# What does this PR do?
The goal of this PR is code base modernization.
Schema reflection code needed a minor adjustment to handle UnionTypes
and collections.abc.AsyncIterator. (Both are preferred for latest Python
releases.)
Note to reviewers: almost all changes here are automatically generated
by pyupgrade. Some additional unused imports were cleaned up. The only
change worth of note can be found under `docs/openapi_generator` and
`llama_stack/strong_typing/schema.py` where reflection code was updated
to deal with "newer" types.
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# 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?
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?
- 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>
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
```
* persist registered objects with distribution
* linter fixes
* comment
* use annotate and field discriminator
* workign tests
* donot use global state
* precommit failures fixed
* add back Any
* fix imports
* remove unnecessary changes in ollama
* precommit failures fixed
* make kvstore configurable for dist and rename registry
* add comment about registry list return
* fix linter errors
* use registry to hydrate
* remove debug print
* linter fixes
* remove kvstore.db
* rename distribution_registry_store
---------
Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
This PR makes several core changes to the developer experience surrounding Llama Stack.
Background: PR #92 introduced the notion of "routing" to the Llama Stack. It introduces three object types: (1) models, (2) shields and (3) memory banks. Each of these objects can be associated with a distinct provider. So you can get model A to be inferenced locally while model B, C can be inference remotely (e.g.)
However, this had a few drawbacks:
you could not address the provider instances -- i.e., if you configured "meta-reference" with a given model, you could not assign an identifier to this instance which you could re-use later.
the above meant that you could not register a "routing_key" (e.g. model) dynamically and say "please use this existing provider I have already configured" for a new model.
the terms "routing_table" and "routing_key" were exposed directly to the user. in my view, this is way too much overhead for a new user (which almost everyone is.) people come to the stack wanting to do ML and encounter a completely unexpected term.
What this PR does: This PR structures the run config with only a single prominent key:
- providers
Providers are instances of configured provider types. Here's an example which shows two instances of the remote::tgi provider which are serving two different models.
providers:
inference:
- provider_id: foo
provider_type: remote::tgi
config: { ... }
- provider_id: bar
provider_type: remote::tgi
config: { ... }
Secondly, the PR adds dynamic registration of { models | shields | memory_banks } to the API surface. The distribution still acts like a "routing table" (as previously) except that it asks the backing providers for a listing of these objects. For example it asks a TGI or Ollama inference adapter what models it is serving. Only the models that are being actually served can be requested by the user for inference. Otherwise, the Stack server will throw an error.
When dynamically registering these objects, you can use the provider IDs shown above. Info about providers can be obtained using the Api.inspect set of endpoints (/providers, /routes, etc.)
The above examples shows the correspondence between inference providers and models registry items. Things work similarly for the safety <=> shields and memory <=> memory_banks pairs.
Registry: This PR also makes it so that Providers need to implement additional methods for registering and listing objects. For example, each Inference provider is now expected to implement the ModelsProtocolPrivate protocol (naming is not great!) which consists of two methods
register_model
list_models
The goal is to inform the provider that a certain model needs to be supported so the provider can make any relevant backend changes if needed (or throw an error if the model cannot be supported.)
There are many other cleanups included some of which are detailed in a follow-up comment.
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.
