Include the tool call details with the chat when doing Rag with Remote
vllm
Fixes: #1929
With this PR the tool call is included in the chat returned to vllm, the
model (meta-llama/Llama-3.1-8B-Instruct) the returns the answer as
expected.
Signed-off-by: Derek Higgins <derekh@redhat.com>
Test plan:
python tests/verifications/generate_report.py --providers
fireworks,together,llama_meta_ref,openai
Co-authored-by: Eric Huang <erichuang@fb.com>
# What does this PR do?
TLDR: Changes needed to get 100% passing tests for OpenAI API
verification tests when run against Llama Stack with the `together`,
`fireworks`, and `openai` providers. And `groq` is better than before,
at 88% passing.
This cleans up the OpenAI API support for image message types
(specifically `image_url` types) and handling of the `response_format`
chat completion parameter. Both of these required a few more Pydantic
model definitions in our Inference API, just to move from the
not-quite-right stubs I had in place to something fleshed out to match
the actual OpenAI API specs.
As part of testing this, I also found and fixed a bug in the litellm
implementation of openai_completion and openai_chat_completion, so the
providers based on those should actually be working now.
The method `prepare_openai_completion_params` in
`llama_stack/providers/utils/inference/openai_compat.py` was improved to
actually recursively clean up input parameters, including handling of
lists, dicts, and dumping of Pydantic models to dicts. These changes
were required to get to 100% passing tests on the OpenAI API
verification against the `openai` provider.
With the above, the together.ai provider was passing as well as it is
without Llama Stack. But, since we have Llama Stack in the middle, I
took the opportunity to clean up the together.ai provider so that it now
also passes the OpenAI API spec tests we have at 100%. That means
together.ai is now passing our verification test better when using an
OpenAI client talking to Llama Stack than it is when hitting together.ai
directly, without Llama Stack in the middle.
And, another round of work for Fireworks to improve translation of
incoming OpenAI chat completion requests to Llama Stack chat completion
requests gets the fireworks provider passing at 100%. The server-side
fireworks.ai tool calling support with OpenAI chat completions and Llama
4 models isn't great yet, but by pointing the OpenAI clients at Llama
Stack's API we can clean things up and get everything working as
expected for Llama 4 models.
## Test Plan
### OpenAI API Verification Tests
I ran the OpenAI API verification tests as below and 100% of the tests
passed.
First, start a Llama Stack server that runs the `openai` provider with
the `gpt-4o` and `gpt-4o-mini` models deployed. There's not a template
setup to do this out of the box, so I added a
`tests/verifications/openai-api-verification-run.yaml` to do this.
First, ensure you have the necessary API key environment variables set:
```
export TOGETHER_API_KEY="..."
export FIREWORKS_API_KEY="..."
export OPENAI_API_KEY="..."
```
Then, run a Llama Stack server that serves up all these providers:
```
llama stack run \
--image-type venv \
tests/verifications/openai-api-verification-run.yaml
```
Finally, generate a new verification report against all these providers,
both with and without the Llama Stack server in the middle.
```
python tests/verifications/generate_report.py \
--run-tests \
--provider \
together \
fireworks \
groq \
openai \
together-llama-stack \
fireworks-llama-stack \
groq-llama-stack \
openai-llama-stack
```
You'll see that most of the configurations with Llama Stack in the
middle now pass at 100%, even though some of them do not pass at 100%
when hitting the backend provider's API directly with an OpenAI client.
