llama-stack

llama-stack copied to clipboard

# What does this PR do? This PR adds the inline vLLM inference provider to the regression tests for inference providers. The PR also fixes some regressions in that inference...

frreiss

Agent response format

1

# What does this PR do? Add response format for agents structured output. - [ ] Using structured output for agents (interior_design app as an example) (#issue) https://github.com/meta-llama/llama-stack-apps/issues/122 ## Test...

hanzlfs

POC for: #656

aidando73

### 🚀 Describe the new functionality needed For this request: ```python response = client.inference.chat_completion( model_id=MODEL_ID, messages=[ {"role": "user", "content": "Hello World"}, ], response_format={ "type": "json_schema", "json_schema": { "name": "Plan", "description":...

aidando73

### 🚀 Describe the new functionality needed - See prerequisite issue in: https://github.com/meta-llama/llama-stack/issues/651 **Why** - We currently use providers/tests (to test impls) and tests/client-sdk to test SDK (via directClient &...

yanxi0830

### 🚀 Describe the new functionality needed **Why** - We want a comprehensive & consolidated test suite covering all functionalities **What** - Audit existing tests on functionalities in providers/tests -...

yanxi0830

# What does this PR do? Agents to use tools API ## Test Plan pytest -s -v -k fireworks llama_stack/providers/tests/agents/test_agents.py \ --safety-shield=meta-llama/Llama-Guard-3-8B \ --inference-model=meta-llama/Llama-3.1-8B-Instruct

dineshyv

llama stack build not working for CONTAINER_BINARY podman with UBI9 base image.

2

### System Info Fedora linux OS to run llama stack build command. ### Information - [x] The official example scripts - [ ] My own modified scripts ### 🐛 Describe...

vamsi-01

# What does this PR do? This adds some initial content documenting our OpenAI compatible APIs - Responses, Chat Completions, Completions, and Models - along with instructions on how to...

bbrowning

feat: Enable ingestion of precomputed embeddings

1

# What does this PR do? Enable ingestion of precomputed embeddings with `Chunks`. This PR enhances the Llama Stack vector database APIs, schemas, and documentation to allow users to supply...

franciscojavierarceo