# What does this PR do?
- We cannot directly return a literal type
> Note: this is not final jobs API change
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
<img width="837" alt="image"
src="https://github.com/user-attachments/assets/18a17561-35f9-443d-987d-54afdd6ff40c"
/>
[//]: # (## Documentation)
This PR introduces a way to implement Attribute Based Access Control
(ABAC) for the Llama Stack server.
The rough design is:
- https://github.com/meta-llama/llama-stack/pull/1626 added a way for
the Llama Stack server to query an authenticator
- We build upon that and expect "access attributes" as part of the
response. These attributes indicate the scopes available for the
request.
- We use these attributes to perform access control for registered
resources as well as for constructing the default access control
policies for newly created resources.
- By default, if you support authentication but don't return access
attributes, we will add a unique namespace pointing to the API_KEY. That
way, all resources by default will be scoped to API_KEYs.
An important aspect of this design is that Llama Stack stays out of the
business of credential management or the CRUD for attributes. How you
manage your namespaces or projects is entirely up to you. The design
only implements access control checks for the metadata / book-keeping
information that the Stack tracks.
### Limitations
- Currently, read vs. write vs. admin permissions aren't made explicit,
but this can be easily extended by adding appropriate attributes to the
`AccessAttributes` data structure.
- This design does not apply to agent instances since they are not
considered resources the Stack knows about. Agent instances are
completely within the scope of the Agents API provider.
### Test Plan
Added unit tests, existing integration tests
# What does this PR do?
FAILED
tests/integration/tools/test_tools.py::test_toolsgroups_unregister[None]
- AttributeError: 'coroutine' object has no attribute 'data'
## Test Plan
LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/integration/tools/test_tools.py
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/meta-llama/llama-stack/pull/1704).
* #1705
* __->__ #1704
## What does this PR do?
open-benchmark templated is broken after the datasets api refactor due
to 2 reasons
- provider_id and provider_resource_id are no longer needed
- the type in run.yaml will be resolved as dict
this PR is to fix the above 2 issues
## Test
spin up a llama stack server successfully with llama stack run
`llama_stack/templates/open-benchmark/run.yaml`
# What does this PR do?
- To make it easier, delete existing `eval/scoring/scoring_function`
apis. There will be a bunch of broken impls here. The sequence is:
1. migrate benchmark graders
2. clean up existing scoring functions
- Add a skeleton evaluation impl to make tests pass.
## Test Plan
tested in following PRs
[//]: # (## Documentation)
# What does this PR do?
- fixes routing table so that `llama stack run` works
- fixes pre-commit
- one of many fixes to address implementation fix
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
llama stack run
```
[//]: # (## Documentation)
# What does this PR do?
- Removed Optional return types for GET methods
- Raised ValueError when requested resource is not found
- Ensures proper 4xx response for missing resources
- Updated the API generator to check for wrong signatures
```
$ uv run --with ".[dev]" ./docs/openapi_generator/run_openapi_generator.sh
Validating API method return types...
API Method Return Type Validation Errors:
Method ScoringFunctions.get_scoring_function returns Optional type
```
Closes: https://github.com/meta-llama/llama-stack/issues/1630
## Test Plan
Run the server then:
```
curl http://127.0.0.1:8321/v1/models/foo
{"detail":"Invalid value: Model 'foo' not found"}%
```
Server log:
```
INFO: 127.0.0.1:52307 - "GET /v1/models/foo HTTP/1.1" 400 Bad Request
09:51:42.654 [END] /v1/models/foo [StatusCode.OK] (134.65ms)
09:51:42.651 [ERROR] Error executing endpoint route='/v1/models/{model_id:path}' method='get'
Traceback (most recent call last):
File "/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py", line 193, in endpoint
return await maybe_await(value)
File "/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py", line 156, in maybe_await
return await value
File "/Users/leseb/Documents/AI/llama-stack/llama_stack/providers/utils/telemetry/trace_protocol.py", line 102, in async_wrapper
result = await method(self, *args, **kwargs)
File "/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/routers/routing_tables.py", line 217, in get_model
raise ValueError(f"Model '{model_id}' not found")
ValueError: Model 'foo' not found
```
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
This change adds a compact type to include metrics in response as
opposed to the full MetricEvent which is relevant for internal logging
purposes.
## Test Plan
```
LLAMA_STACK_CONFIG=~/.llama/distributions/fireworks/fireworks-run.yaml pytest -s -v agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B --text-model meta-llama/Llama-3.1-8B-Instruct
llama stack run ~/.llama/distributions/fireworks/fireworks-run.yaml
curl --request POST \
--url http://localhost:8321/v1/inference/chat-completion \
--header 'content-type: application/json' \
--data '{
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"messages": [
{
"role": "user",
"content": {
"type": "text",
"text": "where do humans live"
}
}
],
"stream": false
}'
{
"metrics": [
{
"metric": "prompt_tokens",
"value": 10,
"unit": null
},
{
"metric": "completion_tokens",
"value": 522,
"unit": null
},
{
"metric": "total_tokens",
"value": 532,
"unit": null
}
],
"completion_message": {
"role": "assistant",
"content": "Humans live in various parts of the world...............",
"stop_reason": "out_of_tokens",
"tool_calls": []
},
"logprobs": null
}
```
# What does this PR do?
This PR adds back the changes in #1300 which were reverted in #1476 .
