- Integrate with Ollama or other openai compatible APIs by simply
setting `OPENAI_API_BASE' environment variable in docker-compose etc.
- Update docs on integrating with Ollama, openai proxies on first run
- Auto populate all chat models supported by openai compatible APIs
- Auto set vision enabled for all commercial models
- Minor
- Add huggingface cache to khoj_models volume. This is where chat
models and (now) sentence transformer models are stored by default
- Reduce verbosity of yarn install of web app. Otherwise hit docker
log size limit & stops showing remaining logs after web app install
- Suggest `ollama pull <model_name>` to start it in background
- Use tabs for GPU/CPU type khoj being install on
- Update CMAKE flags to use to install Khoj with correct GPU support
Previous flags used DLLAMA, this has been updated to use DGGML now
in llama.cpp
- Improve Self Hosting Docker Instructions
- Ask to Install Docker Desktop to not require separate
docker-compose install and unify the instruction across OS
- To Self Host on Windows, ask to use Docker Desktop with WSL2 backend
- Use nested Tab grouping to split Docker vs Pip Self Host Instructions
- Reduce Self Host Setup Steps in Documentation after code simplification
- First run now avoids need to configure Khoj via admin panel
- So move the chat model config steps into optional post setup
config section
- Improve Instructions to Configure chat models on First Run
- Compress configuring chat model providers into a Tab Group
- Add Documentation for Remote Access under Advanced Self Hosting
- Deprecate khoj-assistant pypi package. Use more accurate and
succinct pypi project name, khoj
- Update references to sye khoj pypi package in docs and code instead
of the legacy khoj-assistant pypi package
- Update pypi workflow to publish to both khoj, khoj-assistant for now
- Update stale python 3.9 support mentioned in our pyproject. Can't
support python 3.9 as depend on latest django which support >=3.10
- Add instructions for self-hosted users with info, warning boxes to
avoid, fix common issues when setting up Khoj server
- Create new Advanced Self Hosting section
- Extract Advanced Self-Hosting Sections from the Advanced Page and
move them to separate Pages under Advanced Self Hosting section
- Improve OpenAI Proxy Docs
- Put Ollama setup as a section under OpenAI API Proxy page instead
of a separate page
- Add Section to use Khoj with chat model from LM Studio
- Update LiteLLM docs to use chat model from LM Studio
To access the Khoj admin panel from a non HTTPS custom domain the
`KHOJ_NO_SSL' and `KHOJ_DOMAIN' env vars need to be explictly set.
See the updated setup docs for details.
Resolves#662
- How to pip install khoj to run offline chat on GPU
After migration to llama-cpp-python more GPU types are supported but
require build step so mention how
- New default offline chat model
- Where to get supported chat models from on HuggingFace
This allows using open or commerical, local or hosted LLM models that
are not supported in Khoj by default.
It also allows users to use other local LLM API servers that support
their GPU
Closes#407
* Add a page about privacy and organize some of the documentation
* Add notice about telemetry
* Improve copy for privacy section, link to telemetry section
- Make the docs overview page available at docs.khoj.dev root instead of
under docs.khoj.dev/docs path
- Remove the new landing page, it is unnecessary.
- Remove /docs path prefix from links to internal doc pages
- Remove .md path suffix in internal doc pages for consistency