### OpenAI Completion Integration Tests with vLLM:
I also ran the smaller `test_openai_completion.py` test suite (that's
not yet merged with the verification tests) on multiple of the
providers, since I had to adjust the method signature of
openai_chat_completion a bit and thus had to touch lots of these
providers to match. Here's the tests I ran there, all passing:
```
VLLM_URL="http://localhost:8000/v1" INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" llama stack build --template remote-vllm --image-type venv --run
```
in another terminal
```
LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "meta-llama/Llama-3.2-3B-Instruct"
```
### OpenAI Completion Integration Tests with ollama
```
INFERENCE_MODEL="llama3.2:3b-instruct-q8_0" llama stack build --template ollama --image-type venv --run
```
in another terminal
```
LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="llama3.2:3b-instruct-q8_0" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "llama3.2:3b-instruct-q8_0"
```
### OpenAI Completion Integration Tests with together.ai
```
INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct-Turbo" llama stack build --template together --image-type venv --run
```
in another terminal
```
LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct-Turbo" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "meta-llama/Llama-3.2-3B-Instruct-Turbo"
```
### OpenAI Completion Integration Tests with fireworks.ai
```
INFERENCE_MODEL="meta-llama/Llama-3.1-8B-Instruct" llama stack build --template fireworks --image-type venv --run
```
in another terminal
```
LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="meta-llama/Llama-3.1-8B-Instruct" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "meta-llama/Llama-3.1-8B-Instruct"
---------
Signed-off-by: Ben Browning <bbrownin@redhat.com>
# What does this PR do?
This stubs in some OpenAI server-side compatibility with three new
endpoints:
/v1/openai/v1/models
/v1/openai/v1/completions
/v1/openai/v1/chat/completions
This gives common inference apps using OpenAI clients the ability to
talk to Llama Stack using an endpoint like
http://localhost:8321/v1/openai/v1 .
The two "v1" instances in there isn't awesome, but the thinking is that
Llama Stack's API is v1 and then our OpenAI compatibility layer is
compatible with OpenAI V1. And, some OpenAI clients implicitly assume
the URL ends with "v1", so this gives maximum compatibility.
The openai models endpoint is implemented in the routing layer, and just
returns all the models Llama Stack knows about.
The following providers should be working with the new OpenAI
completions and chat/completions API:
* remote::anthropic (untested)
* remote::cerebras-openai-compat (untested)
* remote::fireworks (tested)
* remote::fireworks-openai-compat (untested)
* remote::gemini (untested)
* remote::groq-openai-compat (untested)
* remote::nvidia (tested)
* remote::ollama (tested)
* remote::openai (untested)
* remote::passthrough (untested)
* remote::sambanova-openai-compat (untested)
* remote::together (tested)
* remote::together-openai-compat (untested)
* remote::vllm (tested)
The goal to support this for every inference provider - proxying
directly to the provider's OpenAI endpoint for OpenAI-compatible
providers. For providers that don't have an OpenAI-compatible API, we'll
add a mixin to translate incoming OpenAI requests to Llama Stack
inference requests and translate the Llama Stack inference responses to
OpenAI responses.
This is related to #1817 but is a bit larger in scope than just chat
completions, as I have real use-cases that need the older completions
API as well.
## Test Plan
### vLLM
```
VLLM_URL="http://localhost:8000/v1" INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" llama stack build --template remote-vllm --image-type venv --run
LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "meta-llama/Llama-3.2-3B-Instruct"
```
### ollama
```
INFERENCE_MODEL="llama3.2:3b-instruct-q8_0" llama stack build --template ollama --image-type venv --run
LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="llama3.2:3b-instruct-q8_0" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "llama3.2:3b-instruct-q8_0"
```
## Documentation
Run a Llama Stack distribution that uses one of the providers mentioned
in the list above. Then, use your favorite OpenAI client to send
completion or chat completion requests with the base_url set to
http://localhost:8321/v1/openai/v1 . Replace "localhost:8321" with the
host and port of your Llama Stack server, if different.
---------
Signed-off-by: Ben Browning <bbrownin@redhat.com>
# What does this PR do?
## Test Plan
export MODEL=accounts/fireworks/models/llama4-scout-instruct-basic;
LLAMA_STACK_CONFIG=verification pytest -s -v tests/integration/inference
--vision-model $MODEL --text-model $MODEL
# 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?
Currently, `ToolCall.arguments` is a `Dict[str, RecursiveType]`.