It also adds logic to preserve context variables across asyncio
boundary. this is needed with the library client since the async
generator logic yields control to code outside the event loop, and on
resuming, does not have the same context as before and this requires
preserving the context vars.
address #1477
## Test Plan
```
curl --request POST \
--url http://localhost:8321/v1/inference/chat-completion \
--header 'content-type: application/json' \
--data '{
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"messages": [
{
"role": "user",
"content": {
"type": "text",
"text": "where do humans live"
}
}
],
"stream": false
}' | jq .
{
"metrics": [
{
"trace_id": "kCZwO3tyQC-FuAGb",
"span_id": "bsP_5a5O",
"timestamp": "2025-03-11T16:47:38.549084Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "prompt_tokens",
"value": 10,
"unit": "tokens"
},
{
"trace_id": "kCZwO3tyQC-FuAGb",
"span_id": "bsP_5a5O",
"timestamp": "2025-03-11T16:47:38.549449Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "completion_tokens",
"value": 369,
"unit": "tokens"
},
{
"trace_id": "kCZwO3tyQC-FuAGb",
"span_id": "bsP_5a5O",
"timestamp": "2025-03-11T16:47:38.549457Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "total_tokens",
"value": 379,
"unit": "tokens"
}
],
"completion_message": {
"role": "assistant",
"content": "Humans live on the planet Earth, specifically on its landmasses and in its oceans. Here's a breakdown of where humans live:\n\n1. **Continents:** Humans inhabit all seven continents:\n\t* Africa\n\t* Antarctica ( temporary residents, mostly scientists and researchers)\n\t* Asia\n\t* Australia\n\t* Europe\n\t* North America\n\t* South America\n2. **Countries:** There are 196 countries recognized by the United Nations, and humans live in almost all of them.\n3. **Cities and towns:** Many humans live in urban areas, such as cities and towns, which are often located near coastlines, rivers, or other bodies of water.\n4. **Rural areas:** Some humans live in rural areas, such as villages, farms, and countryside.\n5. **Islands:** Humans inhabit many islands around the world, including those in the Pacific, Indian, and Atlantic Oceans.\n6. **Mountains and highlands:** Humans live in mountainous regions, such as the Himalayas, the Andes, and the Rocky Mountains.\n7. **Deserts:** Some humans live in desert regions, such as the Sahara, the Mojave, and the Atacama.\n8. **Coastal areas:** Many humans live in coastal areas, such as beaches, ports, and coastal cities.\n9. **Underwater habitats:** A few humans live in underwater habitats, such as research stations and submarines.\n10. **Space:** A small number of humans have lived in space, including astronauts on the International Space Station and those who have visited the Moon.\n\nOverall, humans can be found living in almost every environment on Earth, from the frozen tundra to the hottest deserts, and from the highest mountains to the deepest oceans.",
"stop_reason": "end_of_turn",
"tool_calls": []
},
"logprobs": null
}
```
Orignal repro no longer showing any error:
```
LLAMA_STACK_DISABLE_VERSION_CHECK=true llama stack run ~/.llama/distributions/fireworks/fireworks-run.yaml
python -m examples.agents.e2e_loop_with_client_tools localhost 8321
```
client logs:
https://gist.github.com/dineshyv/047c7e87b18a5792aa660e311ea53166
server logs:
https://gist.github.com/dineshyv/97a2174099619e9916c7c490be26e559
# What does this PR do?
This commit introduces a new logging system that allows loggers to be
assigned
a category while retaining the logger name based on the file name. The
log
format includes both the logger name and the category, producing output
like:
```
INFO 2025-03-03 21:44:11,323 llama_stack.distribution.stack:103 [core]: Tool_groups: builtin::websearch served by
tavily-search
```
Key features include:
- Category-based logging: Loggers can be assigned a category (e.g.,
"core", "server") when programming. The logger can be loaded like
this: `logger = get_logger(name=__name__, category="server")`
- Environment variable control: Log levels can be configured
per-category using the
`LLAMA_STACK_LOGGING` environment variable. For example:
`LLAMA_STACK_LOGGING="server=DEBUG;core=debug"` enables DEBUG level for
the "server"
and "core" categories.
- `LLAMA_STACK_LOGGING="all=debug"` sets DEBUG level globally for all
categories and
third-party libraries.
This provides fine-grained control over logging levels while maintaining
a clean and
informative log format.
