forked from phoenix-oss/llama-stack-mirror
91e7efbc91
# What does this PR do? The chroma provider maintains a cache but does not sync up with chroma on a cold start. this change adds a fallback to read from chroma on a cache miss. ## Test Plan ```bash #start stack llama stack run /Users/dineshyv/.llama/distributions/llamastack-together/together-run.yaml # Add documents PYTHONPATH=. python -m examples.agents.rag_with_memory_bank localhost 5000 No available shields. Disable safety. Using model: Llama3.1-8B-Instruct Created session_id=b951b14f-a9d2-43a3-8b80-d80114d58322 for Agent(0687a251-6906-4081-8d4c-f52e19db9dd7) memory_retrieval> Retrieved context from banks: ['test_bank']. ==== Here are the retrieved documents for relevant context: === START-RETRIEVED-CONTEXT === id:num-1; content:_ the template from Llama2 to better support multiturn conversations. The same text in the Lla... > inference> Based on the retrieved documentation, the top 5 topics that were explained are: ............... # Kill stack # Bootup stack llama stack run /Users/dineshyv/.llama/distributions/llamastack-together/together-run.yaml # Run a RAG app with just the agent flow. it discovers the previously added documents No available shields. Disable safety. Using model: Llama3.1-8B-Instruct Created session_id=7a30c1a7-c87e-4787-936c-d0306589fe5d for Agent(b30420f3-c928-498a-887b-d084f0f3806c) memory_retrieval> Retrieved context from banks: ['test_bank']. ==== Here are the retrieved documents for relevant context: === START-RETRIEVED-CONTEXT === id:num-1; content:_ the template from Llama2 to better support multiturn conversations. The same text in the Lla... > inference> Based on the provided documentation, the top 5 topics that were explained are: ..... ``` |
||
|---|---|---|
| .. | ||
| chroma | ||
| pgvector | ||
| qdrant | ||
| sample | ||
| weaviate | ||
| __init__.py | ||