# What does this PR do?
This PR updates the sqlite-vec database calls to be non-blocking. Note
that each operation creates a new connection, which incurs some
performance overhead but is reasonable given [SQLite's threading and
connections constraints](https://www.sqlite.org/threadsafe.html).
Summary of changes:
- Refactored `SQLiteVecIndex` class to store database path instead of
connection object
- Added `_create_sqlite_connection()` helper function to create
connections on demand
- Ensured proper connection closure in all database operations
- Fixed test fixtures to use a file-based SQLite database for
thread-safety
- Updated the `SQLiteVecVectorIOAdapter` class to handle per-operation
connections
This PR helps chip away at
https://github.com/meta-llama/llama-stack/issues/1489
## Test Plan
sqlite-vec unit tests passed locally as well as a test script using the
client as a library.
## Misc
FYI @varshaprasad96 @kevincogan
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
# What does this PR do?
**What**
Instead of adhoc creating a vectordb and chunking when documents ae sent
as an attachment to agent turn, we directly pass raw text from document
into messages to model for user context, and let model perform
summarization directly.
This removes the magic behaviour, and yields better performance than
existing approach.
**Improved Performance**
- RAG lifecycle notebook
- Model: 0.3 factuality score
- (+ websearch) Agent: 0.44 factuality score
- (+ vector db) Agent: 0.3 factuality score
- (+ raw context) Agent: 0.6 factuality score
Closes https://github.com/meta-llama/llama-stack/issues/1478
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
- [NEW] added section in RAG lifecycle notebook shows better performance
<img width="840" alt="image"
src="https://github.com/user-attachments/assets/a0c4e816-809a-41c0-9124-89825983e3f5"
/>
[//]: # (## Documentation)
# What does this PR do?
- Remove `/eval` and `/scoring` impls
- Clean up benchmarks. The benchmarks exists in the `llama-stack-evals`
repo.
- Rest of grading functions will be added in follow up PR.
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
- CI
[//]: # (## Documentation)
# What does this PR do?
1) Uses otel compatible id generation for stack
2) Stack starts returning trace id info in the header of response
3) We inject the same trace id that we have into otel in order to force
it to use our trace ids.
## Test Plan
```
curl -i --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
}'
HTTP/1.1 200 OK
date: Fri, 21 Mar 2025 21:51:19 GMT
server: uvicorn
content-length: 1712
content-type: application/json
x-trace-id: 595101ede31ece116ebe35b26d67e8cf
{"metrics":[{"metric":"prompt_tokens","value":10,"unit":null},{"metric":"completion_tokens","value":320,"unit":null},{"metric":"total_tokens","value":330,"unit":null}],"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 tropical islands, island nations, and islands in the Arctic and Antarctic regions.\n6. **Underwater habitats:** A few humans live in underwater habitats, such as research stations and submarines.\n7. **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\nIn terms of specific environments, humans live in a wide range of ecosystems, including:\n\n* Deserts\n* Forests\n* Grasslands\n* Mountains\n* Oceans\n* Rivers\n* Tundras\n* Wetlands\n\nOverall, humans are incredibly adaptable and can be found living in almost every corner of the globe.","stop_reason":"end_of_turn","tool_calls":[]},"logprobs":null}
```
Same trace id in Jaeger and sqlite:
# What does this PR do?
## Test Plan
LLAMA_STACK_CONFIG=dev pytest -s -v
tests/integration/agents/test_agents.py::test_custom_tool
--safety-shield meta-llama/Llama-Guard-3-8B --text-model
accounts/fireworks/models/llama-v3p1-8b-instruct
and verify trace in jaeger UI
https://llama-stack.readthedocs.io/en/latest/building_applications/telemetry.html#
# What does this PR do?
- We cannot directly return a literal type
> Note: this is not final jobs API change
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
<img width="837" alt="image"
src="https://github.com/user-attachments/assets/18a17561-35f9-443d-987d-54afdd6ff40c"
/>
[//]: # (## Documentation)
# What does this PR do?
Since we now start recording and exporting metrics, we no longer can use
single OTEL endpoint to export both traces and metrics. This PR adds two
sinks: OTEL_TRACE and OTEL_METRIC to be able to selectively enable the
exporters.