The formatter uses the rich library which provides nice colors better
stack traces like so:
```
ERROR 2025-03-03 21:49:37,124 asyncio:1758 [uncategorized]: unhandled exception during asyncio.run() shutdown
task: <Task finished name='Task-16' coro=<handle_signal.<locals>.shutdown() done, defined at
/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py:146>
exception=UnboundLocalError("local variable 'loop' referenced before assignment")>
╭────────────────────────────────────── Traceback (most recent call last) ───────────────────────────────────────╮
│ /Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py:178 in shutdown │
│ │
│ 175 │ │ except asyncio.CancelledError: │
│ 176 │ │ │ pass │
│ 177 │ │ finally: │
│ ❱ 178 │ │ │ loop.stop() │
│ 179 │ │
│ 180 │ loop = asyncio.get_running_loop() │
│ 181 │ loop.create_task(shutdown()) │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
UnboundLocalError: local variable 'loop' referenced before assignment
```
Co-authored-by: Ashwin Bharambe <@ashwinb>
Signed-off-by: Sébastien Han <seb@redhat.com>
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
python -m llama_stack.distribution.server.server --yaml-config ./llama_stack/templates/ollama/run.yaml
INFO 2025-03-03 21:55:35,918 __main__:365 [server]: Using config file: llama_stack/templates/ollama/run.yaml
INFO 2025-03-03 21:55:35,925 __main__:378 [server]: Run configuration:
INFO 2025-03-03 21:55:35,928 __main__:380 [server]: apis:
- agents
```
[//]: # (## Documentation)
---------
Signed-off-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
# What does this PR do?
The commit addresses the Ruff warning B008 by refactoring the code to
avoid calling SamplingParams() directly in function argument defaults.
Instead, it either uses Field(default_factory=SamplingParams) for
Pydantic models or sets the default to None and instantiates
SamplingParams inside the function body when the argument is None.
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
Some imports were not switched to in-tree copy of the modules.
This is a follow-up to:
https://github.com/meta-llama/llama-stack/pull/1344Closes#1435
## Test Plan
Manually started the server...
[//]: # (## Documentation)
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
Inference router computes the token usage related metrics for all
providers and returns the metrics as part of response and also logs to
telemetry.
## Test Plan
LLAMA_STACK_DISABLE_VERSION_CHECK=true llama stack run
~/.llama/distributions/fireworks/fireworks-run.yaml
```
curl --request POST \
--url http://localhost:8321/v1/inference/chat-completion \
--header 'content-type: application/json' \
--data '{
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"messages": [
{
"role": "user",
"content": {
"type": "text",
"text": "where do humans live"
}
}
],
"stream": false
}' | jq .
{
"metrics": [
{
"trace_id": "yjv1tf0jS1evOyPm",
"span_id": "WqYKvg0_",
"timestamp": "2025-02-27T18:55:10.770903Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "prompt_tokens",
"value": 10,
"unit": "tokens"
},
{
"trace_id": "yjv1tf0jS1evOyPm",
"span_id": "WqYKvg0_",
"timestamp": "2025-02-27T18:55:10.770916Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "completion_tokens",
"value": 411,
"unit": "tokens"
},
{
"trace_id": "yjv1tf0jS1evOyPm",
"span_id": "WqYKvg0_",
"timestamp": "2025-02-27T18:55:10.770919Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "total_tokens",
"value": 421,
"unit": "tokens"
}
],
"completion_message": {
"role": "assistant",
"content": "Humans live in various parts of the world, inhabiting almost every continent, country, and region. Here's a breakdown of where humans live:\n\n1. **Continents:** Humans inhabit all seven continents:\n\t* Africa\n\t* Antarctica (research stations only)\n\t* Asia\n\t* Australia\n\t* Europe\n\t* North America\n\t* South America\n2. **Countries:** There are 196 countries recognized by the United Nations, and humans live in almost all of them.\n3. **Regions:** Humans live in diverse regions, including:\n\t* Deserts (e.g., Sahara, Mojave)\n\t* Forests (e.g., Amazon, Congo)\n\t* Grasslands (e.g., Prairies, Steppes)\n\t* Mountains (e.g., Himalayas, Andes)\n\t* Oceans (e.g., coastal areas, islands)\n\t* Tundras (e.g., Arctic, sub-Arctic)\n4. **Cities and towns:** Many humans live in urban areas, such as cities and towns, which are often located near:\n\t* Coastlines\n\t* Rivers\n\t* Lakes\n\t* Mountains\n5. **Rural areas:** Some humans live in rural areas, such as:\n\t* Villages\n\t* Farms\n\t* Countryside\n6. **Islands:** Humans inhabit many islands, including:\n\t* Tropical islands (e.g., Hawaii, Maldives)\n\t* Arctic islands (e.g., Greenland, Iceland)\n\t* Continental islands (e.g., Great Britain, Ireland)\n7. **Extreme environments:** Humans also live in extreme environments, such as:\n\t* High-altitude areas (e.g., Tibet, Andes)\n\t* Low-altitude areas (e.g., Death Valley, Dead Sea)\n\t* Areas with extreme temperatures (e.g., Arctic, Sahara)\n\nOverall, humans have adapted to live in a wide range of environments and ecosystems around the world.",
"stop_reason": "end_of_turn",
"tool_calls": []
},
"logprobs": null
}
```
```
LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/integration/inference
======================================================================== short test summary info =========================================================================
FAILED tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=8B:vis=11B-inference:chat_completion:tool_calling_tools_absent-True] - ValueError: Unsupported tool prompt format: ToolPromptFormat.json
FAILED tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=8B:vis=11B-inference:chat_completion:tool_calling_tools_absent-False] - ValueError: Unsupported tool prompt format: ToolPromptFormat.json
FAILED tests/integration/inference/test_vision_inference.py::test_image_chat_completion_non_streaming[txt=8B:vis=11B] - fireworks.client.error.InvalidRequestError: {'error': {'object': 'error', 'type': 'invalid_request_error', 'message': 'Failed to decode image cannot identify image f...