However, on the client SDK side -- the `RecursiveType` gets deserialized
into a number ( both int and float get collapsed ) and hence when params
are `int` they get converted to float which might break client side
tools that might be doing type checking.
Closes: https://github.com/meta-llama/llama-stack/issues/1683
### Test Plan
Stainless changes --
https://github.com/meta-llama/llama-stack-client-python/pull/204
```
pytest -s -v --stack-config=fireworks tests/integration/agents/test_agents.py --text-model meta-llama/Llama-3.1-8B-Instruct
```
# Summary:
Includes fixes to get test_agents working with openAI model, e.g. tool
parsing and message conversion
# Test Plan:
```
LLAMA_STACK_CONFIG=dev pytest -s -v tests/integration/agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B --text-model openai/gpt-4o-mini
```
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/meta-llama/llama-stack/pull/1550).
* #1556
* __->__ #1550
`ChatCompletionResponseEventType: start` is ignored and not yielded in
the agent_instance as we expect that to not have any content.
However, litellm sends first event as `ChatCompletionResponseEventType:
start` with content ( which was the first token that we were skipping )
```
LLAMA_STACK_CONFIG=dev pytest -s -v tests/client-sdk/agents/test_agents.py --inference-model "openai/gpt-4o-mini" -k test_agent_simple
```
This was failing before ( since the word hello was not in the final
response )
# What does this PR do?
Tool format depends on the model. @ehhuang introduced a
`get_default_tool_prompt_format` function for this purpose. We should
use that instead of hacky model ID matching we had before.
Secondly, non llama models don't have this concept so testing with those
models should work as is.
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```bash
for distro in fireworks ollama; do
LLAMA_STACK_CONFIG=$distro \
pytest -s -v tests/client-sdk/inference/test_text_inference.py \
--inference-model=meta-llama/Llama-3.2-3B-Instruct \
--vision-inference-model=""
done
LLAMA_STACK_CONFIG=dev \
pytest -s -v tests/client-sdk/inference/test_text_inference.py \
--inference-model=openai/gpt-4o \
--vision-inference-model=""
```
[//]: # (## Documentation)
There should be a choke-point for llama3.api imports -- this is the
prompt adapter. Creating a ChatFormat() object on demand is inexpensive.
The underlying Tokenizer is a singleton anyway.
# What does this PR do?
This fixes an issue when running the e2e agent example:
https://github.com/meta-llama/llama-stack-apps/blob/main/examples/agents/e2e_loop_with_client_tools.py
```
| File "/home/yutang/repos/llama-stack/llama_stack/providers/remote/inference/vllm/vllm.py", line 175, in _process_vllm_chat_completion_stream_response
| tool_call = convert_tool_call(choice.delta.tool_calls[0])
| File "/home/yutang/repos/llama-stack/llama_stack/providers/utils/inference/openai_compat.py", line 441, in convert_tool_call
| return ToolCall(
| File "/home/yutang/.conda/envs/distribution-myenv/lib/python3.10/site-packages/pydantic/main.py", line 214, in __init__
| validated_self = self.__pydantic_validator__.validate_python(data, self_instance=self)
| pydantic_core._pydantic_core.ValidationError: 4 validation errors for ToolCall
| call_id
| Input should be a valid string [type=string_type, input_value=None, input_type=NoneType]
| For further information visit https://errors.pydantic.dev/2.10/v/string_type
| tool_name.enum[BuiltinTool]
| Input should be 'brave_search', 'wolfram_alpha', 'photogen' or 'code_interpreter' [type=enum, input_value=None, input_type=NoneType]
| For further information visit https://errors.pydantic.dev/2.10/v/enum
| tool_name.str
| Input should be a valid string [type=string_type, input_value=None, input_type=NoneType]
| For further information visit https://errors.pydantic.dev/2.10/v/string_type
| arguments
| Input should be a valid dictionary [type=dict_type, input_value=202, input_type=int]
| For further information visit https://errors.pydantic.dev/2.10/v/dict_type
```
This issue happened because not all arguments have been appended to the
tool call buffer yet. The current code assumes that we are ready to
convert the tool call whenever args can be converted to JSON
successfully. In this case, `json.loads("202")` would succeed but the
rest of the arguments have not been properly parsed yet.
