# What does this PR do?
Update the llama model supported list for Ollama.
- [x] Addresses issue (#462)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
# 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:
.....
```
# What does this PR do?
adds a new method build_model_alias_with_just_llama_model which is
needed for cases like ollama's quantized models which do not really have
a repo in hf and an entry in SKU list.
## Test Plan
pytest -v -s -m "ollama"
llama_stack/providers/tests/inference/test_text_inference.py
---------
Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
# What does this PR do?
- Fix issue w/ llama stack build using together template
<img width="669" alt="image"
src="https://github.com/user-attachments/assets/1cbef052-d902-40b9-98f8-37efb494d117">
- For builds from templates, copy over the
`templates/<template-name>/run.yaml` file to the
`~/.llama/distributions/<name>/<name>-run.yaml` instead of re-building
run config.
## Test Plan
```
$ llama stack build --template together --image-type conda
..
Build spec configuration saved at /opt/anaconda3/envs/llamastack-together/together-build.yaml
Build Successful! Next steps:
1. Set the environment variables: LLAMASTACK_PORT, TOGETHER_API_KEY
2. `llama stack run /Users/xiyan/.llama/distributions/llamastack-together/together-run.yaml`
```
```
$ llama stack run /Users/xiyan/.llama/distributions/llamastack-together/together-run.yaml
```
```
$ llama-stack-client models list
$ pytest -v -s -m remote agents/test_agents.py --env REMOTE_STACK_URL=http://localhost:5000 --inference-model meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
```
<img width="764" alt="image"
src="https://github.com/user-attachments/assets/b805b6c5-a316-4561-8fe3-24fc3b1f8b80">
## Sources
Please link relevant resources if necessary.
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.
# What does this PR do?
add more quantized model support for ollama.
- [ ] Addresses issue (#issue)
## Test Plan
Tested with ollama docker that run llama3.2 3b 4bit model.
```
root@docker-desktop:/# ollama ps
NAME ID SIZE PROCESSOR UNTIL
llama3.2:3b a80c4f17acd5 3.5 GB 100% CPU 3 minutes from now
```
## Sources
Please link relevant resources if necessary.
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.
# What does this PR do?
Automatically generates
- build.yaml
- run.yaml
- run-with-safety.yaml
- parts of markdown docs
for the distributions.
## Test Plan
At this point, this only updates the YAMLs and the docs. Some testing
(especially with ollama and vllm) has been performed but needs to be
much more tested.
# What does this PR do?
- move folder
## Test Plan
**Unit Test**
```
pytest -v -s -m "huggingface" datasetio/test_datasetio.py
```
**E2E**
```
llama stack run
```
```
llama-stack-client eval run_benchmark meta-reference-mmlu --num-examples 5 --output-dir ./ --eval-task-config ~/eval_task_config.json --visualize
```
<img width="657" alt="image"
src="https://github.com/user-attachments/assets/63d53f9d-6c7e-4667-af8c-9d16c91ae6e3">
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.
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>
# What does this PR do?
This PR kills the notion of "pure passthrough" remote providers. You
cannot specify a single provider you must specify a whole distribution
(stack) as remote.
This PR also significantly fixes / upgrades testing infrastructure so
you can now test against a remotely hosted stack server by just doing
```bash
pytest -s -v -m remote test_agents.py \
--inference-model=Llama3.1-8B-Instruct --safety-shield=Llama-Guard-3-1B \
--env REMOTE_STACK_URL=http://localhost:5001
```
Also fixed `test_agents_persistence.py` (which was broken) and killed
some deprecated testing functions.
## Test Plan
All the tests.
This PR changes the way model id gets translated to the final model name
that gets passed through the provider.
Major changes include:
1) Providers are responsible for registering an object and as part of
the registration returning the object with the correct provider specific
name of the model provider_resource_id
2) To help with the common look ups different names a new ModelLookup
class is created.
Tested all inference providers including together, fireworks, vllm,
ollama, meta reference and bedrock
# What does this PR do?
This PR kills the notion of "ShieldType". The impetus for this is the
realization:
> Why is keyword llama-guard appearing so many times everywhere,
sometimes with hyphens, sometimes with underscores?
Now that we have a notion of "provider specific resource identifiers"
and "user specific aliases" for those and the fact that this works with
models ("Llama3.1-8B-Instruct" <> "fireworks/llama-3pv1-..."), we can
follow the same rules for Shields.
So each Safety provider can make up a notion of identifiers it has
registered. This already happens with Bedrock correctly. We just
generalize it for Llama Guard, Prompt Guard, etc.
For Llama Guard, we further simplify by just adopting the underlying
model name itself as the identifier! No confusion necessary.
While doing this, I noticed a bug in our DistributionRegistry where we
weren't scoping identifiers by type. Fixed.
## Feature/Issue validation/testing/test plan
Ran (inference, safety, memory, agents) tests with ollama and fireworks
providers.
Splits the meta-reference safety implementation into three distinct providers:
- inline::llama-guard
- inline::prompt-guard
- inline::code-scanner
Note that this PR is a backward incompatible change to the llama stack server. I have added deprecation_error field to ProviderSpec -- the server reads it and immediately barfs. This is used to direct the user with a specific message on what action to perform. An automagical "config upgrade" is a bit too much work to implement right now :/
(Note that we will be gradually prefixing all inline providers with inline:: -- I am only doing this for this set of new providers because otherwise existing configuration files will break even more badly.)
* init
* working bedrock tests
* bedrock test for inference fixes
* use env vars for bedrock guardrail vars
* add register in meta reference
* use correct shield impl in meta ref
* dont add together fixture
* right naming
* minor updates
* improved registration flow
* address feedback
---------
Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