FAILED tests/integration/inference/test_vision_inference.py::test_image_chat_completion_streaming[txt=8B:vis=11B] - fireworks.client.error.InvalidRequestError: {'error': {'object': 'error', 'type': 'invalid_request_error', 'message': 'Failed to decode image cannot identify image f...
========================================================= 4 failed, 16 passed, 23 xfailed, 17 warnings in 44.36s =========================================================
```
# What does this PR do?
The agent API allows to query multiple DBs using the `vector_db_ids`
argument of the `rag` tool:
```py
toolgroups=[
{
"name": "builtin::rag",
"args": {"vector_db_ids": [vector_db_id]},
}
],
```
This means that multiple DBs can be used to compose an aggregated
context by executing the query on each of them.
When documents are passed to the next agent turn, there is no explicit
way to configure the vector DB where the embeddings will be ingested. In
such cases, we can assume that:
- if any `vector_db_ids` is given, we use the first one (it probably
makes sense to assume that it's the only one in the list, otherwise we
should loop on all the given DBs to have a consistent ingestion)
- if no `vector_db_ids` is given, we can use the current logic to
generate a default DB using the default provider. If multiple providers
are defined, the API will fail as expected: the user has to provide
details on where to ingest the documents.
(Closes#1270)
## Test Plan
The issue description details how to replicate the problem.
[//]: # (## Documentation)
---------
Signed-off-by: Daniele Martinoli <dmartino@redhat.com>
All of the tests from `llama_stack/providers/tests/` are now moved to
`tests/integration`.
I converted the `tools`, `scoring` and `datasetio` tests to use API.
However, `eval` and `post_training` proved to be a bit challenging to
leaving those. I think `post_training` should be relatively
straightforward also.
As part of this, I noticed that `wolfram_alpha` tool wasn't added to
some of our commonly used distros so I added it. I am going to remove a
lot of code duplication from distros next so while this looks like a
one-off right now, it will go away and be there uniformly for all
distros.
# What does this PR do?
- This was missed from previous deprecation:
https://github.com/meta-llama/llama-stack/pull/1186
- Part of https://github.com/meta-llama/llama-stack/issues/1396
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
pytest -v -s --nbval-lax ./llama-stack/docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
```
[//]: # (## Documentation)
A self-respecting server needs good observability which starts with
configurable logging. Llama Stack had little until now. This PR adds a
`logcat` facility towards that. Callsites look like:
```python
logcat.debug("inference", f"params to ollama: {params}")
```
- the first parameter is a category. there is a static list of
categories in `llama_stack/logcat.py`
- each category can be associated with a log-level which can be
configured via the `LLAMA_STACK_LOGGING` env var.
- a value `LLAMA_STACK_LOGGING=inference=debug;server=info"` does the
obvious thing. there is a special key called `all` which is an alias for
all categories
## Test Plan
Ran with `LLAMA_STACK_LOGGING="all=debug" llama stack run fireworks` and
saw the following:
Hit it with a client-sdk test case and saw this:
Summary:
Lets the model decide which tool it needs to call to respond to a query.
Test Plan:
```
LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/client-sdk/ --safety-shield meta-llama/Llama-Guard-3-8B
```
Also evaluated on a small benchmark with 20 questions from HotpotQA.
With this PR and some prompting, the performance is 77% recall compared
to 50% currently.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/meta-llama/llama-stack/pull/1015).
* #1268
* #1239
* __->__ #1015
Summary:
Currently we don't set the best tool_prompt_format according to model as
promisd.
Test Plan:
Added print around raw model input and inspected manually
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/meta-llama/llama-stack/pull/1214).