## Test Plan
Start server with OTEL_TRACE as sink and verify traces show up in jaeger
# What does this PR do?
Clean up mypy violations for inline::{telemetry,tool_runtime,vector_io}.
This also makes API accept a tool call result without any content (like
RAG tool already may produce).
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
In this PR, we added a new eval open benchmark IfEval based on paper
https://arxiv.org/abs/2311.07911 to measure the model capability of
instruction following.
## Test Plan
spin up a llama stack server with open-benchmark template
run `llama-stack-client --endpoint xxx eval run-benchmark
"meta-reference-ifeval" --model-id "meta-llama/Llama-3.3-70B-Instruct"
--output-dir "/home/markchen1015/" --num-examples 20` on client side and
get the eval aggregate results
# What does this PR do?
DocVQA asks model to look a a picture, then answer a question given in
text, with a text answer by text information in the picture. these
questions often require understanding of relative positions of texts
within the picture.
original dataset is defined in the "Task1" of
https://www.docvqa.org/datasets
## Test Plan
setup llama server with
```
llama stack run ./llama_stack/templates/open-benchmark/run.yaml
```
then send traffic:
```
llama-stack-client eval run-benchmark "meta-reference-docvqa" --model-id meta-llama/Llama-3.3-70B-Instruct --output-dir /tmp/gpqa --num-examples 200
```
# What does this PR do?
- To make it easier, delete existing `eval/scoring/scoring_function`
apis. There will be a bunch of broken impls here. The sequence is:
1. migrate benchmark graders
2. clean up existing scoring functions
- Add a skeleton evaluation impl to make tests pass.
## Test Plan
tested in following PRs
[//]: # (## Documentation)
These block on io reads which in turn block the
server. Move them to their own thread.
Closes: #1697
# What does this PR do?
To avoid blocking the main eventloop, updates datasetio/localfs to load
data in a seperate thread
Signed-off-by: Derek Higgins <derekh@redhat.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
```
# What does this PR do?
Fixes a bunch of violations.
Note: this patch touches all files but post_training.py that will be
significantly changed by #1437, hence leaving it out of the picture for
now.
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
Testing with https://github.com/meta-llama/llama-stack/pull/1543
Also checked that GPU training works with the change:
```
INFO: ::1:53316 - "POST /v1/post-training/supervised-fine-tune HTTP/1.1" 200 OK
INFO: ::1:53316 - "GET /v1/post-training/job/status?job_uuid=test-jobb5ca2d84-d541-42f8-883b-762828b4c0e7 HTTP/1.1" 200 OK
INFO: ::1:53316 - "GET /v1/post-training/job/artifacts?job_uuid=test-jobb5ca2d84-d541-42f8-883b-762828b4c0e7 HTTP/1.1" 200 OK
21:24:01.161 [END] /v1/post-training/supervised-fine-tune [StatusCode.OK] (32526.75ms)
21:23:28.769 [DEBUG] Setting manual seed to local seed 3918872849. Local seed is seed + rank = 3918872849 + 0
21:23:28.996 [INFO] Identified model_type = Llama3_2. Ignoring output.weight in checkpoint in favor of the tok_embedding.weight tied weights.
21:23:29.933 [INFO] Memory stats after model init:
GPU peak memory allocation: 6.05 GiB
GPU peak memory reserved: 6.10 GiB
GPU peak memory active: 6.05 GiB
21:23:29.934 [INFO] Model is initialized with precision torch.bfloat16.
21:23:30.115 [INFO] Tokenizer is initialized.
