# What does this PR do?
This commit significantly improves the environment variable substitution
functionality in Llama Stack configuration files:
* The version field in configuration files has been changed from string
to integer type for better type consistency across build and run
configurations.
* The environment variable substitution system for ${env.FOO:} was fixed
and properly returns an error
* The environment variable substitution system for ${env.FOO+} returns
None instead of an empty strings, it better matches type annotations in
config fields
* The system includes automatic type conversion for boolean, integer,
and float values.
* The error messages have been enhanced to provide clearer guidance when
environment variables are missing, including suggestions for using
default values or conditional syntax.
* Comprehensive documentation has been added to the configuration guide
explaining all supported syntax patterns, best practices, and runtime
override capabilities.
* Multiple provider configurations have been updated to use the new
conditional syntax for optional API keys, making the system more
flexible for different deployment scenarios. The telemetry configuration
has been improved to properly handle optional endpoints with appropriate
validation, ensuring that required endpoints are specified when their
corresponding sinks are enabled.
* There were many instances of ${env.NVIDIA_API_KEY:} that should have
caused the code to fail. However, due to a bug, the distro server was
still being started, and early validation wasn’t triggered. As a result,
failures were likely being handled downstream by the providers. I’ve
maintained similar behavior by using ${env.NVIDIA_API_KEY:+}, though I
believe this is incorrect for many configurations. I’ll leave it to each
provider to correct it as needed.
* Environment variable substitution now uses the same syntax as Bash
parameter expansion.
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
This extracts the W3C trace context headers (traceparent and tracestate)
from incoming requests, stuffs them as attributes on the spans we
create, and uses them within the tracing provider implementation to
actually wrap our spans in the proper context.
What this means in practice is that when a client (such as an OpenAI
client) is instrumented to create these traces, we'll continue that
distributed trace within Llama Stack as opposed to creating our own root
span that breaks the distributed trace between client and server.
It's slightly awkward to do this in Llama Stack because our Tracing API
knows nothing about opentelemetry, W3C trace headers, etc - that's only
knowledge the specific provider implementation has. So, that's why the
trace headers get extracted by in the server code but not actually used
until the provider implementation to form the proper context.
This also centralizes how we were adding the `__root__` and
`__root_span__` attributes, as those two were being added in different
parts of the code instead of from a single place.
Closes#2097
## Test Plan
This was tested manually using the helpful scripts from #2097. I
verified that Llama Stack properly joined the client's span when the
client was instrumented for distributed tracing, and that Llama Stack
properly started its own root span when the incoming request was not
part of an existing trace.
Here's an example of the joined spans:
Signed-off-by: Ben Browning <bbrownin@redhat.com>
# What does this PR do?
Adds the API to query metrics from telemetry.
## Test Plan
llama stack run ~/.llama/distributions/fireworks/fireworks-run.yaml
---------
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
# What does this PR do?
The goal of this PR is code base modernization.
Schema reflection code needed a minor adjustment to handle UnionTypes
and collections.abc.AsyncIterator. (Both are preferred for latest Python
releases.)
Note to reviewers: almost all changes here are automatically generated
by pyupgrade. Some additional unused imports were cleaned up. The only
change worth of note can be found under `docs/openapi_generator` and
`llama_stack/strong_typing/schema.py` where reflection code was updated
to deal with "newer" types.
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
https://github.com/meta-llama/llama-stack/pull/1828 removed
__root_span__ attribute which is still needed
## Test Plan
added telemetry integration test
LLAMA_STACK_CONFIG=http://localhost:5001 pytest -s -v
tests/integration/telemetry --safety-shield meta-llama/Llama-Guard-3-8B
--text-model accounts/fireworks/models/llama-v3p3-70b-instruct
# 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?
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?
This PR adds back the changes in #1300 which were reverted in #1476 .
It also adds logic to preserve context variables across asyncio
boundary. this is needed with the library client since the async
generator logic yields control to code outside the event loop, and on
resuming, does not have the same context as before and this requires
preserving the context vars.
address #1477
## Test Plan
```
curl --request POST \
--url http://localhost:8321/v1/inference/chat-completion \
--header 'content-type: application/json' \
--data '{
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"messages": [
{
"role": "user",
"content": {
"type": "text",
"text": "where do humans live"
}
}
],
"stream": false
}' | jq .
