Open-source LLMs as LangChain Agents

📰 Hugging Face Blog

Hugging Face explores using open-source LLMs as LangChain agents for general-purpose reasoning

intermediate Published 24 Jan 2024
Action Steps
  1. Understand the concept of agents and their challenges
  2. Explore LangChain and its capabilities for running agents
  3. Evaluate the performance of open-source LLMs as general-purpose reasoning agents
Who Needs to Know This

AI engineers and researchers can benefit from this article to understand the potential of open-source LLMs as agents, while product managers can consider the implications for building more intelligent systems

Key Insight

💡 Open-source LLMs can be used as LangChain agents for general-purpose reasoning, but their performance may vary depending on the task and evaluation metrics

Share This
🤖 Open-source LLMs as LangChain agents: exploring their potential for general-purpose reasoning

Key Takeaways

Hugging Face explores using open-source LLMs as LangChain agents for general-purpose reasoning

Full Article

Published Time: 2024-01-24T00:00:00.324Z

# Open-source LLMs as LangChain Agents

[![Image 1: Hugging Face's logo](https://huggingface.co/front/assets/huggingface_logo-noborder.svg)Hugging Face](https://huggingface.co/)

* [Models](https://huggingface.co/models)
* [Datasets](https://huggingface.co/datasets)
* [Spaces](https://huggingface.co/spaces)
* [Buckets new](https://huggingface.co/storage)
* [Docs](https://huggingface.co/docs)
* [Enterprise](https://huggingface.co/enterprise)
* [Pricing](https://huggingface.co/pricing)
*
*
* * *

* [Log In](https://huggingface.co/login)
* [Sign Up](https://huggingface.co/join)

[Back to Articles](https://huggingface.co/blog)

# [](https://huggingface.co/blog/open-source-llms-as-agents#open-source-llms-as-langchain-agents) Open-source LLMs as LangChain Agents

Published January 24, 2024

[Update on GitHub](https://github.com/huggingface/blog/blob/main/open-source-llms-as-agents.md)

[- [x] Upvote 77](https://huggingface.co/login?next=%2Fblog%2Fopen-source-llms-as-agents)
* [![Image 2](https://cdn-avatars.huggingface.co/v1/production/uploads/5f43448a79c1ba4c353d0d8f/DiSygV3dn7A_OjmGVTrHD.jpeg)](https://huggingface.co/sugatoray "sugatoray")
* [![Image 3](https://huggingface.co/avatars/d229b33d78690b6d03901cfac9f7bd77.svg)](https://huggingface.co/pegah-a "pegah-a")
* [![Image 4](https://huggingface.co/avatars/8cdef21cd68135c58514373013031554.svg)](https://huggingface.co/raahulrahl "raahulrahl")
* [![Image 5](https://cdn-avatars.huggingface.co/v1/production/uploads/1603993433940-noauth.jpeg)](https://huggingface.co/kargarisaac "kargarisaac")
* [![Image 6](https://cdn-avatars.huggingface.co/v1/production/uploads/5ff0d1fc821741e1d652a533/RokKNYx12uLUopSm7PtFh.jpeg)](https://huggingface.co/akdeniz27 "akdeniz27")
* [![Image 7](https://huggingface.co/avatars/c63d77732ea6ac4dbf0fe1f44256d7fd.svg)](https://huggingface.co/raja "raja")
* +71

[![Image 8: Aymeric Roucher's avatar](https://cdn-avatars.huggingface.co/v1/production/uploads/63d10d4e8eaa4831005e92b5/7p7-OmWM6PqqCs7ZStPGD.jpeg)](https://huggingface.co/m-ric)

[Aymeric Roucher m-ric Follow](https://huggingface.co/m-ric)

[![Image 9: Joffrey THOMAS's avatar](https://cdn-avatars.huggingface.co/v1/production/uploads/64257c616d0f0f5f1dc6aa2a/WNXC2PcyDn-jt9ZY5Rbka.jpeg)](https://huggingface.co/Jofthomas)

[Joffrey THOMAS Jofthomas Follow](https://huggingface.co/Jofthomas)

[![Image 10: Andrew Reed's avatar](https://cdn-avatars.huggingface.co/v1/production/uploads/61d375fd733d3a83ecd1bba9/oIXwvvs1-HaCnJXMCZgkc.jpeg)](https://huggingface.co/andrewrreed)

[Andrew Reed andrewrreed Follow](https://huggingface.co/andrewrreed)

## * [TL;DR](https://huggingface.co/blog/open-source-llms-as-agents#tldr "TL;DR")

* [Introduction](https://huggingface.co/blog/open-source-llms-as-agents#introduction "Introduction")

* [Table of Contents](https://huggingface.co/blog/open-source-llms-as-agents#table-of-contents "Table of Contents")

* [What are agents?](https://huggingface.co/blog/open-source-llms-as-agents#what-are-agents "What are agents?")
* [Toy example of a ReAct agent's inner working](https://huggingface.co/blog/open-source-llms-as-agents#toy-example-of-a-react-agents-inner-working "Toy example of a ReAct agent's inner working")

* [Challenges of agent systems](https://huggingface.co/blog/open-source-llms-as-agents#challenges-of-agent-systems "Challenges of agent systems")

* [Running agents with LangChain](https://huggingface.co/blog/open-source-llms-as-agents#running-agents-with-langchain "Running agents with LangChain")

* [Agents Showdown: how do open-source LLMs perform as general purpose reasoning agents?](https://huggingface.co/blog/open-source-llms-as-agents#agents-showdown-how-do-open-source-llms-perform-as-general-purpose-reasoning-agents "Agents Showdown: how do open-source LLMs perform as general purpose reasoning agents?")
* [Evaluation](https://huggingface.co/blog/open-so
Read full article → ← Back to Reads

Related Videos

5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
Kimi K3 by Moonshot AI Surpassed Claude Fable 5
Kimi K3 by Moonshot AI Surpassed Claude Fable 5
Dr Mehrdad Arashpour
Get expert perspectives on any problem with Gemini Gems | Google AI Professional Certificate
Get expert perspectives on any problem with Gemini Gems | Google AI Professional Certificate
Google Career Certificates
Learn to use AI as your strategic thought partner | Google AI Professional Certificate
Learn to use AI as your strategic thought partner | Google AI Professional Certificate
Google Career Certificates
What Are Embeddings in AI? | When to Use Them & Why They Matter
What Are Embeddings in AI? | When to Use Them & Why They Matter
Pavithra’s Podcast
What is LLM? Explained in one minute #karthiksshow #chatgpt #artificialintelligence
What is LLM? Explained in one minute #karthiksshow #chatgpt #artificialintelligence
Karthik's Show