Debanjum a337d9e4b8 Structure research iteration msgs for more granular context management
Previously research iterations and conversation logs were added to a
single user message. This prevented truncating each past iteration
separately on hitting context limits. So the whole past research
context had to be dropped on hitting context limits.

This change splits each research iteration into a separate item in a
message content list.

It uses the ability for message content to be a list, that is
supported by all major ai model apis like openai, anthropic and gemini.

The change in message format seen by pick next tool chat actor:
- New Format
  - System: System Message
  - User/Assistant: Chat History
  - User: Raw Query
  - Assistant: Iteration History
    - Iteration 1
    - Iteration 2
  - User: Query with Pick Next Tool Nudge

- Old Format
  - User: System + Chat History + Previous Iterations Message
  - User: Query

- Collateral Changes
The construct_structured_message function has been updated to always
return a list[dict[str, Any]].

Previously it'd only use list if attached_file_context or vision model
with images for wider compatibility with other openai compatible api
2025-05-17 17:37:15 -07:00
2025-04-23 19:01:27 +05:30
2025-04-23 19:01:27 +05:30

Khoj Logo

test docker pypi discord

Your AI second brain

📑 Docs   •   🌐 Web   •   🔥 App   •   💬 Discord   •   ✍🏽 Blog

khoj-ai%2Fkhoj | Trendshift


🎁 New

  • Start any message with /research to try out the experimental research mode with Khoj.
  • Anyone can now create custom agents with tunable personality, tools and knowledge bases.
  • Read about Khoj's excellent performance on modern retrieval and reasoning benchmarks.

Overview

Khoj is a personal AI app to extend your capabilities. It smoothly scales up from an on-device personal AI to a cloud-scale enterprise AI.

  • Chat with any local or online LLM (e.g llama3, qwen, gemma, mistral, gpt, claude, gemini, deepseek).
  • Get answers from the internet and your docs (including image, pdf, markdown, org-mode, word, notion files).
  • Access it from your Browser, Obsidian, Emacs, Desktop, Phone or Whatsapp.
  • Create agents with custom knowledge, persona, chat model and tools to take on any role.
  • Automate away repetitive research. Get personal newsletters and smart notifications delivered to your inbox.
  • Find relevant docs quickly and easily using our advanced semantic search.
  • Generate images, talk out loud, play your messages.
  • Khoj is open-source, self-hostable. Always.
  • Run it privately on your computer or try it on our cloud app.

See it in action

demo_chat

Go to https://app.khoj.dev to see Khoj live.

Full feature list

You can see the full feature list here.

Self-Host

To get started with self-hosting Khoj, read the docs.

Enterprise

Khoj is available as a cloud service, on-premises, or as a hybrid solution. To learn more about Khoj Enterprise, visit our website.

Frequently Asked Questions (FAQ)

Q: Can I use Khoj without self-hosting?

Yes! You can use Khoj right away at https://app.khoj.dev — no setup required.

Q: What kinds of documents can Khoj read?

Khoj supports a wide variety: PDFs, Markdown, Notion, Word docs, org-mode files, and more.

Q: How can I make my own agent?

Check out this blog post for a step-by-step guide to custom agents. For more questions, head over to our Discord!

Contributors

Cheers to our awesome contributors! 🎉

Made with contrib.rocks.

Interested in Contributing?

Khoj is open source. It is sustained by the community and wed love for you to join it! Whether youre a coder, designer, writer, or enthusiast, theres a place for you.

Why Contribute?

  • Make an Impact: Help build, test and improve a tool used by thousands to boost productivity.
  • Learn & Grow: Work on cutting-edge AI, LLMs, and semantic search technologies.

You can help us build new features, improve the project documentation, report issues and fix bugs. If you're a developer, please see our Contributing Guidelines and check out good first issues to work on.

Description
No description provided
Readme AGPL-3.0 116 MiB
Languages
Python 51%
TypeScript 36.1%
CSS 4.1%
HTML 3.2%
Emacs Lisp 2.4%
Other 3.1%