21:23:30.118 [INFO] Optimizer is initialized.
21:23:30.119 [INFO] Loss is initialized.
21:23:30.896 [INFO] Dataset and Sampler are initialized.
21:23:30.898 [INFO] Learning rate scheduler is initialized.
21:23:31.618 [INFO] Memory stats after model init:
GPU peak memory allocation: 6.24 GiB
GPU peak memory reserved: 6.30 GiB
GPU peak memory active: 6.24 GiB
21:23:31.620 [INFO] Starting checkpoint save...
21:23:59.428 [INFO] Model checkpoint of size 6.43 GB saved to /home/ec2-user/.llama/checkpoints/meta-llama/Llama-3.2-3B-Instruct-sft-0/consolidated.00.pth
21:23:59.445 [INFO] Adapter checkpoint of size 0.00 GB saved to /home/ec2-user/.llama/checkpoints/meta-llama/Llama-3.2-3B-Instruct-sft-0/adapter/adapter.pth
```
[//]: # (## Documentation)
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
Made code interpreter tool call to be async such that its non blocking
## Test Plan
pytest -s -v tests/integration/agents/test_agents.py
--stack-config=together --text-model=meta-llama/Llama-3.3-70B-Instruct
<img width="1693" alt="image"
src="https://github.com/user-attachments/assets/42520bb6-7acf-42d5-b71f-b35ca149d722"
/>
[//]: # (## Documentation)
Co-authored-by: sarthakdeshpande <sarthak.deshpande@engati.com>
# What does this PR do?
Removed local execution option from the remote Qdrant provider and
introduced an explicit inline provider for the embedded execution.
Updated the ollama template to include this option: this part can be
reverted in case we don't want to have two default `vector_io`
providers.
(Closes#1082)
## Test Plan
Build and run an ollama distro:
```bash
llama stack build --template ollama --image-type conda
llama stack run --image-type conda ollama
```
Run one of the sample ingestionapplicatinos like
[rag_with_vector_db.py](https://github.com/meta-llama/llama-stack-apps/blob/main/examples/agents/rag_with_vector_db.py),
but replace this line:
```py
selected_vector_provider = vector_providers[0]
```
with the following, to use the `qdrant` provider:
```py
selected_vector_provider = vector_providers[1]
```
After running the test code, verify the timestamp of the Qdrant store:
```bash
% ls -ltr ~/.llama/distributions/ollama/qdrant.db/collection/test_vector_db_*
total 784
-rw-r--r--@ 1 dmartino staff 401408 Feb 26 10:07 storage.sqlite
```
[//]: # (## Documentation)
---------
Signed-off-by: Daniele Martinoli <dmartino@redhat.com>
Co-authored-by: Francisco Arceo <farceo@redhat.com>
# 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
# What does this PR do?
create a new dataset BFCL_v3 from
https://gorilla.cs.berkeley.edu/blogs/13_bfcl_v3_multi_turn.html
overall each question asks the model to perform a task described in
natural language, and additionally a set of available functions and
their schema are given for the model to choose from. the model is
required to write the function call form including function name and
parameters , to achieve the stated purpose. the results are validated
against provided ground truth, to make sure that the generated function
call and the ground truth function call are syntactically and
semantically equivalent, by checking their AST .
## Test Plan
start server by
```
llama stack run ./llama_stack/templates/ollama/run.yaml
```
then send traffic
```
llama-stack-client eval run-benchmark "bfcl" --model-id meta-llama/Llama-3.2-3B-Instruct --output-dir /tmp/gpqa --num-examples 2
```
[//]: # (## Documentation)
# What does this PR do?
Updated all instances of datetime.now() to use timezone.utc for
consistency in handling time across different systems. This ensures that
timestamps are always in Coordinated Universal Time (UTC), avoiding
issues with time zone discrepancies and promoting uniformity in
time-related data.
