Loading repository data…
Loading repository data…
antoinewg / repository
Collection of Langchain agents
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
This repository is aimed at testing a few agents from langchain, with different use cases.
Install dependencies with pnpm i.
Make sure ts-node is installed globally.
Add environment variables as prescribed by each agent in .env.
Run the agent script you want to try ts-node agent-rag-chat-tools-gpt4
Here's the list of templates currenlty available. Feel free to open up a PR to add one.
agent-rag-chat-tools-gpt4Conversational agent with document retriever, and web tool. Using OpenAI's GPT4 model.
See code here.
Run with ts-node agent-rag-chat-tools-gpt4
agent-rag-chat-tools-claudeConversational agent with document retriever, and web tool. Using Anthropic's Claude 2.1 model.
See code here.
Run with ts-node agent-rag-chat-tools-claude
agent-rag-chat-tools-gpt4-streamingConversational agent with document retriever, and web tool. Using OpenAI's GPT4 model. The output can be streamed to the user.
See code here.
Run with ts-node agent-rag-chat-tools-gpt4-streaming
Running those scripts will incur service fees from Anthropic/OpenAI. Results are not guaranteed, this repo should be used only as a list of examples that can be adapted to specific use cases.
Most of the code comes and is based from the langchain documentation. Make sure to check it out.