This PR does the following:
1) adds the ability to generate embeddings in all supported inference
providers.
2) Moves all the memory providers to use the inference API and improved
the memory tests to setup the inference stack correctly and use the
embedding models
This is a merge from #589 and #598
The same code is used (inside providers/remote/memory/chroma/chroma.py)
but it is driven by separate configurations and changes which Chroma
client to use. Note that the dependencies are separate
(`chromadb-client` vs `chromadb` -- the latter is a _much_ heavier
package.)
```
pytest -s -v -m chroma memory/test_memory.py --env CHROMA_DB_PATH=/tmp/chroma_test
pytest -s -v -m chroma memory/test_memory.py --env CHROMA_URL=http://localhost:6001
```
# What does this PR do?
This PR fixes some of the issues with our telemetry setup to enable logs
to be delivered to opentelemetry and jaeger. Main fixes
1) Updates the open telemetry provider to use the latest oltp exports
instead of deprected ones.
2) Adds a tracing middleware, which injects traces into each HTTP
request that the server recieves and this is going to be the root trace.
Previously, we did this in the create_dynamic_route method, which is
actually not the actual exectuion flow, but more of a config and this
causes the traces to end prematurely. Through middleware, we plugin the
trace start and end at the right location.
3) We manage our own methods to create traces and spans and this does
not fit well with Opentelemetry SDK since it does not support provide a
way to take in traces and spans that are already created. it expects us
to use the SDK to create them. For now, I have a hacky approach of just
maintaining a map from our internal telemetry objects to the open
telemetry specfic ones. This is not the ideal solution. I will explore
other ways to get around this issue. for now, to have something that
works, i am going to keep this as is.
Addresses: #509
# What does this PR do?
This PR moves all print statements to use logging. Things changed:
- Had to add `await start_trace("sse_generator")` to server.py to
actually get tracing working. else was not seeing any logs
- If no telemetry provider is provided in the run.yaml, we will write to
stdout
- by default, the logs are going to be in JSON, but we expose an option
to configure to output in a human readable way.
# 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:
.....
```
The semantics of an Update on resources is very tricky to reason about
especially for memory banks and models. The best way to go forward here
is for the user to unregister and register a new resource. We don't have
a compelling reason to support update APIs.
Tests:
pytest -v -s llama_stack/providers/tests/memory/test_memory.py -m
"chroma" --env CHROMA_HOST=localhost --env CHROMA_PORT=8000
pytest -v -s llama_stack/providers/tests/memory/test_memory.py -m
"pgvector" --env PGVECTOR_DB=postgres --env PGVECTOR_USER=postgres --env
PGVECTOR_PASSWORD=mysecretpassword --env PGVECTOR_HOST=0.0.0.0
$CONDA_PREFIX/bin/pytest -v -s -m "ollama"
llama_stack/providers/tests/inference/test_model_registration.py
---------
Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