Signed-off-by: Sébastien Han <seb@redhat.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
Summary:
1. adds option to not use bwrap for code execution
2. disable bwrap when running tests on macs
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
```
Verify code_interpreter result in logs
INFO 2025-03-11 08:10:39,858
llama_stack.providers.inline.agents.meta_reference.agent_instance:1032
agents: tool
call code_interpreter completed with result:
content='completed\n\n541\n' error_message=None error_code=None
metadata=None
Summary:
Refactoring only.
Centralize logic to preprocess toolgroup to one place.
Test Plan:
LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/api/agents/test_agents.py --safety-shield
meta-llama/Llama-Guard-3-8B
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/meta-llama/llama-stack/pull/1381).
* #1384
* __->__ #1381
# 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
Bug https://github.com/meta-llama/llama-stack/issues/1357
# What does this PR do?
Fix a bug of a wrong file name in inline::localfs datasetio provider
[//]: # (If resolving an issue, uncomment and update the line below)
# (Closes#1357)
## 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: Josh Salomon <jsalomon@redhat.com>
# What does this PR do?
- recent merge https://github.com/meta-llama/llama-stack/pull/1410
introduce error
```
ValueError: Provider meta-reference (Api.agents) does not implement the following methods:
[('list_agent_sessions', 'not_actually_implemented'), ('list_agents', 'not_actually_implemented')]
```
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
llama stack run
```
```
LLAMA_STACK_CONFIG=fireworks pytest -v tests/integration/agents/test_agents.py --text-model meta-llama/Llama-3.3-70B-Instruct
```
1379530386
[//]: # (## Documentation)
# What does this PR do?
It's a dict that may contain different types, as per
resolver:instantiate_provider implementation. (AFAIU it also never
contains ProviderSpecs, but *instances* of provider implementations.)
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
mypy passing if enabled checks for these modules. (See #1543)
[//]: # (## Documentation)
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
Added missing shutdown handler. (Currently empty.)
Without it, when server shuts down, it posts the following warning:
```
__main__:129 server: No shutdown method for TorchtunePostTrainingImpl
```
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
(The test plan assumes shutdown logic is fixed, see #1495)
Without the patch:
```
INFO: Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit)
INFO: Shutting down
INFO: Waiting for application shutdown.
INFO 2025-03-10 20:56:43,961 __main__:140 server: Shutting down
INFO 2025-03-10 20:56:43,962 __main__:124 server: Shutting down DatasetsRoutingTable
INFO 2025-03-10 20:56:43,964 __main__:124 server: Shutting down DatasetIORouter
INFO 2025-03-10 20:56:43,965 __main__:124 server: Shutting down ScoringFunctionsRoutingTable
INFO 2025-03-10 20:56:43,966 __main__:124 server: Shutting down ScoringRouter
INFO 2025-03-10 20:56:43,967 __main__:124 server: Shutting down ModelsRoutingTable
INFO 2025-03-10 20:56:43,968 __main__:124 server: Shutting down InferenceRouter
INFO 2025-03-10 20:56:43,969 __main__:124 server: Shutting down ShieldsRoutingTable
INFO 2025-03-10 20:56:43,971 __main__:124 server: Shutting down SafetyRouter
INFO 2025-03-10 20:56:43,972 __main__:124 server: Shutting down VectorDBsRoutingTable
INFO 2025-03-10 20:56:43,973 __main__:124 server: Shutting down VectorIORouter
INFO 2025-03-10 20:56:43,974 __main__:124 server: Shutting down ToolGroupsRoutingTable
INFO 2025-03-10 20:56:43,975 __main__:124 server: Shutting down ToolRuntimeRouter
INFO 2025-03-10 20:56:43,976 __main__:124 server: Shutting down MetaReferenceAgentsImpl
INFO 2025-03-10 20:56:43,977 __main__:124 server: Shutting down TelemetryAdapter
INFO 2025-03-10 20:56:43,978 __main__:124 server: Shutting down TorchtunePostTrainingImpl
WARNING 2025-03-10 20:56:43,979 __main__:129 server: No shutdown method for TorchtunePostTrainingImpl
INFO 2025-03-10 20:56:43,979 __main__:124 server: Shutting down BenchmarksRoutingTable
INFO 2025-03-10 20:56:43,980 __main__:124 server: Shutting down EvalRouter
INFO 2025-03-10 20:56:43,981 __main__:124 server: Shutting down DistributionInspectImpl
INFO: Application shutdown complete.
