jiayuanzhang

Former post: https://news.ycombinator.com/item?id=40299091

We've just released GitHub Mode for Devv (https://devv.ai). This feature lets you chat with your GitHub repositories. It's currently in public beta and supports Python repos.

Here's a brief intro video: https://youtu.be/eYI746AKHQM?si=yOQi0PsOxS4pfpfe

Some examples you can check out:

* mistralai/mistral-finetune: https://devv.ai/search?threadId=dn380pjcbjls * pallets/werkzeug: https://devv.ai/search?threadId=dn38y917snb4 * django/django: https://devv.ai/search?threadId=dn397f4qqghs

Some technical details:

We developed specialized indexers for each programming language to perform in-depth analysis of code repositories. These indexers:

* Understand the structure of the entire repository from a high-level perspective.

* Analyze the relationships between functions and parse Abstract Syntax Trees (AST).

* Break down code into atomic fragments (functions or classes) and use language models to generate descriptive vector-encoded representations.

* Interpret user queries semantically by integrating multiple external data sources including code repositories, documentation, and search engines.

---

Let me know if you need any further adjustments!

Essential components include: - A search engine API (such as Bing or Google's) - Integration of search engine results with a Large Language Model (LLM)

This framework, known as Retrieval-Augmented Generation (RAG), was the foundation for the initial version of Perplexity.

The challenging aspect lies in refining the generation outcomes, which involves more proprietary techniques.

You can view the terms here: https://indexlabs.notion.site/Term-of-Service-6ca77cbc49504c...

backend: go/rust/python + gin + mysql + pinecone + es + redis + aws

llm: openai/azure + aws gpu + aws bedrock

Thank you for your valuable feedback; it's an excellent suggestion! In fact, we've already begun implementing this feature with our initial step being the introduction of GitHub Mode. This new functionality will enable seamless integration with your personal GitHub repositories. We've developed a bespoke indexer tailored to various programming languages to enhance this experience.

Furthermore, we can expand this capability to include documentation and other resources as well. The architecture is designed to be extensible, so all that's needed is the creation of additional indexers to support these materials.

I've outlined some initial ideas in this post and may develop a more detailed article later on. Stay tuned!

P.S. Agent Mode is a superior option to Fast Mode. It meticulously examines your questions and assigns an appropriate agent to provide answers, leveraging GPT-4 technology in its operations.

You might want to check out this project.

That sounds interesting. Could you provide further details? By the way, integrating an API is part of our future plans. We plan to enable Devv integration with Slack, Linear, and websites in the future.

Also, if you want to discuss more, feel free to email me at [email protected]

Yes, this is on our roadmap. We will launch "Devv for Teams" in the upcoming quarter. This new feature will enable seamless integration of internal team knowledge, including codebases, wikis, issue trackers, and logs.

The results: https://devv.ai/search?threadId=dl3vwbdu52ww

P.S. Agent Mode is a superior option to Fast Mode. It meticulously examines your questions and assigns an appropriate agent to provide answers, leveraging GPT-4 technology in its operations.

I utilized Agent Mode to rephrase the query, and here are the results: https://devv.ai/search?threadId=dl3rtxmcsruo

P.S. Agent Mode is a superior option to Fast Mode. It meticulously examines your questions and assigns an appropriate agent to provide answers, leveraging GPT-4 technology in its operations.

---

> The syntax came from a language proposal in a github issue from 8 years ago, so I guess it's not fully hallucinated. But still not the best choice of what source to use.

Yes, if the source contains errors, the response may generate inaccurate information. We are continually refining our re-ranking algorithm within the Retrieval-Augmented Generation (RAG) system to select the most reliable sources.