langchainjs VS instructor

*** 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

Ah yes. Have you tried out instructor [0] or Guidance [1]?

[0]: https://github.com/jxnl/instructor/

Good stuff. How does this compare to Instructor? I’ve been using this extensively

https://jxnl.github.io/instructor/

it's super cool! checkout how the Instructor repo uses it to keep various parts of their docs in sync: https://github.com/jxnl/instructor/blob/main/ellipsis.yaml

I've been using the instructor[1] library recently and have found the abstractions simple and extremely helpful for getting great structured outputs from LLMs with pydantic.

1 https://github.com/jxnl/instructor/tree/main

Maybe try using jason liu’s instructor package (https://github.com/jxnl/instructor) to structure the outputs with pydantic? It’s explained in his presentation from the AI Engineer summit (https://youtu.be/yj-wSRJwrrc)

One of the most powerful ways to integrate LLMs with existing systems is constrained generation. Libraries such as outlines[1] and instructor[2] allow structural specification of the expected outputs as regex patterns, simple types, jsonschema or pydantic models.

These outputs often consume significantly fewer tokens than chat or text completion.

[1] https://github.com/outlines-dev/outlines

[2] https://github.com/jxnl/instructor

The best GPT-wrapper you’ll see today?

...but this one hasn't raised oodles of cash.

Mike (creator) here, excited to hear what HN-folks think. Anything to add/improve?

Had fun building, extra s/out to Railway, NextJS, and https://github.com/jxnl/instructor

Check it out: https://www.unboundedbooks.com/