AIQA
ask-your-stack
AIQA | ask-your-stack | |
---|---|---|
4 | 4 | |
38 | 10 | |
- | - | |
3.1 | 4.6 | |
about 1 year ago | about 1 year ago | |
JavaScript | TypeScript | |
- | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
AIQA
-
How to train a chatbot on customer service data?
> I have this dream of training an LLM to replace me
Here's a simple example in JS - https://github.com/realrasengan/AIQA [1]
[1] Just uses langchainjs
-
Show HN: SiteGPT – Create ChatGPT-like chatbots trained on your website content
You could combine this https://github.com/realrasengan/AIQA
with
this https://github.com/realrasengan/gpt4all-wrapper-js
And do it locally on your computer with just a little mod.
- Show HN: How to use ChatGPT and embeddings in Node.js
- Show HN: QA for an embedded PDF using OpenAI and Node.js
ask-your-stack
-
Show HN: SiteGPT – Create ChatGPT-like chatbots trained on your website content
Even better, just ask your stack
https://ask-your-stack.vercel.app/
(It uses official docs to provide answers with context)
- Ask questions to your tech stack documentation
-
Show HN: Ask questions to your tech stack documentation
* This blog post provides more details on the general approach
All the code is open source: https://github.com/xataio/ask-your-stack
The web-crawler can be found here: https://github.com/tsg/xata-crawler
I think this is similar to GitHub Copilot for Docs but I don't have access to it.
What are some alternatives?
gpt4all-wrapper-js - just a wrapper for gpt4all https://github.com/nomic-ai/gpt4all/ for nodejs
xata-crawler - Sample crawler
langchainjs - 🦜🔗 Build context-aware reasoning applications 🦜🔗
NLTK - NLTK Source
Scrapy - Scrapy, a fast high-level web crawling & scraping framework for Python.
marqo - Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai
langchain - ⚡ Building applications with LLMs through composability ⚡ [Moved to: https://github.com/langchain-ai/langchain]
client-vector-search - A client side vector search library that can embed, store, search, and cache vectors. Works on the browser and node. It outperforms OpenAI's text-embedding-ada-002 and is way faster than Pinecone and other VectorDBs.