ^ Buniatyan, Davit (2023). "Code Understanding Using LangChain". Activeloop.
  3. ^ Auffarth, Ben (2023). Generative AI with LangChain. Birmingham: Packt Publishing. p. 83. ISBN 9781835083468.
  4. ^ Palazzolo, Stephanie (2023-04-13). "AI startup LangChain taps Sequoia to lead funding round at a valuation of at least $200 million". Business Insider. Archived from the original on 2023-04-18. Retrieved 2023-04-18.
  5. ^ Griffith, Erin; Metz, Cade (2023-03-14). "'Let 1,000 Flowers Bloom': A.I. Funding Frenzy Escalates". The New York Times. ISSN 0362-4331. Archived from the original on 2023-04-18. Retrieved 2023-04-18.
  6. ^ "Introducing LangServe, the best way to deploy your LangChains". LangChain Blog. 2023-10-12. Retrieved 2023-10-17.
  7. ^ "Chatbots | 🦜️🔗 Langchain". python.langchain.com. Retrieved 2023-11-26.
  8. ^ "Retrieval-augmented generation (RAG) | 🦜️🔗 Langchain". python.langchain.com. Retrieved 2023-11-26.
  9. ^ "Summarization | 🦜️🔗 Langchain". python.langchain.com. Retrieved 2023-11-26.
  10. ^ "Synthetic data generation | 🦜️🔗 Langchain". python.langchain.com. Retrieved 2023-11-26.
  11. ^ "Milvus — LangChain". python.langchain.com. Retrieved 2023-10-29.
  12. ^ "Weaviate". python.langchain.com. Retrieved 2024-01-17.
  13. ^ Hug, Daniel Patrick (2023-03-08). "Hierarchical topic tree of LangChain's integrations" (PDF). GitHub. Archived from the original on 2023-04-29. Retrieved 2023-04-18.
  14. ^ "Document Loaders — LangChain 0.0.142". python.langchain.com. Archived from the original on 2023-04-18. Retrieved 2023-04-18.
Retrieved from "https://en.wikipedia.org/w/index.php?title=LangChain&oldid=1200742978"