forked from phoenix-oss/llama-stack-mirror
2 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Ashwin Bharambe
|
8de8eb03c8
|
Update the "InterleavedTextMedia" type (#635)
## 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
```
|
||
Henry Tu
|
64c6df8392
|
Cerebras Inference Integration (#265)
Adding Cerebras Inference as an API provider. ## Testing ### Conda ``` $ llama stack build --template cerebras --image-type conda $ llama stack run ~/.llama/distributions/llamastack-cerebras/cerebras-run.yaml ... Listening on ['::', '0.0.0.0']:5000 INFO: Started server process [12443] INFO: Waiting for application startup. INFO: Application startup complete. INFO: Uvicorn running on http://['::', '0.0.0.0']:5000 (Press CTRL+C to quit) ``` ### Chat Completion ``` $ curl --location 'http://localhost:5000/alpha/inference/chat-completion' --header 'Content-Type: application/json' --data '{ "model_id": "meta-llama/Llama-3.1-8B-Instruct", "messages": [ { "role": "user", "content": "What is the temperature in Seattle right now?" } ], "stream": false, "sampling_params": { "strategy": "top_p", "temperature": 0.5, "max_tokens": 100 }, "tool_choice": "auto", "tool_prompt_format": "json", "tools": [ { "tool_name": "getTemperature", "description": "Gets the current temperature of a location.", "parameters": { "location": { "param_type": "string", "description": "The name of the place to get the temperature from in degress celsius.", "required": true } } } ] }' ``` #### Non-Streaming Response ``` { "completion_message": { "role": "assistant", "content": "", "stop_reason": "end_of_message", "tool_calls": [ { "call_id": "6f42fdcc-6cbb-46ad-a17b-5d20ac64b678", "tool_name": "getTemperature", "arguments": { "location": "Seattle" } } ] }, "logprobs": null } ``` #### Streaming Response ``` data: {"event":{"event_type":"start","delta":"","logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"","parse_status":"started"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"{\"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"type","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"\":","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"function","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"\",","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"name","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"\":","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"get","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"Temperature","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"\",","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"parameters","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"\":","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":" {\"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"location","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"\":","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"Seattle","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":"\"}}","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}} data: {"event":{"event_type":"progress","delta":{"content":{"call_id":"e742df1f-0ae9-40ad-a49e-18e5c905484f","tool_name":"getTemperature","arguments":{"location":"Seattle"}},"parse_status":"success"},"logprobs":null,"stop_reason":"end_of_message"}} data: {"event":{"event_type":"complete","delta":"","logprobs":null,"stop_reason":"end_of_message"}} ``` ### Completion ``` $ curl --location 'http://localhost:5000/alpha/inference/completion' --header 'Content-Type: application/json' --data '{ "model_id": "meta-llama/Llama-3.1-8B-Instruct", "content": "1,2,3,", "stream": true, "sampling_params": { "strategy": "top_p", "temperature": 0.5, "max_tokens": 10 }, "tool_choice": "auto", "tool_prompt_format": "json", "tools": [ { "tool_name": "getTemperature", "description": "Gets the current temperature of a location.", "parameters": { "location": { "param_type": "string", "description": "The name of the place to get the temperature from in degress celsius.", "required": true } } } ] }' ``` #### Non-Streaming Response ``` { "content": "4,5,6,7,8,", "stop_reason": "out_of_tokens", "logprobs": null } ``` #### Streaming Response ``` data: {"delta":"4","stop_reason":null,"logprobs":null} data: {"delta":",","stop_reason":null,"logprobs":null} data: {"delta":"5","stop_reason":null,"logprobs":null} data: {"delta":",","stop_reason":null,"logprobs":null} data: {"delta":"6","stop_reason":null,"logprobs":null} data: {"delta":",","stop_reason":null,"logprobs":null} data: {"delta":"7","stop_reason":null,"logprobs":null} data: {"delta":",","stop_reason":null,"logprobs":null} data: {"delta":"8","stop_reason":null,"logprobs":null} data: {"delta":",","stop_reason":null,"logprobs":null} data: {"delta":"","stop_reason":null,"logprobs":null} data: {"delta":"","stop_reason":"out_of_tokens","logprobs":null} ``` ### Pre-Commit Checks ``` trim trailing whitespace.................................................Passed check python ast.........................................................Passed check for merge conflicts................................................Passed check for added large files..............................................Passed fix end of files.........................................................Passed Insert license in comments...............................................Passed flake8...................................................................Passed Format files with µfmt...................................................Passed ``` ### Testing with `test_inference.py` ``` $ export CEREBRAS_API_KEY=<insert API key here> $ pytest -v -s llama_stack/providers/tests/inference/test_text_inference.py -m "cerebras and llama_8b" /net/henryt-dev/srv/nfs/henryt-data/ws/llama-stack/.venv/lib/python3.12/site-packages/pytest_asyncio/plugin.py:208: PytestDeprecationWarning: The configuration option "asyncio_default_fixture_loop_scope" is unset. The event loop scope for asynchronous fixtures will default to the fixture caching scope. Future versions of pytest-asyncio will default the loop scope for asynchronous fixtures to function scope. Set the default fixture loop scope explicitly in order to avoid unexpected behavior in the future. Valid fixture loop scopes are: "function", "class", "module", "package", "session" warnings.warn(PytestDeprecationWarning(_DEFAULT_FIXTURE_LOOP_SCOPE_UNSET)) =================================================== test session starts =================================================== platform linux -- Python 3.12.3, pytest-8.3.3, pluggy-1.5.0 -- /net/henryt-dev/srv/nfs/henryt-data/ws/llama-stack/.venv/bin/python3.12 cachedir: .pytest_cache rootdir: /net/henryt-dev/srv/nfs/henryt-data/ws/llama-stack configfile: pyproject.toml plugins: anyio-4.6.2.post1, asyncio-0.24.0 asyncio: mode=Mode.STRICT, default_loop_scope=None collected 128 items / 120 deselected / 8 selected llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_model_list[llama_8b-cerebras] Resolved 4 providers inner-inference => cerebras models => __routing_table__ inference => __autorouted__ inspect => __builtin__ Models: meta-llama/Llama-3.1-8B-Instruct served by cerebras PASSED llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion[llama_8b-cerebras] PASSED llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completions_structured_output[llama_8b-cerebras] SKIPPED llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_non_streaming[llama_8b-cerebras] PASSED llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_structured_output[llama_8b-cerebras] SKIPPED llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_streaming[llama_8b-cerebras] PASSED llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling[llama_8b-cerebras] PASSED llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling_streaming[llama_8b-cerebras] PASSED ================================ 6 passed, 2 skipped, 120 deselected, 6 warnings in 3.95s ================================= ``` I ran `python llama_stack/scripts/distro_codegen.py` to run codegen. |