INFO: Finished server process [33862]
```
Run with the patch and observe no warning:
```
$ kill -INT $(ps ax | grep llama_stack.distribution.server.server | grep -v nvim | awk -e '{print $1}' | sort | head -n 1)
```
```
INFO: Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit)
INFO: Shutting down
INFO: Waiting for application shutdown.
INFO 2025-03-11 00:32:56,863 __main__:140 server: Shutting down
INFO 2025-03-11 00:32:56,864 __main__:124 server: Shutting down DatasetsRoutingTable
INFO 2025-03-11 00:32:56,866 __main__:124 server: Shutting down DatasetIORouter
INFO 2025-03-11 00:32:56,867 __main__:124 server: Shutting down ScoringFunctionsRoutingTable
INFO 2025-03-11 00:32:56,868 __main__:124 server: Shutting down ScoringRouter
INFO 2025-03-11 00:32:56,869 __main__:124 server: Shutting down ModelsRoutingTable
INFO 2025-03-11 00:32:56,870 __main__:124 server: Shutting down InferenceRouter
INFO 2025-03-11 00:32:56,871 __main__:124 server: Shutting down ShieldsRoutingTable
INFO 2025-03-11 00:32:56,872 __main__:124 server: Shutting down SafetyRouter
INFO 2025-03-11 00:32:56,873 __main__:124 server: Shutting down VectorDBsRoutingTable
INFO 2025-03-11 00:32:56,874 __main__:124 server: Shutting down VectorIORouter
INFO 2025-03-11 00:32:56,875 __main__:124 server: Shutting down ToolGroupsRoutingTable
INFO 2025-03-11 00:32:56,876 __main__:124 server: Shutting down ToolRuntimeRouter
INFO 2025-03-11 00:32:56,877 __main__:124 server: Shutting down MetaReferenceAgentsImpl
INFO 2025-03-11 00:32:56,878 __main__:124 server: Shutting down TelemetryAdapter
INFO 2025-03-11 00:32:56,879 __main__:124 server: Shutting down TorchtunePostTrainingImpl
INFO 2025-03-11 00:32:56,880 __main__:124 server: Shutting down BenchmarksRoutingTable
INFO 2025-03-11 00:32:56,881 __main__:124 server: Shutting down EvalRouter
INFO 2025-03-11 00:32:56,882 __main__:124 server: Shutting down DistributionInspectImpl
```
[//]: # (## Documentation)
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
This PR has two fixes needed for correct trace context propagation
across asycnio boundary
Fix 1: Start using context vars to store the global trace context.
This is needed since we cannot use the same trace context across
coroutines since the state is shared. each coroutine
should have its own trace context so that each of it can start storing
its state correctly.