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
The e2e example worked successfully (although note that I ran the script
twice with each function call separately due to
https://github.com/meta-llama/llama-stack/issues/1120):
```
tool_execution> Tool:get_ticker_data Args:{'ticker_symbol': 'GOOG', 'start': '2023-01-01', 'end': '2023-12-31'}
tool_execution> Tool:get_ticker_data Response:"[{\"('Year', '')\":2023,\"('Close', 'GOOG')\":140.4254455566}]"
tool_execution> Tool:web_search Args:{'query': '42nd president of the United States'}
tool_execution> Tool:web_search Response:"{\"query\": \"42nd president of the United States\", \"top_k\": [{\"title\": \"William J. Clinton | whitehouse.gov\", \"url\": \"https://obamawhitehouse.archives.gov/1600/presidents/williamjclinton\", \"description\": \"<strong>Bill Clinton</strong> is an American politician from Arkansas who served as the 42nd President of the United States (1993-2001). He took office at the end of the Cold War, and was the first baby-boomer generation President.\", \"type\": \"search_result\"}, {\"title\": \"Bill Clinton - Wikipedia\", \"url\": \"https://en.wikipedia.org/wiki/Bill_Clinton\", \"description\": \"<strong>William Jefferson Clinton</strong> (n\\u00e9 Blythe; born August 19, 1946) is an American politician and lawyer who served as the 42nd president of the United States from 1993 to 2001. A member of the Democratic Party, he previously served as the attorney general of Arkansas from 1977 to 1979 and as the ...\", \"type\": \"search_result\"}, [{\"type\": \"video_result\", \"url\": \"https://www.youtube.com/watch?v=eR2z_1-v87Y\", \"title\": \"A Conversation with Bill Clinton, 42nd President of the United ...\", \"description\": \"William Jefferson Clinton, the first Democratic president in six decades to be elected twice, led the United States to the longest economic expansion in Amer...\"}, {\"type\": \"video_result\", \"url\": \"4484174096/\", \"title\": \"January 20, 1993, President Clinton was sworn in as the 42nd ...\", \"description\": \"WATCH: On January 20, 1993, President Bill Clinton was sworn in as the 42nd President of the United States. #InaugurationDay Video courtesy of the...\"}, {\"type\": \"video_result\", \"url\": \"https://www.youtube.com/watch?v=vI0HGQqEJh0\", \"title\": \"42nd President of the United States, Bill Clinton, shared thoughts ...\", \"description\": \"AboutPressCopyrightContact usCreatorsAdvertiseDevelopersTermsPrivacyPolicy & SafetyHow YouTube worksTest new features \\u00b7 \\u00a9 2024 Google LLC\"}, {\"type\": \"video_result\", \"url\": \"https://www.youtube.com/shorts/vI0HGQqEJh0\", \"title\": \"42nd President of the United States, Bill Clinton, shared ...\", \"description\": \"Enjoy the videos and music you love, upload original content, and share it all with friends, family, and the world on YouTube.\"}, {\"type\": \"video_result\", \"url\": \"https://www.youtube.com/watch?v=PHihhihVth0\", \"title\": \"Bill & Hillary Clinton returning to Little Rock for 20th ...\", \"description\": \"Enjoy the videos and music you love, upload original content, and share it all with friends, family, and the world on YouTube.\"}]]}"
```
All text inference tests passed.
[//]: # (## Documentation)
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
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?
- Remove hardcoded configurations from pre-commit.
