langchainjs VS PythonGPT

*** all code examples are using LangChain TS on the main branch on September 22nd, 2023 (roughly version 0.0.153).

At the time of the prototype's development, the Langchain GitHub loader sent one request per file to fetch the repository sequentially, leading to prolonged download times. In our case about 2 minutes for the insights.opensauced.pizza repository. This issue was later resolved in hwchase17/langchainjs#2224, enabling parallel requests for faster retrieval.

Another llm orchestration library for js/ts

You will probably need to create a custom agent with custom tools to do what you want to do. Look at Langchain (seems like there is an open PR for Google calendar tools here: https://github.com/hwchase17/langchainjs/pull/1777). There are a lot of great integration examples on their website (including for vectorDB memory https://python.langchain.com/docs/modules/memory/how_to/vectorstore_retriever_memory)

You can checkout there docs (here)[https://js.langchain.com/docs/].

The strategy I tried, was to point scalablytyped, at langchainJS.

TL;DR the BANGER TWEET BRAINSToRMER 💥 🐦 🧠 is an open-source, fullstack React/Express/Postgres/Pinecone app that brainstorms new ideas and tweet drafts based on your own notes/ideas and the tweets of your favorite twitter users. This isn't a bot, but you can think of it rather as your personal twitter intern that monitors current twitter **trends**, keeps note of your **ideas**, helps you **brainstorm** new ones, and write **draft** tweets. It's your job to find and edit the best ideas before saving them to your personal notes database or tweeting them out from the app itself. it uses pg-boss cron jobs via Wasp, OpenAI, langChain, and Pinecone for the vector store https://github.com/vincanger/twitter-brainstorming-agent

It is not great. It has a lot of limitations, but can be used under certain conditions. https://github.com/hwchase17/langchainjs/pull/655

There was another post today about using Pydantic for function enabled completions: https://github.com/jxnl/openai_function_call

I whipped up an example doing something similar last Friday using a decorator, inspect, ast and __doc__ usage: https://gist.github.com/kordless/7d306b0646bf0b56c44ebca2b8e.... The example pulls top results from Algoia's HN search and then chains them into another prompt for GPT-X. The blog post is here: https://www.featurebase.com/blog/function-integration-in-ope...

Currently integrating this approach into PythonGPT[1], which will build a function on the fly, extract the method info, then call the code in exec(). I would label it "very dangerous"...

[1] https://github.com/FeatureBaseDB/PythonGPT