# What does this PR do?
Move around bits. This makes the copies from llama-models _much_ easier
to maintain and ensures we don't entangle meta-reference specific
tidbits into llama-models code even by accident.
Also, kills the meta-reference-quantized-gpu distro and rolls
quantization deps into meta-reference-gpu.
## Test Plan
```
LLAMA_MODELS_DEBUG=1 \
with-proxy llama stack run meta-reference-gpu \
--env INFERENCE_MODEL=meta-llama/Llama-4-Scout-17B-16E-Instruct \
--env INFERENCE_CHECKPOINT_DIR=<DIR> \
--env MODEL_PARALLEL_SIZE=4 \
--env QUANTIZATION_TYPE=fp8_mixed
```
Start a server with and without quantization. Point integration tests to
it using:
```
pytest -s -v tests/integration/inference/test_text_inference.py \
--stack-config http://localhost:8321 --text-model meta-llama/Llama-4-Scout-17B-16E-Instruct
```
# What does this PR do?
- **chore: mypy for strong_typing**
- **chore: mypy for remote::vllm**
- **chore: mypy for remote::ollama**
- **chore: mypy for providers.datatype**
---------
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
Don't set type variables from register_schema().
`mypy` is not happy about it since type variables are calculated at
runtime and hence the typing hints are not available during static
analysis.
Good news is there is no good reason to set the variables from the
return type.
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
Summary:
This is not used anywhere.
closes#1421
Test Plan:
LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/integration/agents/test_agents.py --safety-shield
meta-llama/Llama-Guard-3-8B --text-model
meta-llama/Llama-3.1-8B-Instruct --record-responses
# 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?
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?
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 =========================================================
```
Summary:
Allows tools to output metadata. This is useful for evaluating tool
outputs, e.g. RAG tool will output document IDs, which can be used to
score recall.
Will need to make a similar change on the client side to support
ClientTool outputting metadata.
Test Plan:
LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/client-sdk/agents/test_agents.py
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`
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?
Defines a MetricResponseMixin which can be inherited by any response
class. Adds it to chat completion response types.
This is a short term solution to allow inference API to return metrics
The ideal way to do this is to have a way for all response types to
include metrics
and all metric events logged to the telemetry API to be included with
the response
To do this, we will need to augment all response types with a metrics
field.
We have hit a blocker from stainless SDK that prevents us from doing
this.
The blocker is that if we were to augment the response types that have a
data field
in them like so
class ListModelsResponse(BaseModel):
metrics: Optional[List[MetricEvent]] = None
data: List[Models]
...
The client SDK will need to access the data by using a .data field,
which is not
ergonomic. Stainless SDK does support unwrapping the response type, but
it
requires that the response type to only have a single field.
We will need a way in the client SDK to signal that the metrics are
needed
and if they are needed, the client SDK has to return the full response
type
without unwrapping it.
## Test Plan
sh run_openapi_generator.sh ./
sh stainless_sync.sh dineshyv/dev add-metrics-to-resp-v4
LLAMA_STACK_CONFIG="/Users/dineshyv/.llama/distributions/fireworks/fireworks-run.yaml"
pytest -v tests/client-sdk/agents/test_agents.py
# 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>
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
```
# 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?
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
```
# What does this PR do?
Change the Telemetry API to be able to support different use cases like
returning traces for the UI and ability to export for Evals.
Other changes:
* Add a new trace_protocol decorator to decorate all our API methods so
that any call to them will automatically get traced across all impls.
* There is some issue with the decorator pattern of span creation when
using async generators, where there are multiple yields with in the same
context. I think its much more explicit by using the explicit context
manager pattern using with. I moved the span creations in agent instance
to be using with
* Inject session id at the turn level, which should quickly give us all
traces across turns for a given session
Addresses #509
## Test Plan
```
llama stack run /Users/dineshyv/.llama/distributions/llamastack-together/together-run.yaml
PYTHONPATH=. python -m examples.agents.rag_with_memory_bank localhost 5000
curl -X POST 'http://localhost:5000/alpha/telemetry/query-traces' \
-H 'Content-Type: application/json' \
-d '{
"attribute_filters": [
{
"key": "session_id",
"op": "eq",
"value": "dd667b87-ca4b-4d30-9265-5a0de318fc65" }],
"limit": 100,
"offset": 0,
"order_by": ["start_time"]
}' | jq .
[
{
"trace_id": "6902f54b83b4b48be18a6f422b13e16f",
"root_span_id": "5f37b85543afc15a",
"start_time": "2024-12-04T08:08:30.501587",
"end_time": "2024-12-04T08:08:36.026463"
},
{
"trace_id": "92227dac84c0615ed741be393813fb5f",
"root_span_id": "af7c5bb46665c2c8",
"start_time": "2024-12-04T08:08:36.031170",
"end_time": "2024-12-04T08:08:41.693301"
},
{
"trace_id": "7d578a6edac62f204ab479fba82f77b6",
"root_span_id": "1d935e3362676896",
"start_time": "2024-12-04T08:08:41.695204",
"end_time": "2024-12-04T08:08:47.228016"
},
{
"trace_id": "dbd767d76991bc816f9f078907dc9ff2",
"root_span_id": "f5a7ee76683b9602",
"start_time": "2024-12-04T08:08:47.234578",
"end_time": "2024-12-04T08:08:53.189412"
}
]
curl -X POST 'http://localhost:5000/alpha/telemetry/get-span-tree' \
-H 'Content-Type: application/json' \
-d '{ "span_id" : "6cceb4b48a156913", "max_depth": 2, "attributes_to_return": ["input"] }' | jq .
% Total % Received % Xferd Average Speed Time Time Time Current
Dload Upload Total Spent Left Speed
100 875 100 790 100 85 18462 1986 --:--:-- --:--:-- --:--:-- 20833
{
"span_id": "6cceb4b48a156913",
"trace_id": "dafa796f6aaf925f511c04cd7c67fdda",
"parent_span_id": "892a66d726c7f990",
"name": "retrieve_rag_context",
"start_time": "2024-12-04T09:28:21.781995",
"end_time": "2024-12-04T09:28:21.913352",
"attributes": {
"input": [
"{\"role\":\"system\",\"content\":\"You are a helpful assistant\"}",
"{\"role\":\"user\",\"content\":\"What are the top 5 topics that were explained in the documentation? Only list succinct bullet points.\",\"context\":null}"
]
},
"children": [
{
"span_id": "1a2df181854064a8",
"trace_id": "dafa796f6aaf925f511c04cd7c67fdda",
"parent_span_id": "6cceb4b48a156913",
"name": "MemoryRouter.query_documents",
"start_time": "2024-12-04T09:28:21.787620",
"end_time": "2024-12-04T09:28:21.906512",
"attributes": {
"input": null
},
"children": [],
"status": "ok"
}
],
"status": "ok"
}
```
<img width="1677" alt="Screenshot 2024-12-04 at 9 42 56 AM"
src="https://github.com/user-attachments/assets/4d3cea93-05ce-415a-93d9-4b1628631bf8">
# 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.
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
Added support for structured output in the API and added a reference implementation for meta-reference.
A few notes:
* Two formats are specified in the API: Json schema and EBNF based grammar
* Implementation only supports Json for now
We use lm-format-enhancer to provide the implementation right now but may change this especially because BNF grammars aren't supported by that library.
Fireworks has support for structured output and Together has limited supported for it too. Subsequent PRs will add these changes. We would like all our inference providers to provide structured output for llama models since it is an extremely important and highly sought-after need by the developers.
PR #201 had made several changes while trying to fix issues with getting the stream=False branches of inference and agents API working. As part of this, it made a change which was slightly gratuitous. Namely, making chat_completion() and brethren "def" instead of "async def".
The rationale was that this allowed the user (within llama-stack) of this to use it as:
```
async for chunk in api.chat_completion(params)
```
However, it causes unnecessary confusion for several folks. Given that clients (e.g., llama-stack-apps) anyway use the SDK methods (which are completely isolated) this choice was not ideal. Let's revert back so the call now looks like:
```
async for chunk in await api.chat_completion(params)
```
Bonus: Added a completion() implementation for the meta-reference provider. Technically should have been another PR :)
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.
Test Plan:
First, start a TGI container with `meta-llama/Llama-Guard-3-8B` model
serving on port 5099. See https://github.com/meta-llama/llama-stack/pull/53 and its
description for how.
Then run llama-stack with the following run config:
```
image_name: safety
docker_image: null
conda_env: safety
apis_to_serve:
- models
- inference
- shields
- safety
api_providers:
inference:
providers:
- remote::tgi
safety:
providers:
- meta-reference
telemetry:
provider_id: meta-reference
config: {}
routing_table:
inference:
- provider_id: remote::tgi
config:
url: http://localhost:5099
api_token: null
hf_endpoint_name: null
routing_key: Llama-Guard-3-8B
safety:
- provider_id: meta-reference
config:
llama_guard_shield:
model: Llama-Guard-3-8B
excluded_categories: []
disable_input_check: false
disable_output_check: false
prompt_guard_shield: null
routing_key: llama_guard
```
Now simply run `python -m llama_stack.apis.safety.client localhost
<port>` and check that the llama_guard shield calls run correctly. (The
injection_shield calls fail as expected since we have not set up a
router for them.)
* API Keys passed from Client instead of distro configuration
* delete distribution registry
* Rename the "package" word away
* Introduce a "Router" layer for providers
Some providers need to be factorized and considered as thin routing
layers on top of other providers. Consider two examples:
- The inference API should be a routing layer over inference providers,
routed using the "model" key
- The memory banks API is another instance where various memory bank
types will be provided by independent providers (e.g., a vector store
is served by Chroma while a keyvalue memory can be served by Redis or
PGVector)
This commit introduces a generalized routing layer for this purpose.
* update `apis_to_serve`
* llama_toolchain -> llama_stack
* Codemod from llama_toolchain -> llama_stack
- added providers/registry
- cleaned up api/ subdirectories and moved impls away
- restructured api/api.py
- from llama_stack.apis.<api> import foo should work now
- update imports to do llama_stack.apis.<api>
- update many other imports
- added __init__, fixed some registry imports
- updated registry imports
- create_agentic_system -> create_agent
- AgenticSystem -> Agent
* Moved some stuff out of common/; re-generated OpenAPI spec
* llama-toolchain -> llama-stack (hyphens)
* add control plane API
* add redis adapter + sqlite provider
* move core -> distribution
* Some more toolchain -> stack changes
* small naming shenanigans
* Removing custom tool and agent utilities and moving them client side
* Move control plane to distribution server for now
* Remove control plane from API list
* no codeshield dependency randomly plzzzzz
* Add "fire" as a dependency
* add back event loggers
* stack configure fixes
* use brave instead of bing in the example client
* add init file so it gets packaged
* add init files so it gets packaged
* Update MANIFEST
* bug fix
---------
Co-authored-by: Hardik Shah <hjshah@fb.com>
Co-authored-by: Xi Yan <xiyan@meta.com>
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
2024-09-17 19:51:35 -07:00
Renamed from llama_toolchain/inference/api/api.py (Browse further)