- Allow configuration to be set via pyproject.toml.
- Merge .ruff.toml settings into pyproject.toml.
- Ensure the linter and formatter use the defined configuration instead
of being overridden by pre-commit.
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)
Signed-off-by: Sébastien Han <seb@redhat.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?
[Provide a short summary of what this PR does and why. Link to relevant
issues if applicable.]
Closes https://github.com/meta-llama/llama-stack/issues/1046.
## 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.*]
```
LLAMA_STACK_BASE_URL=http://localhost:5002 pytest -v tests/client-sdk/inference/test_text_inference.py
================================================================= test session starts =================================================================
platform linux -- Python 3.10.16, pytest-8.3.4, pluggy-1.5.0 -- /home/yutang/.conda/envs/distribution-myenv/bin/python3.10
cachedir: .pytest_cache
rootdir: /home/yutang/repos/llama-stack
configfile: pyproject.toml
plugins: anyio-4.8.0
collected 14 items
tests/client-sdk/inference/test_text_inference.py::test_text_completion_non_streaming[meta-llama/Llama-3.1-8B-Instruct] PASSED [ 7%]
tests/client-sdk/inference/test_text_inference.py::test_text_completion_streaming[meta-llama/Llama-3.1-8B-Instruct] PASSED [ 14%]
tests/client-sdk/inference/test_text_inference.py::test_completion_log_probs_non_streaming[meta-llama/Llama-3.1-8B-Instruct] XFAIL (remote:...) [ 21%]
tests/client-sdk/inference/test_text_inference.py::test_completion_log_probs_streaming[meta-llama/Llama-3.1-8B-Instruct] XFAIL (remote::vll...) [ 28%]
tests/client-sdk/inference/test_text_inference.py::test_text_completion_structured_output[meta-llama/Llama-3.1-8B-Instruct] PASSED [ 35%]
tests/client-sdk/inference/test_text_inference.py::test_text_chat_completion_non_streaming[meta-llama/Llama-3.1-8B-Instruct-Which planet do humans live on?-Earth] PASSED [ 42%]
tests/client-sdk/inference/test_text_inference.py::test_text_chat_completion_non_streaming[meta-llama/Llama-3.1-8B-Instruct-Which planet has rings around it with a name starting with letter S?-Saturn] PASSED [ 50%]
tests/client-sdk/inference/test_text_inference.py::test_text_chat_completion_streaming[meta-llama/Llama-3.1-8B-Instruct-What's the name of the Sun in latin?-Sol] PASSED [ 57%]
tests/client-sdk/inference/test_text_inference.py::test_text_chat_completion_streaming[meta-llama/Llama-3.1-8B-Instruct-What is the name of the US captial?-Washington] PASSED [ 64%]
tests/client-sdk/inference/test_text_inference.py::test_text_chat_completion_with_tool_calling_and_non_streaming[meta-llama/Llama-3.1-8B-Instruct] PASSED [ 71%]
tests/client-sdk/inference/test_text_inference.py::test_text_chat_completion_with_tool_calling_and_streaming[meta-llama/Llama-3.1-8B-Instruct] PASSED [ 78%]
tests/client-sdk/inference/test_text_inference.py::test_text_chat_completion_structured_output[meta-llama/Llama-3.1-8B-Instruct] PASSED [ 85%]
tests/client-sdk/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[meta-llama/Llama-3.1-8B-Instruct-True] PASSED [ 92%]
tests/client-sdk/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[meta-llama/Llama-3.1-8B-Instruct-False] PASSED [100%]
=============================================== 12 passed, 2 xfailed, 1 warning in 366.56s (0:06:06) ================================================
```
---------
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
# What does this PR do?
This PR adds support for tool calling for non-streaming chat completion.
Prior to this, tool calls were not passed to chat completion requests
and the tools object needs to be restructured properly to be compatible
with vLLM provider.