Fix 2: Start a new span for each new coroutines started for running
shields to keep the span tree clean
## Test Plan
### Integration tests with server
LLAMA_STACK_DISABLE_VERSION_CHECK=true llama stack run
~/.llama/distributions/together/together-run.yaml
LLAMA_STACK_CONFIG=http://localhost:8321 pytest -s --safety-shield
meta-llama/Llama-Guard-3-8B --text-model
meta-llama/Llama-3.1-8B-Instruct
server logs:
https://gist.github.com/dineshyv/51ac5d9864ed031d0d89ce77352821fe
test logs:
https://gist.github.com/dineshyv/e66acc1c4648a42f1854600609c467f3
### Integration tests with library client
LLAMA_STACK_CONFIG=fireworks pytest -s --safety-shield
meta-llama/Llama-Guard-3-8B --text-model
meta-llama/Llama-3.1-8B-Instruct
logs: https://gist.github.com/dineshyv/ca160696a0b167223378673fb1dcefb8
### Apps test with server:
```
LLAMA_STACK_DISABLE_VERSION_CHECK=true llama stack run ~/.llama/distributions/together/together-run.yaml
python -m examples.agents.e2e_loop_with_client_tools localhost 8321
```
server logs:
https://gist.github.com/dineshyv/1717a572d8f7c14279c36123b79c5797
app logs:
https://gist.github.com/dineshyv/44167e9f57806a0ba3b710c32aec02f8
## What does this PR do?
Created a new math_500 open-benchmark based on OpenAI's [Let's Verify
Step by Step](https://arxiv.org/abs/2305.20050) paper and hugging face's
[HuggingFaceH4/MATH-500](https://huggingface.co/datasets/HuggingFaceH4/MATH-500)
dataset.
The challenge part of this benchmark is to parse the generated and
expected answer and verify if they are same. For the parsing part, we
refer to [Minerva: Solving Quantitative Reasoning Problems with Language
Models](https://research.google/blog/minerva-solving-quantitative-reasoning-problems-with-language-models/).
To simply the parse logic, as the next step, we plan to also refer to
what [simple-eval](https://github.com/openai/simple-evals) is doing,
using llm as judge to check if the generated answer matches the expected
answer or not
## Test Plan
on sever side, spin up a server with open-benchmark template `llama
stack run llama_stack/templates/open-benchamrk/run.yaml`
on client side, issue an open benchmark eval request `llama-stack-client
--endpoint xxx eval run-benchmark "meta-reference-math-500" --model-id
"meta-llama/Llama-3.3-70B-Instruct" --output-dir "/home/markchen1015/"
--num-examples 20` and get ther aggregated eval results
<img width="238" alt="Screenshot 2025-03-10 at 7 57 04 PM"
src="https://github.com/user-attachments/assets/2c9da042-3b70-470e-a7c4-69f4cc24d1fb"
/>
check the generated answer and the related scoring and they make sense
# What does this PR do?
This PR converts blocking calls for in built tools like wolfram, brave,
tavily and bing into non blocking async calls
[//]: # (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.*]
pytest -s -v tool_runtime/test_builtin_tools.py --stack-config=together
--text-model=meta-llama/Llama-3.1-8B-Instruct
Used the command above to get the below results
<img width="1710" alt="image"
src="https://github.com/user-attachments/assets/76b0ca06-f6e4-45fa-a114-0449bef2325b"
/>
<img width="1389" alt="image"
src="https://github.com/user-attachments/assets/5220ccbb-7882-4240-b17e-f362ad46d25b"
/>
<img width="1432" alt="image"
src="https://github.com/user-attachments/assets/bb93a41e-e82a-4c98-a22d-6b0e320aa974"
/>
[//]: # (## Documentation)
---------
Co-authored-by: sarthakdeshpande <sarthak.deshpande@engati.com>
Summary:
| File
"/Users/erichuang/projects/llama-stack/llama_stack/distribution/server/server.py",
line 213, in sse_generator
| logger.exception(f"Error in sse_generator: {e}")
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1864, in exception
| self.log(ERROR, msg, *args, exc_info=exc_info, **kwargs)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1879, in log
| self.logger.log(level, msg, *args, **kwargs)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1547, in log
| self._log(level, msg, args, **kwargs)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1624, in _log
| self.handle(record)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1634, in handle
| self.callHandlers(record)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1696, in callHandlers
| hdlr.handle(record)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 968, in handle
| self.emit(record)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/logging.py",
line 167, in emit
| message_renderable = self.render_message(record, message)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/logging.py",
line 193, in render_message
| message_text = Text.from_markup(message) if use_markup else
Text(message)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/text.py",
line 287, in from_markup
| rendered_text = render(text, style, emoji=emoji,
emoji_variant=emoji_variant)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/markup.py",
line 167, in render
| raise MarkupError(
| rich.errors.MarkupError: closing tag '[/INST]' at position 105 doesn't
match any open tag
Test Plan:
reran failing rag_with_vector_db example
# What does this PR do?
This PR updates the inline vLLM inference provider in several
significant ways:
* Models are now attached at run time to instances of the provider via
the `.../models` API instead of hard-coding the model's full name into
the provider's YAML configuration.
* The provider supports models that are not Meta Llama models. Any model
that vLLM supports can be loaded by passing Huggingface coordinates in
the "provider_model_id" field. Custom fine-tuned versions of Meta Llama
models can be loaded by specifying a path on local disk in the
"provider_model_id".
* To implement full chat completions support, including tool calling and
constrained decoding, the provider now routes the `chat_completions` API
to a captive (i.e. called directly in-process, not via HTTPS) instance
of vLLM's OpenAI-compatible server .
* The `logprobs` parameter and completions API are also working.
## Test Plan
Existing tests in
`llama_stack/providers/tests/inference/test_text_inference.py` have good
coverage of the new functionality. These tests can be invoked as
follows:
```
cd llama-stack && pytest \
-vvv \
llama_stack/providers/tests/inference/test_text_inference.py \
--providers inference=vllm \
--inference-model meta-llama/Llama-3.2-3B-Instruct
====================================== test session starts ======================================
platform linux -- Python 3.12.8, pytest-8.3.4, pluggy-1.5.0 -- /mnt/datadisk1/freiss/llama/env/bin/python3.12
cachedir: .pytest_cache
metadata: {'Python': '3.12.8', 'Platform': 'Linux-6.8.0-1016-ibm-x86_64-with-glibc2.39', 'Packages': {'pytest': '8.3.4', 'pluggy': '1.5.0'}, 'Plugins': {'anyio': '4.8.0', 'html': '4.1.1', 'metadata': '3.1.1', 'asyncio': '0.25.2'}, 'JAVA_HOME': '/usr/lib/jvm/java-8-openjdk-amd64'}
rootdir: /mnt/datadisk1/freiss/llama/llama-stack
configfile: pyproject.toml
plugins: anyio-4.8.0, html-4.1.1, metadata-3.1.1, asyncio-0.25.2
asyncio: mode=Mode.STRICT, asyncio_default_fixture_loop_scope=None
collected 9 items
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_model_list[-vllm] PASSED [ 11%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion[-vllm] PASSED [ 22%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_logprobs[-vllm] PASSED [ 33%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_structured_output[-vllm] PASSED [ 44%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_non_streaming[-vllm] PASSED [ 55%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_structured_output[-vllm] PASSED [ 66%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_streaming[-vllm] PASSED [ 77%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling[-vllm] PASSED [ 88%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling_streaming[-vllm] PASSED [100%]
=========================== 9 passed, 13 warnings in 97.18s (0:01:37) ===========================
```
## Sources
## 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?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.
---------
Co-authored-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
Summary:
error:
llama_stack/providers/inline/agents/meta_reference/agent_instance.py:1032:
in execute_tool_call_maybe
logger.info(f"tool call {name} completed with result: {result}")
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py:1841:
in info
self.log(INFO, msg, *args, **kwargs)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py:1879:
in log
self.logger.log(level, msg, *args, **kwargs)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py:1547:
in log
self._log(level, msg, args, **kwargs)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py:1624:
in _log
self.handle(record)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py:1634:
in handle
self.callHandlers(record)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py:1696:
in callHandlers
hdlr.handle(record)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py:968:
in handle
self.emit(record)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/logging.py:167:
in emit
message_renderable = self.render_message(record, message)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/logging.py:193:
in render_message
message_text = Text.from_markup(message) if use_markup else
Text(message)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/text.py:287:
in from_markup
rendered_text = render(text, style, emoji=emoji,
emoji_variant=emoji_variant)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/markup.py:167:
in render
raise MarkupError(
E rich.errors.MarkupError: closing tag '[/INST]' at position 3274
doesn't match any open tag
Test Plan:
# What does this PR do?
This commit introduces a new logging system that allows loggers to be
assigned
a category while retaining the logger name based on the file name. The
log
format includes both the logger name and the category, producing output
like:
```
INFO 2025-03-03 21:44:11,323 llama_stack.distribution.stack:103 [core]: Tool_groups: builtin::websearch served by
tavily-search
```
Key features include:
- Category-based logging: Loggers can be assigned a category (e.g.,
"core", "server") when programming. The logger can be loaded like
this: `logger = get_logger(name=__name__, category="server")`
- Environment variable control: Log levels can be configured
per-category using the
`LLAMA_STACK_LOGGING` environment variable. For example:
`LLAMA_STACK_LOGGING="server=DEBUG;core=debug"` enables DEBUG level for
the "server"
and "core" categories.
- `LLAMA_STACK_LOGGING="all=debug"` sets DEBUG level globally for all
categories and
third-party libraries.
This provides fine-grained control over logging levels while maintaining
a clean and
informative log format.
The formatter uses the rich library which provides nice colors better
stack traces like so:
```
ERROR 2025-03-03 21:49:37,124 asyncio:1758 [uncategorized]: unhandled exception during asyncio.run() shutdown
task: <Task finished name='Task-16' coro=<handle_signal.<locals>.shutdown() done, defined at
/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py:146>
exception=UnboundLocalError("local variable 'loop' referenced before assignment")>
╭────────────────────────────────────── Traceback (most recent call last) ───────────────────────────────────────╮
│ /Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py:178 in shutdown │
│ │
│ 175 │ │ except asyncio.CancelledError: │
│ 176 │ │ │ pass │
│ 177 │ │ finally: │
│ ❱ 178 │ │ │ loop.stop() │
│ 179 │ │
│ 180 │ loop = asyncio.get_running_loop() │
│ 181 │ loop.create_task(shutdown()) │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
UnboundLocalError: local variable 'loop' referenced before assignment
```
Co-authored-by: Ashwin Bharambe <@ashwinb>
Signed-off-by: Sébastien Han <seb@redhat.com>
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
python -m llama_stack.distribution.server.server --yaml-config ./llama_stack/templates/ollama/run.yaml
INFO 2025-03-03 21:55:35,918 __main__:365 [server]: Using config file: llama_stack/templates/ollama/run.yaml
INFO 2025-03-03 21:55:35,925 __main__:378 [server]: Run configuration:
INFO 2025-03-03 21:55:35,928 __main__:380 [server]: apis:
- agents
```
[//]: # (## Documentation)
---------
Signed-off-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
# What does this PR do?
See https://github.com/meta-llama/llama-stack/pull/1171 which is the
original PR. Author: @zc277584121
feat: add [Milvus](https://milvus.io/) vectorDB
note: I use the MilvusClient to implement it instead of
AsyncMilvusClient, because when I tested AsyncMilvusClient, it would
raise issues about evenloop, which I think AsyncMilvusClient SDK is not
robust enough to be compatible with llama_stack framework.
## Test Plan
have passed the unit test and ene2end test
Here is my end2end test logs, including the client code, client log,
server logs from inline and remote settings
[test_end2end_logs.zip](https://github.com/user-attachments/files/18964391/test_end2end_logs.zip)
---------
Signed-off-by: ChengZi <chen.zhang@zilliz.com>
Co-authored-by: Cheney Zhang <chen.zhang@zilliz.com>
