llama-stack

llama-stack copied to clipboard

serve model other than downloaded via `llama download ...`

2

Hi, I have successfully done the cycle of ``` llama download --source huggingface --model-id Llama3.1-8B-Instruct --hf-token llama stack build llama stack configure testerx llama stack run testerx ``` now my...

lumensparkxy

Same as Title ...

Sarthakaushal

Object of type SearchEngineType is not JSON serializable

11

Hi, I try to use the bing search engine tool and I have the Object of type SearchEngineType is not JSON serializable error when executing the agent.create_agent(agent_config) line. There is...

Pentar0o

Added support for structured output in the API and added a reference implementation for meta-reference. A few notes: - Two formats are specified in the API: Json schema and EBNF...

ashwinb

Added Pinecone Memory Adapter

5

Added Pinecone Memory Adapter implementation

cheesecake100201

Cannot connect to docker container on windows 11

2

I've got the models downloaded and my container starts: ``` docker run -it -p 5000:5000 -v C:/Users/sivar/.llama:/root/.llama --gpus=all llamastack/llamastack-local-gpu ``` But when I try to connect to my container I...

Travis-Barton

test plan: PROVIDER_ID=test-tgi PROVIDER_CONFIG=tests/inference/provider_config_example.yaml MODEL_IDS="Llama3.2-1B-Instruct" pytest -s tests/inference/test_inference.py --tb=short --disable-warnings -rs

dineshyv

---continuation of https://github.com/meta-llama/llama-stack/pull/288 # TL;DR - `scoring` depends on `datasetio` & `datasets` - Enforce dataset_schema, client enforces dataset schema to follow specified column names/types - Add clients for datasets /...

yanxi0830

Implement embeddings for ollama PROVIDER_ID=test-ollama PROVIDER_CONFIG=llama_stack/providers/tests/inference/provider_config_example.yaml MODEL_IDS="Llama3.1-8B-Instruct" pytest -s llama_stack/providers/tests/inference/test_inference.py --tb=short --disable-warnings -rs

krgutha

Added a fix for get_agents_session method.

cheesecake100201