## Test Plan
```
LLAMA_STACK_BASE_URL=http://localhost:5002 pytest -v tests/client-sdk/inference/test_text_inference.py
================================================================= test session starts =================================================================
platform linux -- Python 3.10.16, pytest-8.3.4, pluggy-1.5.0 -- /home/yutang/.conda/envs/distribution-myenv/bin/python3.10
cachedir: .pytest_cache
rootdir: /home/yutang/repos/llama-stack
configfile: pyproject.toml
plugins: anyio-4.8.0
collected 12 items
tests/client-sdk/inference/test_text_inference.py::test_text_completion_non_streaming[meta-llama/Llama-3.1-8B-Instruct] PASSED [ 8%]
tests/client-sdk/inference/test_text_inference.py::test_text_completion_streaming[meta-llama/Llama-3.1-8B-Instruct] PASSED [ 16%]
tests/client-sdk/inference/test_text_inference.py::test_completion_log_probs_non_streaming[meta-llama/Llama-3.1-8B-Instruct] XFAIL (remote:...) [ 25%]
tests/client-sdk/inference/test_text_inference.py::test_completion_log_probs_streaming[meta-llama/Llama-3.1-8B-Instruct] XFAIL (remote::vll...) [ 33%]
tests/client-sdk/inference/test_text_inference.py::test_text_completion_structured_output[meta-llama/Llama-3.1-8B-Instruct] PASSED [ 41%]
tests/client-sdk/inference/test_text_inference.py::test_text_chat_completion_non_streaming[meta-llama/Llama-3.1-8B-Instruct-Which planet do humans live on?-Earth] PASSED [ 50%]
tests/client-sdk/inference/test_text_inference.py::test_text_chat_completion_non_streaming[meta-llama/Llama-3.1-8B-Instruct-Which planet has rings around it with a name starting with letter S?-Saturn] PASSED [ 58%]
tests/client-sdk/inference/test_text_inference.py::test_text_chat_completion_streaming[meta-llama/Llama-3.1-8B-Instruct-What's the name of the Sun in latin?-Sol] PASSED [ 66%]
tests/client-sdk/inference/test_text_inference.py::test_text_chat_completion_streaming[meta-llama/Llama-3.1-8B-Instruct-What is the name of the US captial?-Washington] PASSED [ 75%]
tests/client-sdk/inference/test_text_inference.py::test_text_chat_completion_with_tool_calling_and_non_streaming[meta-llama/Llama-3.1-8B-Instruct] PASSED [ 83%]
tests/client-sdk/inference/test_text_inference.py::test_text_chat_completion_with_tool_calling_and_streaming[meta-llama/Llama-3.1-8B-Instruct] FAILED [ 91%]
tests/client-sdk/inference/test_text_inference.py::test_text_chat_completion_structured_output[meta-llama/Llama-3.1-8B-Instruct] PASSED [100%]
```
---------
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
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>
# What does this PR do?
1) As per @mattf's suggestion, we want to mark the pytest as xfail for
providers that do not support the functionality. In this diff, we xfail
the logProbs inference tests for providers who does not support log
probs.
( log probs is only supported by together, fireworks and vllm)
2) Added logProbs support for together according to their developer
[doc](https://docs.together.ai/docs/logprobs).
