# What does this PR do?
An API spec must talk about Error handling. This was a pretty glaring
omission so far. This PR begins to address it by adding a set of
standard error responses we can attach to all our API calls.
At a future point, we can add specific error types where necessary
(although we should not hurry to do that; it is best done very late.)
## Test Plan
Checked that Stainless SDK generation succeeds.
llama-models should have extremely minimal cruft. Its sole purpose
should be didactic -- show the simplest implementation of the llama
models and document the prompt formats, etc.
This PR is the complement to
https://github.com/meta-llama/llama-models/pull/279
## Test Plan
Ensure all `llama` CLI `model` sub-commands work:
```bash
llama model list
llama model download --model-id ...
llama model prompt-format -m ...
```
Ran tests:
```bash
cd tests/client-sdk
LLAMA_STACK_CONFIG=fireworks pytest -s -v inference/
LLAMA_STACK_CONFIG=fireworks pytest -s -v vector_io/
LLAMA_STACK_CONFIG=fireworks pytest -s -v agents/
```
Create a fresh venv `uv venv && source .venv/bin/activate` and run
`llama stack build --template fireworks --image-type venv` followed by
`llama stack run together --image-type venv` <-- the server runs
Also checked that the OpenAPI generator can run and there is no change
in the generated files as a result.
```bash
cd docs/openapi_generator
sh run_openapi_generator.sh
```
# What does this PR do?
- Update `/eval-tasks` to `/benchmarks`
- ⚠️ Remove differentiation between `app` v.s. `benchmark` eval task
config. Now we only have `BenchmarkConfig`. The overloaded `benchmark`
is confusing and do not add any value. Backward compatibility is being
kept as the "type" is not being used anywhere.
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
- This change is backward compatible
- Run notebook test with
```
pytest -v -s --nbval-lax ./docs/getting_started.ipynb
pytest -v -s --nbval-lax ./docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
```
<img width="846" alt="image"
src="https://github.com/user-attachments/assets/d2fc06a7-593a-444f-bc1f-10ab9b0c843d"
/>
[//]: # (## Documentation)
[//]: # (- [ ] Added a Changelog entry if the change is significant)
---------
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
Signed-off-by: Ben Browning <bbrownin@redhat.com>
Signed-off-by: Sébastien Han <seb@redhat.com>
Signed-off-by: reidliu <reid201711@gmail.com>
Co-authored-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
Co-authored-by: Ben Browning <ben324@gmail.com>
Co-authored-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Reid <61492567+reidliu41@users.noreply.github.com>
Co-authored-by: reidliu <reid201711@gmail.com>
Co-authored-by: Yuan Tang <terrytangyuan@gmail.com>
# What does this PR do?
We need to change
```yaml
/v1/inference/chat-completion:
post:
responses:
'200':
description: >-
If stream=False, returns a ChatCompletionResponse with the full completion.
If stream=True, returns an SSE event stream of ChatCompletionResponseStreamChunk
content:
text/event-stream:
schema:
oneOf:
- $ref: '#/components/schemas/ChatCompletionResponse'
- $ref: '#/components/schemas/ChatCompletionResponseStreamChunk'
```
into
```yaml
/v1/inference/chat-completion:
post:
responses:
'200':
description: >-
If stream=False, returns a ChatCompletionResponse with the full completion.
If stream=True, returns an SSE event stream of ChatCompletionResponseStreamChunk
content:
text/event-stream:
schema:
$ref: '#/components/schemas/ChatCompletionResponseStreamChunk'
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionResponse'
```
## Test Plan
**Python**
- tested in SDK sync:
https://github.com/meta-llama/llama-stack-client-python/pull/108
**Node**
- tested w/
https://gist.github.com/yanxi0830/b782f4b91e21dcccdfef8898ce55157e (SDK
udpate follow up)
## 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?
- Discussion in
https://github.com/meta-llama/llama-stack/pull/906#discussion_r1936260819
- image.data should accept base64 string as input instead of binary
bytes, change prompt_adapter to account for that.