* #1234
* __->__ #1214
See Issue #922
The change is slightly backwards incompatible but no callsite (in our
client codebases or stack-apps) every passes a depth-2
`List[List[InterleavedContentItem]]` (which is now disallowed.)
## Test Plan
```bash
$ cd llama_stack/providers/tests/inference
$ pytest -s -v -k fireworks test_embeddings.py \
--inference-model nomic-ai/nomic-embed-text-v1.5 --env EMBEDDING_DIMENSION=784
$ pytest -s -v -k together test_embeddings.py \
--inference-model togethercomputer/m2-bert-80M-8k-retrieval --env EMBEDDING_DIMENSION=784
$ pytest -s -v -k ollama test_embeddings.py \
--inference-model all-minilm:latest --env EMBEDDING_DIMENSION=784
```
Also ran `tests/client-sdk/inference/test_embeddings.py`
# What does this PR do?
- Fully deprecate eval/tasks
[//]: # (If resolving an issue, uncomment and update the line below)
Closes#1088
NOTE: this will be a breaking change. We have introduced the new API in
0.1.3 .
Notebook has been updated to use the new endpoints.
## Test Plan
```
pytest -v -s --nbval-lax ./docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
```
<img width="611" alt="image"
src="https://github.com/user-attachments/assets/79f6efe1-81ba-494e-bf36-1fc0c2b9bc6f"
/>
cc @SLR722 for awareness
[//]: # (## Documentation)
# 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?
- Configured ruff linter to automatically fix import sorting issues.
- Set --exit-non-zero-on-fix to ensure non-zero exit code when fixes are
applied.
- Enabled the 'I' selection to focus on import-related linting rules.
- Ran the linter, and formatted all codebase imports accordingly.
- Removed the black dep from the "dev" group since we use ruff
Signed-off-by: Sébastien Han <seb@redhat.com>
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
[Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.*]
[//]: # (## Documentation)
[//]: # (- [ ] Added a Changelog entry if the change is significant)
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
This commit enhances the signal handling mechanism in the server by
improving the `handle_signal` (previously handle_sigint) function. It
now properly retrieves the signal name, ensuring clearer logging when a
termination signal is received. Additionally, it cancels all running
tasks and waits for their completion before stopping the event loop,
allowing for a more graceful shutdown. Support for handling
SIGTERM has also been added alongside SIGINT.
Before the changes, handle_sigint used asyncio.run(run_shutdown()).
However, asyncio.run() is meant to start a new event loop, and calling
it inside an existing one (like when running Uvicorn) raises an error.
The fix replaces asyncio.run(run_shutdown()) with an async function
scheduled on the existing loop using loop.create_task(shutdown()). This
ensures that the shutdown coroutine runs within the current event loop
instead of trying to create a new one.
Furthermore, this commit updates the project dependencies. `fastapi` and
`uvicorn` have been added to the development dependencies in
`pyproject.toml` and `uv.lock`, ensuring that the necessary packages are
available for development and execution.
Closes: https://github.com/meta-llama/llama-stack/issues/1043
Signed-off-by: Sébastien Han <seb@redhat.com>
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
Run a server and send SIGINT:
```
INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" python -m llama_stack.distribution.server.server --yaml-config ./llama_stack/templates/ollama/run.yaml
Using config file: llama_stack/templates/ollama/run.yaml
Run configuration:
apis:
- agents
- datasetio
- eval
- inference
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
container_image: null
datasets: []
eval_tasks: []
image_name: ollama
metadata_store:
db_path: /Users/leseb/.llama/distributions/ollama/registry.db
namespace: null
type: sqlite
models:
- metadata: {}
model_id: meta-llama/Llama-3.2-3B-Instruct
model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType
- llm
provider_id: ollama
provider_model_id: null
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType
- embedding
provider_id: sentence-transformers
provider_model_id: null
providers:
agents:
- config:
persistence_store:
db_path: /Users/leseb/.llama/distributions/ollama/agents_store.db
namespace: null
type: sqlite
provider_id: meta-reference
provider_type: inline::meta-reference
datasetio:
- config: {}
provider_id: huggingface
provider_type: remote::huggingface
- config: {}
provider_id: localfs
provider_type: inline::localfs
eval:
- config: {}
provider_id: meta-reference
provider_type: inline::meta-reference
inference:
- config:
url: http://localhost:11434
provider_id: ollama
provider_type: remote::ollama
- config: {}
provider_id: sentence-transformers
provider_type: inline::sentence-transformers
safety:
- config: {}
provider_id: llama-guard
provider_type: inline::llama-guard
scoring:
- config: {}
provider_id: basic
provider_type: inline::basic
- config: {}
provider_id: llm-as-judge