## Test Plan
1) Together & Fireworks
```
export LLAMA_STACK_CONFIG=/Users/sxyi/llama-stack/llama_stack/templates/together/run.yaml
/opt/miniconda3/envs/stack/bin/pytest -s -v /Users/sxyi/llama-stack/tests/client-sdk/inference/test_inference.py
```
```
tests/client-sdk/inference/test_inference.py::test_text_completion_streaming[meta-llama/Llama-3.1-8B-Instruct] PASSED
tests/client-sdk/inference/test_inference.py::test_completion_log_probs_non_streaming[meta-llama/Llama-3.1-8B-Instruct] PASSED
tests/client-sdk/inference/test_inference.py::test_completion_log_probs_streaming[meta-llama/Llama-3.1-8B-Instruct] PASSED
tests/client-sdk/inference/test_inference.py::test_text_completion_structured_output[meta-llama/Llama-3.1-8B-Instruct] PASSED
tests/client-sdk/inference/test_inference.py::test_text_chat_completion_non_streaming[meta-llama/Llama-3.1-8B-Instruct-What are the names of planets in our solar system?-Earth] PASSED
tests/client-sdk/inference/test_inference.py::test_text_chat_completion_non_streaming[meta-llama/Llama-3.1-8B-Instruct-What are the names of the planets that have rings around them?-Saturn] PASSED
tests/client-sdk/inference/test_inference.py::test_text_chat_completion_streaming[meta-llama/Llama-3.1-8B-Instruct-What's the name of the Sun in latin?-Sol] PASSED
tests/client-sdk/inference/test_inference.py::test_text_chat_completion_streaming[meta-llama/Llama-3.1-8B-Instruct-What is the name of the US captial?-Washington] PASSED
tests/client-sdk/inference/test_inference.py::test_text_chat_completion_with_tool_calling_and_non_streaming[meta-llama/Llama-3.1-8B-Instruct] PASSED
tests/client-sdk/inference/test_inference.py::test_text_chat_completion_with_tool_calling_and_streaming[meta-llama/Llama-3.1-8B-Instruct] PASSED
tests/client-sdk/inference/test_inference.py::test_text_chat_completion_structured_output[meta-llama/Llama-3.1-8B-Instruct] PASSED
tests/client-sdk/inference/test_inference.py::test_image_chat_completion_non_streaming[meta-llama/Llama-3.2-11B-Vision-Instruct] PASSED
tests/client-sdk/inference/test_inference.py::test_image_chat_completion_streaming[meta-llama/Llama-3.2-11B-Vision-Instruct] PASSED
tests/client-sdk/inference/test_inference.py::test_image_chat_completion_base64_url[meta-llama/Llama-3.2-11B-Vision-Instruct] PASSED
========================================================================================== 15 passed, 2 warnings in 19.46s ===========================================================================================
```
```
export LLAMA_STACK_CONFIG=/Users/sxyi/llama-stack/llama_stack/templates/fireworks/run.yaml
/opt/miniconda3/envs/stack/bin/pytest -s -v /Users/sxyi/llama-stack/tests/client-sdk/inference/test_inference.py
```
All tests passed
2) Ollama - LogProbs tests are marked as xfailed.
```
tests/client-sdk/inference/test_inference.py::test_completion_log_probs_non_streaming[meta-llama/Llama-3.1-8B-Instruct] XFAIL (remote::ollama doesn't support log probs yet)
tests/client-sdk/inference/test_inference.py::test_completion_log_probs_streaming[meta-llama/Llama-3.1-8B-Instruct] XFAIL (remote::ollama doesn't support log probs yet)
```
## 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.
Some small updates to the inference types to make them more standard
Specifically:
- image data is now located in a "image" subkey
- similarly tool call data is located in a "tool_call" subkey
The pattern followed is `dict(type="foo", foo=<...>)`
# What does this PR do?
Fixes error when running an provider using openai_compat.py
```python
Traceback (most recent call last):
File "/home/ubuntu/miniconda3/envs/llamastack-vllm/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/home/ubuntu/miniconda3/envs/llamastack-vllm/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/home/ubuntu/us-south-2/llama-stack/llama_stack/distribution/server/server.py", line 426, in <module>
main()
File "/home/ubuntu/us-south-2/llama-stack/llama_stack/distribution/server/server.py", line 349, in main
impls = asyncio.run(construct_stack(config))
File "/home/ubuntu/miniconda3/envs/llamastack-vllm/lib/python3.10/asyncio/runners.py", line 44, in run
return loop.run_until_complete(main)
File "/home/ubuntu/miniconda3/envs/llamastack-vllm/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete
return future.result()
File "/home/ubuntu/us-south-2/llama-stack/llama_stack/distribution/stack.py", line 207, in construct_stack
impls = await resolve_impls(
File "/home/ubuntu/us-south-2/llama-stack/llama_stack/distribution/resolver.py", line 239, in resolve_impls
impl = await instantiate_provider(
File "/home/ubuntu/us-south-2/llama-stack/llama_stack/distribution/resolver.py", line 330, in instantiate_provider
impl = await fn(*args)
File "/home/ubuntu/us-south-2/llama-stack/llama_stack/providers/remote/inference/vllm/__init__.py", line 11, in get_adapter_impl
from .vllm import VLLMInferenceAdapter
File "/home/ubuntu/us-south-2/llama-stack/llama_stack/providers/remote/inference/vllm/vllm.py", line 39, in <module>
from llama_stack.providers.utils.inference.openai_compat import (
File "/home/ubuntu/us-south-2/llama-stack/llama_stack/providers/utils/inference/openai_compat.py", line 11, in <module>
from llama_models.llama3.api.datatypes import (
ImportError: cannot import name 'GreedySamplingStrategy' from 'llama_models.llama3.api.datatypes' (/home/ubuntu/miniconda3/envs/llamastack-vllm/lib/python3.10/site-packages/llama_models/llama3/api/datatypes.py)
++ error_handler 61
++ echo 'Error occurred in script at line: 61'
Error occurred in script at line: 61
++ exit 1
```
## Test Plan
```bash
conda create --name llamastack-vllm python=3.10
conda activate llamastack-vllm
# To sync with the current llama-models repo
pip install -e git+https://github.com/meta-llama/llama-models.git#egg=llama-models
export INFERENCE_MODEL=unsloth/Llama-3.3-70B-Instruct-bnb-4bit && \
pip install -e . && \
llama stack build --template remote-vllm --image-type conda && \
llama stack run ./distributions/remote-vllm/run.yaml \
--port 5000 \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env VLLM_URL=http://localhost:8000
```
## 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.
- [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?
- add completion log probs for fireworks
## Test Plan
<img width="849" alt="image"
src="https://github.com/user-attachments/assets/5aa1f27f-02a6-422c-8478-94dd1e345342"
/>
## Sources
Please link relevant resources if necessary.
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.
# What does this PR do?
Cleans up how we provide sampling params. Earlier, strategy was an enum
and all params (top_p, temperature, top_k) across all strategies were
grouped. We now have a strategy union object with each strategy (greedy,
top_p, top_k) having its corresponding params.
Earlier,
```
class SamplingParams:
strategy: enum ()
top_p, temperature, top_k and other params
```
However, the `strategy` field was not being used in any providers making
it confusing to know the exact sampling behavior purely based on the
params since you could pass temperature, top_p, top_k and how the
provider would interpret those would not be clear.
Hence we introduced -- a union where the strategy and relevant params
are all clubbed together to avoid this confusion.
Have updated all providers, tests, notebooks, readme and otehr places
where sampling params was being used to use the new format.
## Test Plan
`pytest llama_stack/providers/tests/inference/groq/test_groq_utils.py`
// inference on ollama, fireworks and together
`with-proxy pytest -v -s -k "ollama"
--inference-model="meta-llama/Llama-3.1-8B-Instruct"
llama_stack/providers/tests/inference/test_text_inference.py `
// agents on fireworks
`pytest -v -s -k 'fireworks and create_agent'
--inference-model="meta-llama/Llama-3.1-8B-Instruct"
llama_stack/providers/tests/agents/test_agents.py
--safety-shield="meta-llama/Llama-Guard-3-8B"`
## 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?
- [X] Updated relevant documentation.
- [X] Wrote necessary unit or integration tests.
---------
Co-authored-by: Hardik Shah <hjshah@fb.com>
## 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
```
* 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
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.
