llama-stack

llama-stack copied to clipboard

llama stack build with docker not working: config yaml not found

5

Here is the full trace of logs: > Enter a name for your Llama Stack (e.g. my-local-stack): test > Enter the image type you want your Llama Stack to be...

fjmmontiel

Llama stack build fail

8

Hey, I've launched the llama stack build with either python 3.10 and 3.12 and got this error all the time : > Enter a name for your Llama Stack (e.g....

Pentar0o

Will it support RAG?

2

Do you have plans to support Retrieval-Augmented-Generation (RAG), constructing a vector database based on personal data and then performing the corresponding retrieval and generation processes?

solitude-alive

Updated text references of `HuggingFace` to `Hugging Face`. Also a Minor typo, `donwload` to `download`. No change to parameter values. (and great work on llama-stack!)

marklysze

Reordered pip install and llama model download

3

Only after pip install step, llama cli command could be used (which is also specified in the notebook), so its common sense to put it before

KarthiDreamr

Is there a way to specify the download path?

2

For windows, it uses the default user profile path in C drive. But mostly, the C drive is not the large enough path for download large models. Is there a...

SetoKaiba

Import Error During llama stack configure <name>

2

``` File "/usr/local/Caskroom/miniconda/base/envs/llama/lib/python3.10/site-packages/llama_stack/providers/adapters/inference/together/__init__.py", line 7, in from .config import TogetherImplConfig, TogetherHeaderExtractor File "/usr/local/Caskroom/miniconda/base/envs/llama/lib/python3.10/site-packages/llama_stack/providers/adapters/inference/together/config.py", line 11, in from llama_stack.distribution.request_headers import annotate_header ImportError: cannot import name 'annotate_header' from 'llama_stack.distribution.request_headers' (/usr/local/Caskroom/miniconda/base/envs/llama/lib/python3.10/site-packages/llama_stack/distribution/request_headers.py) ``` This...

cheesecake100201

fixing safety inference and safety adapter for new API spec. Pinned t…

1

…he llama_models version to 0.0.24 as the latest version 0.0.35 has the model descriptor name changed. I was getting the missing package error during runtime as well, hence added the...

yogishbaliga

How do you use the docker distribution?

8

`docker run llamastack/llamastack-local-gpu:latest` does nothing

StoyanStAtanasov

" errors" when processing output stream

3

Every so often I'll get something like this in my output stream when doing async processing ```json {"event":{"event_type":"progress","delta":" errors","logprobs":null,"stop_reason":null}} ``` here's the code reading and printing the response, it's a...

teamblubee