codesearch
openai-cookbook
| codesearch | openai-cookbook | |
|---|---|---|
| 5 | 215 | |
| 26 | 55,954 | |
| - | 1.0% | |
| 10.0 | 9.5 | |
| over 1 year ago | 5 days ago | |
| Python | MDX | |
| MIT License | MIT License |
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.
codesearch
-
Show HN: Natural Language Search for Any GitHub Repo
Hi folks, I created an open-source codebase search tool.
Just enter any public Github URL and your search query to get top matching functions on the repo.
Source Code: https://github.com/rahuldan/codesearch
Made it using the OpenAI's embeddings API, FAISS and Postgres.
Currently supports only Python and vanilla Javascript projects. And the max repo size is 100MB
You can self-host using Docker setup from my Github (This would allow you to index local repos)
Would love to hear your feedback
-
Natural Language Search for Codebases (https://github.com/rahuldan/codesearch)
Link: https://github.com/rahuldan/codesearch
-
Show HN: GPTDuck – Ask questions about any GitHub repo
Great project!!
I was building something on similar lines. It is a semantic search engine for codebases using Openai's embedding and FAISS https://github.com/rahuldan/codesearch
It fetches the functions in the code for a query
-
Show HN: Semantic Search for Any Video
Hey really cool project!!
I also built a semantic search engine for codebases using Openai's embedding and FAISS https://github.com/rahuldan/codesearch
-
Ask HN: Any other tools like CodeQL?
Hi, I recently created an open-source project that does semantic search on code bases. You can check it out on https://github.com/rahuldan/codesearch
Would love to hear your feedback
openai-cookbook
-
Question-Answer System Architectures using LLMs
A pretrained LLM is a closed-book system: It can only access information that it was trained on. With domain fine-tuning, the system manifests additional material. An early prototype of this technique was shown in this OpenAi cookbook: For the target domain, text was embedded using an API, and then when using the LLM, embeddings were retrieved using semantic similarity search to formulate an answer. Although this approach evolved to retrieval-augmented generation, its still a technique to adapt a Gen2 (2020) or Gen3 (2022) LLM into a question-answering system.
-
Ask HN: High quality Python scripts or small libraries to learn from
https://github.com/openai/openai-cookbook/blob/main/examples...
- Collection of notebooks showcasing some fun and effective ways of using Claude
- OpenAI Cookbook: Techniques to improve reliability
- OpenAI Cookbooks
-
How to fine tune vit/convnet to focus on the layout of the input room image and ignore other things ?
It sounds like you are trying to tweak embeddings for similarity search. Rather than fine-tune the model's layers, you may want to try training a linear transformation the existing model's output embedding. Openai has a cookbook on how to do that. You will need some data though - but I think you can try it with ~20 pieces of synthetically generated data.
-
Best base model 1B or 7B for full finetuning
tutorial from OpenAI https://github.com/openai/openai-cookbook/blob/main/examples/Question_answering_using_embeddings.ipynb
-
Resources to learn ChatGPT and the OpenAI API
OpenAI Cookbook
- OpenAI Cookbook
-
Another Major Outage Across ChatGPT and API
OpenAI community repo with lots of examples: https://github.com/openai/openai-cookbook
What are some alternatives?
generate-subtitles - Generate transcripts for audio and video content with a user friendly UI, powered by Open AI's Whisper with automatic translations and download videos automatically with yt-dlp integration
langchain - ⚡ Building applications with LLMs through composability ⚡ [Moved to: https://github.com/langchain-ai/langchain]
weggli - weggli is a fast and robust semantic search tool for C and C++ codebases. It is designed to help security researchers identify interesting functionality in large codebases.
gpt4-pdf-chatbot-langchain - GPT4 & LangChain Chatbot for large PDF docs
website - Code for my personal page at ca.lebe.gg
chatgpt-retrieval-plugin - The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.
yt-semantic-search - OpenAI-powered semantic search for any YouTube playlist – featuring the All-In Podcast. 💪
askai - Command Line Interface for OpenAi ChatGPT
semantic-code-search - Search your codebase with natural language • CLI • No data leaves your computer
gpt_index - LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data. [Moved to: https://github.com/jerryjliu/llama_index]
aidoc - A simple CLI tool to generate documentation for your Python projects automatically.
txtai - 💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows