## What does this PR do?
In this PR, we refactor the meta reference inference logic to support
- load the model during registering model instead of during spinning up
server
- support inference finetuned model checkpoint on top of native llama
model
## Why need these changes
To solve the existing pain points that
- user cannot lazy load the model and hot switch the inference
checkpoint after spinning up the server
- this blocks us doing inference and eval on the same sever for a
finetuned checkpoint after post training
- user cannot do inference on a finetuned checkpoint on top of native
llama models
## Expect user experience change
- The inference model won't be loaded when spinning up server. Instead,
it will be loaded during register model. If user add the model as models
resource in run.yaml, it will be registered and loaded automatically
when starting server. There is an optional flag 'skip_initialize' in
model metadata to skip model loading during registration.
- There is an optional flag 'llama_model' in model metadata to identify
the base model of the Model class for validation and initialize model
arch. model identifier no longer needs to be a native llama model
- the default inference model name updates from
'meta-llama/Llama-3.2-3B-Instruct' to 'Llama3.2-3B-Instruct'
- It aligns with the checkpoint folder name after running 'llama model
download'
- It aligns with the descriptor name defined in llama-models SKU list
bf5b0c4fe7/models/datatypes.py (L95)
## test
run python llama_stack/scripts/distro_codegen.py
**run unit test**
- torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference"
--inference-model="Llama3.1-8B-Instruct"
./llama_stack/providers/tests/inference/test_text_inference.py
- torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference"
--inference-model="Llama3.1-8B-Instruct"
./llama_stack/providers/tests/inference/test_model_registration.py
**test post training experience**
on server side run: llama stack run
llama_stack/templates/experimental-post-training/run.yaml
server is spinning up without model loaded
<img width="812" alt="Screenshot 2024-12-17 at 1 24 50 PM"
src="https://github.com/user-attachments/assets/ce1f606b-3b6f-452f-b48e-b3761ffd90f3"
/>
on client side, run: llama-stack-client --endpoint
http://devgpu018.nha2.facebook.com:5000 models register
Llama3.2-3B-Instruct
register model successfully and the model is loaded
<img width="1111" alt="Screenshot 2024-12-17 at 1 26 30 PM"
src="https://github.com/user-attachments/assets/56e02131-cf7d-4de5-8f63-fbdcb8c55c26"
/>
<img width="1541" alt="Screenshot 2024-12-17 at 1 26 09 PM"
src="https://github.com/user-attachments/assets/a83255a1-20f5-40a2-af51-55641410a115"
/>
if add "skip_initialize" in metadata, model is registered but isn't
loaded
on client side, run: llama-stack-client --endpoint
http://devgpu018.nha2.facebook.com:5000 inference chat-completion
--message "hello, what model are you?"
Inference the model succesfully
<img width="1121" alt="Screenshot 2024-12-17 at 1 27 33 PM"
src="https://github.com/user-attachments/assets/8e708545-3fe7-4a73-8754-1470fa5f1e75"
/>
**test inference experience**
run: llama stack run llama_stack/templates/meta-reference-gpu/run.yaml
model is loaded since the model is in resouce list in run.yaml
<img width="1537" alt="Screenshot 2024-12-17 at 1 30 19 PM"
src="https://github.com/user-attachments/assets/5c8af817-66eb-43f8-bf4c-f5e24b0a12c6"
/>
on client side, run: llama-stack-client --endpoint
http://devgpu018.nha2.facebook.com:5000 inference chat-completion
--message "hello, what model are you?"
inference successfully
<img width="1123" alt="Screenshot 2024-12-17 at 1 31 08 PM"
src="https://github.com/user-attachments/assets/471809aa-c65e-46dc-a37e-7094fb857f97"
/>
## inference on a finetuned model
**register a finetuned model that finetuned by post training api
(torchtune)**
- the model is registered and loaded successfully
- the model is shown up in the model list
<img width="974" alt="Screenshot 2024-12-18 at 3 56 33 PM"
src="https://github.com/user-attachments/assets/2994b4f5-4fa9-40c6-acc6-4b971479f3e2"
/>
**run inference**
<img width="977" alt="Screenshot 2024-12-18 at 3 57 59 PM"
src="https://github.com/user-attachments/assets/d117abbc-b2a0-41d8-a028-1a13128787b2"
/>
## 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?
Adds the sentence transformer provider and the `all-MiniLM-L6-v2`
embedding model to the default models to register in the run.yaml for
all providers.
## Test Plan
llama stack build --template together --image-type conda
llama stack run
~/.llama/distributions/llamastack-together/together-run.yaml
# What does this PR do?
adds a test for the completion api's logprobs parameter
tbd which providers pass this test
## 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.
- [x] Wrote necessary unit or integration tests.
This PR does the following:
1) adds the ability to generate embeddings in all supported inference
providers.
2) Moves all the memory providers to use the inference API and improved
the memory tests to setup the inference stack correctly and use the
embedding models
This is a merge from #589 and #598
# What does this PR do?
add the completion api to the nvidia inference provider
## Test Plan
while running the meta/llama-3.1-8b-instruct NIM from
https://build.nvidia.com/meta/llama-3_1-8b-instruct?snippet_tab=Docker
```
➜ pytest -s -v --providers inference=nvidia llama_stack/providers/tests/inference/ --env NVIDIA_BASE_URL=http://localhost:8000 -k test_completion --inference-model Llama3.1-8B-Instruct
=============================================== test session starts ===============================================
platform linux -- Python 3.10.15, pytest-8.3.3, pluggy-1.5.0 -- /home/matt/.conda/envs/stack/bin/python
cachedir: .pytest_cache
rootdir: /home/matt/Documents/Repositories/meta-llama/llama-stack
configfile: pyproject.toml
plugins: anyio-4.6.2.post1, asyncio-0.24.0, httpx-0.34.0
asyncio: mode=strict, default_loop_scope=None
collected 20 items / 18 deselected / 2 selected
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion[-nvidia] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_structured_output[-nvidia] SKIPPED
============================= 1 passed, 1 skipped, 18 deselected, 6 warnings in 5.40s =============================
```
the structured output functionality works but the accuracy fails
## 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.
- [x] Wrote necessary unit or integration tests.
# What does this PR do?
Addresses issue (#391)
- Adds json structured output for vLLM
- Enables structured output tests for vLLM
> Give me a recipe for Spaghetti Bolognaise:
```json
{
"recipe_name": "Spaghetti Bolognaise",
"preamble": "Ah, spaghetti bolognaise - the quintessential Italian dish that fills my kitchen with the aromas of childhood nostalgia. As a child, I would watch my nonna cook up a big pot of spaghetti bolognaise every Sunday, filling our small Italian household with the savory scent of simmering meat and tomatoes. The way the sauce would thicken and the spaghetti would al dente - it was love at first bite. And now, as a chef, I want to share that same love with you, so you can recreate these warm, comforting memories at home.",
"ingredients": [
"500g minced beef",
"1 medium onion, finely chopped",
"2 cloves garlic, minced",
"1 carrot, finely chopped",
" celery, finely chopped",
"1 (28 oz) can whole peeled tomatoes",
"1 tbsp tomato paste",
"1 tsp dried basil",
"1 tsp dried oregano",
"1 tsp salt",
"1/2 tsp black pepper",
"1/2 tsp sugar",
"1 lb spaghetti",
"Grated Parmesan cheese, for serving",
"Extra virgin olive oil, for serving"
],
"steps": [
"Heat a large pot over medium heat and add a generous drizzle of extra virgin olive oil.",
"Add the chopped onion, garlic, carrot, and celery and cook until the vegetables are soft and translucent, about 5-7 minutes.",
"Add the minced beef and cook until browned, breaking it up with a spoon as it cooks.",
"Add the tomato paste and cook for 1-2 minutes, stirring constantly.",
"Add the canned tomatoes, dried basil, dried oregano, salt, black pepper, and sugar. Stir well to combine.",
"Bring the sauce to a simmer and let it cook for 20-30 minutes, stirring occasionally, until the sauce has thickened and the flavors have melded together.",
"While the sauce cooks, bring a large pot of salted water to a boil and cook the spaghetti according to the package instructions until al dente. Reserve 1 cup of pasta water before draining the spaghetti.",
"Add the reserved pasta water to the sauce and stir to combine.",
"Combine the cooked spaghetti and sauce, tossing to coat the pasta evenly.",
"Serve hot, topped with grated Parmesan cheese and a drizzle of extra virgin olive oil.",
"Enjoy!"
]
}
```
Generated with Llama-3.2-3B-Instruct model - pretty good for a 3B
parameter model 👍
## Test Plan
`pytest -v -s
llama_stack/providers/tests/inference/test_text_inference.py -k
llama_3b-vllm_remote`
With the following setup:
```bash
# Environment
export INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
export INFERENCE_PORT=8000
export VLLM_URL=http://localhost:8000/v1
# vLLM server
sudo docker run --gpus all \
-v $STORAGE_DIR/.cache/huggingface:/root/.cache/huggingface \
--env "HUGGING_FACE_HUB_TOKEN=$(cat ~/.cache/huggingface/token)" \
-p 8000:$INFERENCE_PORT \
--ipc=host \
--net=host \
vllm/vllm-openai:v0.6.3.post1 \
--model $INFERENCE_MODEL
# llama-stack server
llama stack build --template remote-vllm --image-type conda && llama stack run distributions/remote-vllm/run.yaml \
--port 5001 \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
```
Results:
```
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_model_list[llama_3b-vllm_remote] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion[llama_3b-vllm_remote] SKIPPED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completions_structured_output[llama_3b-vllm_remote] SKIPPED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_non_streaming[llama_3b-vllm_remote] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_structured_output[llama_3b-vllm_remote] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_streaming[llama_3b-vllm_remote] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling[llama_3b-vllm_remote] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling_streaming[llama_3b-vllm_remote] PASSED
================================ 6 passed, 2 skipped, 120 deselected, 2 warnings in 13.26s ================================
```
## Sources
- https://github.com/vllm-project/vllm/discussions/8300
- By default, vLLM uses https://github.com/dottxt-ai/outlines for
structured outputs
[[1](32e7db2536/vllm/engine/arg_utils.py (L279-L280))]
## Before submitting
[N/A] 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?
[N/A?] Updated relevant documentation. Couldn't find any relevant
documentation. Lmk if I've missed anything.
- [x] Wrote necessary unit or integration tests.
i find `test_structured_output` to be flakey. it's both a functionality
and accuracy test -
```
answer = AnswerFormat.model_validate_json(response.completion_message.content)
assert answer.first_name == "Michael"
assert answer.last_name == "Jordan"
assert answer.year_of_birth == 1963
assert answer.num_seasons_in_nba == 15
```
it's an accuracy test because it checks the value of first/last name,
birth year, and num seasons.
i find that -
- llama-3.1-8b-instruct and llama-3.2-3b-instruct pass the functionality
portion
- llama-3.2-3b-instruct consistently fails the accuracy portion
(thinking MJ was in the NBA for 14 seasons)
- llama-3.1-8b-instruct occasionally fails the accuracy portion
suggestions (not mutually exclusive) -
1. turn the test into functionality only, skip the value checks
2. split the test into a functionality version and an xfail accuracy
version
3. add context to the prompt so the llm can answer without accessing
embedded memory
# What does this PR do?
implements option (3) by adding context to the system prompt.
## Test Plan
`pytest -s -v ... llama_stack/providers/tests/inference/ ... -k
structured_output`
## Before submitting
- [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?
- [x] Updated relevant documentation.
- [x] Wrote necessary unit or integration tests.
# What does this PR do?
* Add a test fixture for tgi
* Fixes the logic to correctly pass the llama model for chat completion
Fixes#514
## Test Plan
pytest -k "tgi"
llama_stack/providers/tests/inference/test_text_inference.py --env
TGI_URL=http://localhost:$INFERENCE_PORT --env TGI_API_TOKEN=$HF_TOKEN
# What does this PR do?
this PR adds a basic inference adapter to NVIDIA NIMs
what it does -
- chat completion api
- tool calls
- streaming
- structured output
- logprobs
- support hosted NIM on integrate.api.nvidia.com
- support downloaded NIM containers
what it does not do -
- completion api
- embedding api
- vision models
- builtin tools
- have certainty that sampling strategies are correct
## Feature/Issue validation/testing/test plan
`pytest -s -v --providers inference=nvidia
llama_stack/providers/tests/inference/ --env NVIDIA_API_KEY=...`
all tests should pass. there are pydantic v1 warnings.
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [x] Did you read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
Pull Request section?
- [ ] Was this discussed/approved via a Github issue? Please add a link
to it if that's the case.
- [ ] Did you make sure to update the documentation with your changes?
- [x] Did you write any new necessary tests?
Thanks for contributing 🎉!
# What does this PR do?
As the title says.
## Test Plan
This needs
8752149f58
to also land. So the next package (0.0.54) will make this work properly.
The test is:
```bash
pytest -v -s -m "llama_3b and meta_reference" test_model_registration.py
```
This PR allows models to be registered with provider as long as the user
specifies a llama model, even though the model does not match our
prebuilt provider specific mapping.
Test:
pytest -v -s
llama_stack/providers/tests/inference/test_model_registration.py -m
"together" --env TOGETHER_API_KEY=<KEY>
---------
Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
The semantics of an Update on resources is very tricky to reason about
especially for memory banks and models. The best way to go forward here
is for the user to unregister and register a new resource. We don't have
a compelling reason to support update APIs.
Tests:
pytest -v -s llama_stack/providers/tests/memory/test_memory.py -m
"chroma" --env CHROMA_HOST=localhost --env CHROMA_PORT=8000
pytest -v -s llama_stack/providers/tests/memory/test_memory.py -m
"pgvector" --env PGVECTOR_DB=postgres --env PGVECTOR_USER=postgres --env
PGVECTOR_PASSWORD=mysecretpassword --env PGVECTOR_HOST=0.0.0.0
$CONDA_PREFIX/bin/pytest -v -s -m "ollama"
llama_stack/providers/tests/inference/test_model_registration.py
---------
Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
# What does this PR do?
This PR kills the notion of "pure passthrough" remote providers. You
cannot specify a single provider you must specify a whole distribution
(stack) as remote.
This PR also significantly fixes / upgrades testing infrastructure so
you can now test against a remotely hosted stack server by just doing
```bash
pytest -s -v -m remote test_agents.py \
--inference-model=Llama3.1-8B-Instruct --safety-shield=Llama-Guard-3-1B \
--env REMOTE_STACK_URL=http://localhost:5001
```
Also fixed `test_agents_persistence.py` (which was broken) and killed
some deprecated testing functions.
## Test Plan
All the tests.
This PR changes the way model id gets translated to the final model name
that gets passed through the provider.
Major changes include:
1) Providers are responsible for registering an object and as part of
the registration returning the object with the correct provider specific
name of the model provider_resource_id
2) To help with the common look ups different names a new ModelLookup
class is created.
Tested all inference providers including together, fireworks, vllm,
ollama, meta reference and bedrock
# What does this PR do?
This is a follow-up to #425. That PR allows for specifying models in the
registry, but each entry needs to look like:
```yaml
- identifier: ...
provider_id: ...
provider_resource_identifier: ...
```
This is headache-inducing.
The current PR makes this situation better by adopting the shape of our
APIs. Namely, we need the user to only specify `model-id`. The rest
should be optional and figured out by the Stack. You can always override
it.
Here's what example `ollama` "full stack" registry looks like (we still
need to kill or simplify shield_type crap):
```yaml
models:
- model_id: Llama3.2-3B-Instruct
- model_id: Llama-Guard-3-1B
shields:
- shield_id: llama_guard
shield_type: llama_guard
```
## Test Plan
See test plan for #425. Re-ran it.
# What does this PR do?
This PR brings back the facility to not force registration of resources
onto the user. This is not just annoying but actually not feasible
sometimes. For example, you may have a Stack which boots up with private
providers for inference for models A and B. There is no way for the user
to actually know which model is being served by these providers now (to
be able to register it.)
How will this avoid the users needing to do registration? In a follow-up
diff, I will make sure I update the sample run.yaml files so they list
the models served by the distributions explicitly. So when users do
`llama stack build --template <...>` and run it, their distributions
come up with the right set of models they expect.
For self-hosted distributions, it also allows us to have a place to
explicit list the models that need to be served to make the "complete"
stack (including safety, e.g.)
## Test Plan
Started ollama locally with two lightweight models: Llama3.2-3B-Instruct
and Llama-Guard-3-1B.
Updated all the tests including agents. Here's the tests I ran so far:
```bash
pytest -s -v -m "fireworks and llama_3b" test_text_inference.py::TestInference \
--env FIREWORKS_API_KEY=...
pytest -s -v -m "ollama and llama_3b" test_text_inference.py::TestInference
pytest -s -v -m ollama test_safety.py
pytest -s -v -m faiss test_memory.py
pytest -s -v -m ollama test_agents.py \
--inference-model=Llama3.2-3B-Instruct --safety-model=Llama-Guard-3-1B
```
Found a few bugs here and there pre-existing that these test runs fixed.
Splits the meta-reference safety implementation into three distinct providers:
- inline::llama-guard
- inline::prompt-guard
- inline::code-scanner
Note that this PR is a backward incompatible change to the llama stack server. I have added deprecation_error field to ProviderSpec -- the server reads it and immediately barfs. This is used to direct the user with a specific message on what action to perform. An automagical "config upgrade" is a bit too much work to implement right now :/
(Note that we will be gradually prefixing all inline providers with inline:: -- I am only doing this for this set of new providers because otherwise existing configuration files will break even more badly.)
* init
* working bedrock tests
* bedrock test for inference fixes
* use env vars for bedrock guardrail vars
* add register in meta reference
* use correct shield impl in meta ref
* dont add together fixture
* right naming
* minor updates
* improved registration flow
* address feedback
---------
Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
* Enable vision models for Together and Fireworks
* Works with ollama 0.4.0 pre-release with the vision model
* localize media for meta_reference inference
* Fix
* Significantly simpler and malleable test setup
* convert memory tests
* refactor fixtures and add support for composable fixtures
* Fix memory to use the newer fixture organization
* Get agents tests working
* Safety tests work
* yet another refactor to make this more general
now it accepts --inference-model, --safety-model options also
* get multiple providers working for meta-reference (for inference + safety)
* Add README.md
---------
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
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.