provider_type: inline::llm-as-judge
- config:
openai_api_key: '********'
provider_id: braintrust
provider_type: inline::braintrust
telemetry:
- config:
service_name: llama-stack
sinks: console,sqlite
sqlite_db_path: /Users/leseb/.llama/distributions/ollama/trace_store.db
provider_id: meta-reference
provider_type: inline::meta-reference
tool_runtime:
- config:
api_key: '********'
max_results: 3
provider_id: brave-search
provider_type: remote::brave-search
- config:
api_key: '********'
max_results: 3
provider_id: tavily-search
provider_type: remote::tavily-search
- config: {}
provider_id: code-interpreter
provider_type: inline::code-interpreter
- config: {}
provider_id: rag-runtime
provider_type: inline::rag-runtime
vector_io:
- config:
kvstore:
db_path: /Users/leseb/.llama/distributions/ollama/faiss_store.db
namespace: null
type: sqlite
provider_id: faiss
provider_type: inline::faiss
scoring_fns: []
server:
port: 8321
tls_certfile: null
tls_keyfile: null
shields: []
tool_groups:
- args: null
mcp_endpoint: null
provider_id: tavily-search
toolgroup_id: builtin::websearch
- args: null
mcp_endpoint: null
provider_id: rag-runtime
toolgroup_id: builtin::rag
- args: null
mcp_endpoint: null
provider_id: code-interpreter
toolgroup_id: builtin::code_interpreter
vector_dbs: []
version: '2'
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:213: Resolved 31 providers
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: inner-inference => ollama
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: inner-inference => sentence-transformers
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: models => __routing_table__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: inference => __autorouted__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: inner-vector_io => faiss
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: inner-safety => llama-guard
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: shields => __routing_table__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: safety => __autorouted__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: vector_dbs => __routing_table__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: vector_io => __autorouted__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: inner-tool_runtime => brave-search
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: inner-tool_runtime => tavily-search
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: inner-tool_runtime => code-interpreter
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: inner-tool_runtime => rag-runtime
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: tool_groups => __routing_table__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: tool_runtime => __autorouted__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: agents => meta-reference
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: inner-datasetio => huggingface
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: inner-datasetio => localfs
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: datasets => __routing_table__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: datasetio => __autorouted__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: telemetry => meta-reference
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: inner-scoring => basic
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: inner-scoring => llm-as-judge
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: inner-scoring => braintrust
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: scoring_functions => __routing_table__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: scoring => __autorouted__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: inner-eval => meta-reference
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: eval_tasks => __routing_table__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: eval => __autorouted__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215: inspect => __builtin__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:216:
INFO 2025-02-12 10:21:03,723 llama_stack.providers.remote.inference.ollama.ollama:148: checking connectivity to Ollama at `http://localhost:11434`...
INFO 2025-02-12 10:21:03,734 httpx:1740: HTTP Request: GET http://localhost:11434/api/ps "HTTP/1.1 200 OK"
INFO 2025-02-12 10:21:03,843 faiss.loader:148: Loading faiss.
INFO 2025-02-12 10:21:03,865 faiss.loader:150: Successfully loaded faiss.
INFO 2025-02-12 10:21:03,868 faiss:173: Failed to load GPU Faiss: name 'GpuIndexIVFFlat' is not defined. Will not load constructor refs for GPU indexes.
Warning: `bwrap` is not available. Code interpreter tool will not work correctly.
INFO 2025-02-12 10:21:04,315 datasets:54: PyTorch version 2.6.0 available.
INFO 2025-02-12 10:21:04,556 httpx:1740: HTTP Request: GET http://localhost:11434/api/ps "HTTP/1.1 200 OK"
INFO 2025-02-12 10:21:04,557 llama_stack.providers.utils.inference.embedding_mixin:42: Loading sentence transformer for all-MiniLM-L6-v2...