## Test Plan
```
pytest -v tests/client-sdk/inference/test_inference.py
```
with test in https://github.com/meta-llama/llama-stack/pull/906
## 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.
We desperately need to document our APIs. This is the basic requirement
of having a Spec :)
This PR updates the OpenAPI generator so documentation for request
parameters and object fields can be properly added to the OpenAPI specs.
From there, this should get picked by Stainless, etc.
## Test Plan:
Updated client-sdk (See
https://github.com/meta-llama/llama-stack-client-python/pull/104) and
then ran:
```bash
cd tests/client-sdk
LLAMA_STACK_CONFIG=../../llama_stack/templates/fireworks/run.yaml pytest -s -v inference/test_inference.py agents/test_agents.py
```
ClientVersion: We don't need each SDK method to support this parameter
because you wouldn't be passing a different client version each time you
make an API call.
ProviderData: although in this case, you _could_ be passing different
API keys depending on which SDK call you make, it makes for a confusing
experience. It is best to initialize the LlamaStackClient with all the
keys which are then passed in each request.
Stainless ends up reformatting the YAML when we paste it in the Studio.
We cannot have that happen if we are going to ever partially automate
stainless config updates.
Try ruamel.yaml, specifically `block_seq_indent` to avoid that.
See https://github.com/meta-llama/llama-stack/issues/827 for the broader
design.
Third part:
- we need to make `tool_runtime.rag_tool.query_context()` and
`tool_runtime.rag_tool.insert_documents()` methods work smoothly with
complete type safety. To that end, we introduce a sub-resource path
`tool-runtime/rag-tool/` and make changes to the resolver to make things
work.
- the PR updates the agents implementation to directly call these typed
APIs for memory accesses rather than going through the complex, untyped
"invoke_tool" API. the code looks much nicer and simpler (expectedly.)
- there are a number of hacks in the server resolver implementation
still, we will live with some and fix some
Note that we must make sure the client SDKs are able to handle this
subresource complexity also. Stainless has support for subresources, so
this should be possible but beware.
## Test Plan
Our RAG test is sad (doesn't actually test for actual RAG output) but I
verified that the implementation works. I will work on fixing the RAG
test afterwards.
```bash
pytest -s -v tests/agents/test_agents.py -k "rag and together" --safety-shield=meta-llama/Llama-Guard-3-8B
```
# What does this PR do?
This PR changes our API to follow more idiomatic REST API approaches of
having paths being resources and methods indicating the action being
performed.
Changes made to generator:
1) removed the prefix check of "get" as its not required and is actually
needed for other method types too
2) removed _ check on path since variables can have "_"
## Test Plan
LLAMA_STACK_BASE_URL=http://localhost:5000 pytest -v
tests/client-sdk/agents/test_agents.py
Add another header so client SDKs can identify their versions which can
be used for immediate detection of possible compatibility issues. A
semver mismatch against the wrong server should be immediately flagged
and requests should be denied.
Also change `X-LlamaStack-ProviderData` to `X-LlamaStack-Provider-Data`
since that hyphenation is better.
## What does this PR do?
This is a long-pending change and particularly important to get done
now.
Specifically:
- we cannot "localize" (aka download) any URLs from media attachments
anywhere near our modeling code. it must be done within llama-stack.
- `PIL.Image` is infesting all our APIs via `ImageMedia ->
InterleavedTextMedia` and that cannot be right at all. Anything in the
API surface must be "naturally serializable". We need a standard `{
type: "image", image_url: "<...>" }` which is more extensible
- `UserMessage`, `SystemMessage`, etc. are moved completely to
llama-stack from the llama-models repository.
See https://github.com/meta-llama/llama-models/pull/244 for the
corresponding PR in llama-models.
