Ivan Charapanau
Ivan Charapanau
For anyone stumbling upon this: As there were no easy or robust way to alter's `ncc` Webpack config to tweak this behavior, I've opted into using `@vercel/node` or `@now/now-node` build...
> I forgot to ask: are you running the AppImage live or integrating it permanently? Experienced same problem, was running AppImage live without integrating (just marked it as executable), runnin...
Thanks for providing means to sync the env! It looks like it can't be re-run, however, as `$workspace_path` would be present after the first sync
It looks like `gh` version also has the same problem. `NEXT_PUBLIC_` env vars are needed build-time, whereas `ghcr.io` images are of course built without them. App code needs to be...
Usage in no-network conditions, data protection, ability to choose specific models for specific kind of workload (for example fine-tuned) Nothing unique, just a "local LLM" use-case
Ollama works as expected ```bash GRAPHRAG_API_KEY=123 GRAPHRAG_API_BASE=http://172.17.0.1:11434/v1 # GRAPHRAG_LLM_MODEL=llama3:instruct GRAPHRAG_LLM_MODEL=codestral GRAPHRAG_LLM_THREAD_COUNT=4 GRAPHRAG_LLM_CONCURRENT_REQUESTS=8 GRAPHRAG_LLM_MAX_TOKENS=2048 GRAPHRAG_EMBEDDING_API_BASE=http://172.17.0.1:11435/v1 GRAPHRAG_EMBEDDING_MODEL=mxbai-embed-large ``` `:11435` is a dead-simple proxy that converts HTTP requests from OAI to Ollama format...
@bmaltais, no worries! 11435 is a proxy server written in JS/Node to specifically map request/response between OAI and Ollama formats, I didn't list the whole code as it's pretty much...
@gdhua, your prompt-fu failed you, this proxy server doesn't transform embeddings API between OAI/Ollama formats. @bmaltais, here's the final version of the proxy I ended up using. There was another...
You can change the embeddings API base url to the local one ``` GRAPHRAG_EMBEDDING_API_BASE ``` it must still be compatible with OpenAI API schema
@zeyunie-vecml, yes, that's precisely what the provided server does in addition to the OAI Ollama translation UPD: messed up GitHub threads, was in relation to [this server](https://github.com/microsoft/graphrag/issues/345#issuecomment-2213463325)