INFO 2025-02-12 10:21:07,202 sentence_transformers.SentenceTransformer:210: Use pytorch device_name: mps
INFO 2025-02-12 10:21:07,202 sentence_transformers.SentenceTransformer:218: Load pretrained SentenceTransformer: all-MiniLM-L6-v2
INFO 2025-02-12 10:21:09,500 llama_stack.distribution.stack:102: Models: all-MiniLM-L6-v2 served by sentence-transformers
INFO 2025-02-12 10:21:09,500 llama_stack.distribution.stack:102: Models: meta-llama/Llama-3.2-3B-Instruct served by ollama
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: basic::equality served by basic
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: basic::regex_parser_multiple_choice_answer served by basic
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: basic::subset_of served by basic
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::answer-correctness served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::answer-relevancy served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::answer-similarity served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::context-entity-recall served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::context-precision served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::context-recall served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::context-relevancy served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::factuality served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::faithfulness served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: llm-as-judge::405b-simpleqa served by llm-as-judge
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: llm-as-judge::base served by llm-as-judge
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Tool_groups: builtin::code_interpreter served by code-interpreter
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Tool_groups: builtin::rag served by rag-runtime
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Tool_groups: builtin::websearch served by tavily-search
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:106:
Serving API eval
POST /v1/eval/tasks/{task_id}/evaluations
DELETE /v1/eval/tasks/{task_id}/jobs/{job_id}
GET /v1/eval/tasks/{task_id}/jobs/{job_id}/result
GET /v1/eval/tasks/{task_id}/jobs/{job_id}
POST /v1/eval/tasks/{task_id}/jobs
Serving API agents
POST /v1/agents
POST /v1/agents/{agent_id}/session
POST /v1/agents/{agent_id}/session/{session_id}/turn
DELETE /v1/agents/{agent_id}
DELETE /v1/agents/{agent_id}/session/{session_id}
GET /v1/agents/{agent_id}/session/{session_id}
GET /v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}/step/{step_id}
GET /v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}
Serving API scoring_functions
GET /v1/scoring-functions/{scoring_fn_id}
GET /v1/scoring-functions
POST /v1/scoring-functions
Serving API safety
POST /v1/safety/run-shield
Serving API inspect
GET /v1/health
GET /v1/inspect/providers
GET /v1/inspect/routes
GET /v1/version
Serving API tool_runtime
POST /v1/tool-runtime/invoke
GET /v1/tool-runtime/list-tools
POST /v1/tool-runtime/rag-tool/insert
POST /v1/tool-runtime/rag-tool/query
Serving API datasetio
POST /v1/datasetio/rows
GET /v1/datasetio/rows
Serving API shields
GET /v1/shields/{identifier}
GET /v1/shields
POST /v1/shields
Serving API eval_tasks
GET /v1/eval-tasks/{eval_task_id}
GET /v1/eval-tasks
POST /v1/eval-tasks
Serving API models
GET /v1/models/{model_id}
GET /v1/models
POST /v1/models
DELETE /v1/models/{model_id}
Serving API datasets
GET /v1/datasets/{dataset_id}
GET /v1/datasets
POST /v1/datasets
DELETE /v1/datasets/{dataset_id}
Serving API vector_io
POST /v1/vector-io/insert
POST /v1/vector-io/query
Serving API inference
POST /v1/inference/chat-completion
POST /v1/inference/completion
POST /v1/inference/embeddings
Serving API tool_groups
GET /v1/tools/{tool_name}
GET /v1/toolgroups/{toolgroup_id}
GET /v1/toolgroups
GET /v1/tools
POST /v1/toolgroups
DELETE /v1/toolgroups/{toolgroup_id}
Serving API vector_dbs
GET /v1/vector-dbs/{vector_db_id}
GET /v1/vector-dbs
POST /v1/vector-dbs
DELETE /v1/vector-dbs/{vector_db_id}
Serving API scoring
POST /v1/scoring/score
POST /v1/scoring/score-batch
Serving API telemetry
GET /v1/telemetry/traces/{trace_id}/spans/{span_id}
GET /v1/telemetry/spans/{span_id}/tree
GET /v1/telemetry/traces/{trace_id}
POST /v1/telemetry/events
GET /v1/telemetry/spans
GET /v1/telemetry/traces
POST /v1/telemetry/spans/export
Listening on ['::', '0.0.0.0']:5001
INFO: Started server process [65372]
INFO: Waiting for application startup.
INFO: ASGI 'lifespan' protocol appears unsupported.
INFO: Application startup complete.
INFO: Uvicorn running on http://['::', '0.0.0.0']:5001 (Press CTRL+C to quit)
^CINFO: Shutting down
INFO: Finished server process [65372]
Received signal SIGINT (2). Exiting gracefully...
INFO 2025-02-12 10:21:11,215 __main__:151: Shutting down ModelsRoutingTable
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down InferenceRouter
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down ShieldsRoutingTable
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down SafetyRouter
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down VectorDBsRoutingTable
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down VectorIORouter
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down ToolGroupsRoutingTable
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down ToolRuntimeRouter
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down MetaReferenceAgentsImpl
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down DatasetsRoutingTable
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down DatasetIORouter
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down TelemetryAdapter
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down ScoringFunctionsRoutingTable
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down ScoringRouter
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down EvalTasksRoutingTable
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down EvalRouter
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down DistributionInspectImpl
```
[//]: # (## Documentation)
[//]: # (- [ ] Added a Changelog entry if the change is significant)
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
The current default system prompt for llama3.2 tends to overindex on
tool calling and doesn't work well when the prompt does not require tool
calling.
This PR adds an option to override the default system prompt, and
organizes tool-related configs into a new config object.
- [ ] Addresses issue (#issue)
## Test Plan
python -m unittest
llama_stack.providers.tests.inference.test_prompt_adapter
## 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.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/meta-llama/llama-stack/pull/937).
* #938
* __->__ #937
Lint check in main branch is failing. This fixes the lint check after we
moved to ruff in https://github.com/meta-llama/llama-stack/pull/921. We
need to move to a `ruff.toml` file as well as fixing and ignoring some
additional checks.