## Test Plan
```bash
cd llama_stack/providers/tests
pytest -s -v -k "fireworks or ollama or together" inference/test_vision_inference.py
pytest -s -v -k "(fireworks or ollama or together) and llama_3b" inference/test_text_inference.py
pytest -s -v -k chroma memory/test_memory.py \
--env EMBEDDING_DIMENSION=384 --env CHROMA_DB_PATH=/tmp/foobar
pytest -s -v -k fireworks agents/test_agents.py \
--safety-shield=meta-llama/Llama-Guard-3-8B \
--inference-model=meta-llama/Llama-3.1-8B-Instruct
```
Updated the client sdk (see PR ...), installed the SDK in the same
environment and then ran the SDK tests:
```bash
cd tests/client-sdk
LLAMA_STACK_CONFIG=together pytest -s -v agents/test_agents.py
LLAMA_STACK_CONFIG=ollama pytest -s -v memory/test_memory.py
# this one needed a bit of hacking in the run.yaml to ensure I could register the vision model correctly
INFERENCE_MODEL=llama3.2-vision:latest LLAMA_STACK_CONFIG=ollama pytest -s -v inference/test_inference.py
```
We cannot use recursive types because not only does our OpenAPI
generator not like them, even if it did, it is not easy for all client
languages to automatically construct proper APIs (especially considering
garbage collection) around them. For now, we can return a `Dict[str,
SpanWithStatus]` instead of `SpanWithChildren` and rely on the client to
reconstruct the tree.
Also fixed a super subtle issue with the OpenAPI generation process
(monkey-patching of json_schema_type wasn't working because of import
reordering.)
# What does this PR do?
- modify openapi generator to add coming soon tag for unimplemented api
- sphinx-redocs extension for openapi spec to readthedocs page
## Test Plan
https://github.com/user-attachments/assets/b4c7eebc-2361-4198-a987-dbfbcff914cf
## 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?
Adds a `/alpha/` prefix to all the REST API urls.
Also makes them all use hyphens instead of underscores as is more
standard practice.
(This is based on feedback from our partners.)
## Test Plan
The Stack itself does not need updating. However, client SDKs and
documentation will need to be updated.
# What does this PR do?
This PR brings back the facility to not force registration of resources
onto the user. This is not just annoying but actually not feasible
sometimes. For example, you may have a Stack which boots up with private
providers for inference for models A and B. There is no way for the user
to actually know which model is being served by these providers now (to
be able to register it.)
How will this avoid the users needing to do registration? In a follow-up
diff, I will make sure I update the sample run.yaml files so they list
the models served by the distributions explicitly. So when users do
`llama stack build --template <...>` and run it, their distributions
come up with the right set of models they expect.
For self-hosted distributions, it also allows us to have a place to
explicit list the models that need to be served to make the "complete"
stack (including safety, e.g.)
## Test Plan
Started ollama locally with two lightweight models: Llama3.2-3B-Instruct
and Llama-Guard-3-1B.
Updated all the tests including agents. Here's the tests I ran so far:
```bash
pytest -s -v -m "fireworks and llama_3b" test_text_inference.py::TestInference \
--env FIREWORKS_API_KEY=...
pytest -s -v -m "ollama and llama_3b" test_text_inference.py::TestInference
pytest -s -v -m ollama test_safety.py
pytest -s -v -m faiss test_memory.py
pytest -s -v -m ollama test_agents.py \
--inference-model=Llama3.2-3B-Instruct --safety-model=Llama-Guard-3-1B
```
Found a few bugs here and there pre-existing that these test runs fixed.
This is yet another of those large PRs (hopefully we will have less and less of them as things mature fast). This one introduces substantial improvements and some simplifications to the stack.
Most important bits:
* Agents reference implementation now has support for session / turn persistence. The default implementation uses sqlite but there's also support for using Redis.
* We have re-architected the structure of the Stack APIs to allow for more flexible routing. The motivating use cases are:
- routing model A to ollama and model B to a remote provider like Together
- routing shield A to local impl while shield B to a remote provider like Bedrock
- routing a vector memory bank to Weaviate while routing a keyvalue memory bank to Redis
* Support for provider specific parameters to be passed from the clients. A client can pass data using `x_llamastack_provider_data` parameter which can be type-checked and provided to the Adapter implementations.