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
Making a few small naming changes as per feedback:
- RAGToolRuntime methods are called `insert` and `query` to keep them
more general
- The tool names are changed to non-namespaced forms
`insert_into_memory` and `query_from_memory`
- The REST endpoints are more REST-ful
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
```
See https://github.com/meta-llama/llama-stack/issues/827 for the broader
design.
Second part:
- updates routing table / router code
- updates the faiss implementation
## Test Plan
```
pytest -s -v -k sentence test_vector_io.py --env EMBEDDING_DIMENSION=384
```
See https://github.com/meta-llama/llama-stack/issues/827 for the broader
design.
This is the first part:
- delete other kinds of memory banks (keyvalue, keyword, graph) for now;
we will introduce a keyvalue store API as part of this design but not
use it in the RAG tool yet.
- renaming of the APIs
# Context
For test automation, the end goal is to run a single pytest command from
root test directory (llama_stack/providers/tests/.) such that we execute
push-blocking tests
The work plan:
1) trigger pytest from llama_stack/providers/tests/.
2) use config file to determine what tests and parametrization we want
to run
# What does this PR do?
1) consolidates the "inference-models" / "embedding-model" /
"judge-model" ... options in root conftest.py. Without this change, we
will hit into error when trying to run `pytest
/Users/sxyi/llama-stack/llama_stack/providers/tests/.` because of
duplicated `addoptions` definitions across child conftest files.
2) Add a `config` option to specify test config in YAML. (see
[`ci_test_config.yaml`](https://gist.github.com/sixianyi0721/5b37fbce4069139445c2f06f6e42f87e)
for example config file)
For provider_fixtures, we allow users to use either a default fixture
combination or define their own {api:provider} combinations.
```
memory:
....
fixtures:
provider_fixtures:
- default_fixture_param_id: ollama // use default fixture combination with param_id="ollama" in [providers/tests/memory/conftest.py](https://fburl.com/mtjzwsmk)
- inference: sentence_transformers
memory: faiss
- default_fixture_param_id: chroma
```
3) generate tests according to the config. Logic lives in two places:
a) in `{api}/conftest.py::pytest_generate_tests`, we read from config to
do parametrization.
b) after test collection, in `pytest_collection_modifyitems`, we filter
the tests to include only functions listed in config.
## Test Plan
1) `pytest /Users/sxyi/llama-stack/llama_stack/providers/tests/.
--collect-only --config=ci_test_config.yaml`
Using `--collect-only` tag to print the pytests listed in the config
file (`ci_test_config.yaml`).
output:
[gist](https://gist.github.com/sixianyi0721/05145e60d4d085c17cfb304beeb1e60e)
2) sanity check on `--inference-model` option
```
pytest -v -s -k "ollama" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py
```
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [x] Ran pre-commit to handle lint / formatting issues.
- [x] 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?
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
# What does this PR do?
We are setting a default value of json for tool prompt format, which
conflicts with llama 3.2/3.3 models since they use python list. This PR
changes the defaults to None and in the code, we infer default based on
the model.
Addresses: #695
Tests:
❯ LLAMA_STACK_BASE_URL=http://localhost:5000 pytest -v
tests/client-sdk/inference/test_inference.py -k
"test_text_chat_completion"
pytest llama_stack/providers/tests/inference/test_prompt_adapter.py
# What does this PR do?
PR #639 introduced the notion of Tools API and ability to invoke tools
through API just as any resource. This PR changes the Agents to start
using the Tools API to invoke tools. Major changes include:
1) Ability to specify tool groups with AgentConfig
2) Agent gets the corresponding tool definitions for the specified tools
and pass along to the model
3) Attachements are now named as Documents and their behavior is mostly
unchanged from user perspective
4) You can specify args that can be injected to a tool call through
Agent config. This is especially useful in case of memory tool, where
you want the tool to operate on a specific memory bank.
5) You can also register tool groups with args, which lets the agent
inject these as well into the tool call.
6) All tests have been migrated to use new tools API and fixtures
including client SDK tests
7) Telemetry just works with tools API because of our trace protocol
decorator
## 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
pytest -s -v -k together llama_stack/providers/tests/tools/test_tools.py \
--safety-shield=meta-llama/Llama-Guard-3-8B \
--inference-model=meta-llama/Llama-3.1-8B-Instruct
LLAMA_STACK_CONFIG="/Users/dineshyv/.llama/distributions/llamastack-together/together-run.yaml" pytest -v tests/client-sdk/agents/test_agents.py
```
run.yaml:
https://gist.github.com/dineshyv/0365845ad325e1c2cab755788ccc5994
Notebook:
https://colab.research.google.com/drive/1ck7hXQxRl6UvT-ijNRZ-gMZxH1G3cN2d?usp=sharing
## 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
```