{
"metrics": [
{
"trace_id": "kCZwO3tyQC-FuAGb",
"span_id": "bsP_5a5O",
"timestamp": "2025-03-11T16:47:38.549084Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "prompt_tokens",
"value": 10,
"unit": "tokens"
},
{
"trace_id": "kCZwO3tyQC-FuAGb",
"span_id": "bsP_5a5O",
"timestamp": "2025-03-11T16:47:38.549449Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "completion_tokens",
"value": 369,
"unit": "tokens"
},
{
"trace_id": "kCZwO3tyQC-FuAGb",
"span_id": "bsP_5a5O",
"timestamp": "2025-03-11T16:47:38.549457Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "total_tokens",
"value": 379,
"unit": "tokens"
}
],
"completion_message": {
"role": "assistant",
"content": "Humans live on the planet Earth, specifically on its landmasses and in its oceans. Here's a breakdown of where humans live:\n\n1. **Continents:** Humans inhabit all seven continents:\n\t* Africa\n\t* Antarctica ( temporary residents, mostly scientists and researchers)\n\t* Asia\n\t* Australia\n\t* Europe\n\t* North America\n\t* South America\n2. **Countries:** There are 196 countries recognized by the United Nations, and humans live in almost all of them.\n3. **Cities and towns:** Many humans live in urban areas, such as cities and towns, which are often located near coastlines, rivers, or other bodies of water.\n4. **Rural areas:** Some humans live in rural areas, such as villages, farms, and countryside.\n5. **Islands:** Humans inhabit many islands around the world, including those in the Pacific, Indian, and Atlantic Oceans.\n6. **Mountains and highlands:** Humans live in mountainous regions, such as the Himalayas, the Andes, and the Rocky Mountains.\n7. **Deserts:** Some humans live in desert regions, such as the Sahara, the Mojave, and the Atacama.\n8. **Coastal areas:** Many humans live in coastal areas, such as beaches, ports, and coastal cities.\n9. **Underwater habitats:** A few humans live in underwater habitats, such as research stations and submarines.\n10. **Space:** A small number of humans have lived in space, including astronauts on the International Space Station and those who have visited the Moon.\n\nOverall, humans can be found living in almost every environment on Earth, from the frozen tundra to the hottest deserts, and from the highest mountains to the deepest oceans.",
"stop_reason": "end_of_turn",
"tool_calls": []
},
"logprobs": null
}
```
Orignal repro no longer showing any error:
```
LLAMA_STACK_DISABLE_VERSION_CHECK=true llama stack run ~/.llama/distributions/fireworks/fireworks-run.yaml
python -m examples.agents.e2e_loop_with_client_tools localhost 8321
```
client logs:
https://gist.github.com/dineshyv/047c7e87b18a5792aa660e311ea53166
server logs:
https://gist.github.com/dineshyv/97a2174099619e9916c7c490be26e559
# What does this PR do?
Inference router computes the token usage related metrics for all
providers and returns the metrics as part of response and also logs to
telemetry.
## Test Plan
LLAMA_STACK_DISABLE_VERSION_CHECK=true llama stack run
~/.llama/distributions/fireworks/fireworks-run.yaml
```
curl --request POST \
--url http://localhost:8321/v1/inference/chat-completion \
--header 'content-type: application/json' \
--data '{
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"messages": [
{
"role": "user",
"content": {
"type": "text",
"text": "where do humans live"
}
}
],
"stream": false
}' | jq .
{
"metrics": [
{
"trace_id": "yjv1tf0jS1evOyPm",
"span_id": "WqYKvg0_",
"timestamp": "2025-02-27T18:55:10.770903Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "prompt_tokens",
"value": 10,
"unit": "tokens"
},
{
"trace_id": "yjv1tf0jS1evOyPm",
"span_id": "WqYKvg0_",
"timestamp": "2025-02-27T18:55:10.770916Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "completion_tokens",
"value": 411,
"unit": "tokens"
},
{
"trace_id": "yjv1tf0jS1evOyPm",
"span_id": "WqYKvg0_",
"timestamp": "2025-02-27T18:55:10.770919Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "total_tokens",
"value": 421,
"unit": "tokens"
}
],
"completion_message": {
"role": "assistant",
"content": "Humans live in various parts of the world, inhabiting almost every continent, country, and region. Here's a breakdown of where humans live:\n\n1. **Continents:** Humans inhabit all seven continents:\n\t* Africa\n\t* Antarctica (research stations only)\n\t* Asia\n\t* Australia\n\t* Europe\n\t* North America\n\t* South America\n2. **Countries:** There are 196 countries recognized by the United Nations, and humans live in almost all of them.\n3. **Regions:** Humans live in diverse regions, including:\n\t* Deserts (e.g., Sahara, Mojave)\n\t* Forests (e.g., Amazon, Congo)\n\t* Grasslands (e.g., Prairies, Steppes)\n\t* Mountains (e.g., Himalayas, Andes)\n\t* Oceans (e.g., coastal areas, islands)\n\t* Tundras (e.g., Arctic, sub-Arctic)\n4. **Cities and towns:** Many humans live in urban areas, such as cities and towns, which are often located near:\n\t* Coastlines\n\t* Rivers\n\t* Lakes\n\t* Mountains\n5. **Rural areas:** Some humans live in rural areas, such as:\n\t* Villages\n\t* Farms\n\t* Countryside\n6. **Islands:** Humans inhabit many islands, including:\n\t* Tropical islands (e.g., Hawaii, Maldives)\n\t* Arctic islands (e.g., Greenland, Iceland)\n\t* Continental islands (e.g., Great Britain, Ireland)\n7. **Extreme environments:** Humans also live in extreme environments, such as:\n\t* High-altitude areas (e.g., Tibet, Andes)\n\t* Low-altitude areas (e.g., Death Valley, Dead Sea)\n\t* Areas with extreme temperatures (e.g., Arctic, Sahara)\n\nOverall, humans have adapted to live in a wide range of environments and ecosystems around the world.",
"stop_reason": "end_of_turn",
"tool_calls": []
},
"logprobs": null
}
```
```
LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/integration/inference
======================================================================== short test summary info =========================================================================
FAILED tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=8B:vis=11B-inference:chat_completion:tool_calling_tools_absent-True] - ValueError: Unsupported tool prompt format: ToolPromptFormat.json
FAILED tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=8B:vis=11B-inference:chat_completion:tool_calling_tools_absent-False] - ValueError: Unsupported tool prompt format: ToolPromptFormat.json
FAILED tests/integration/inference/test_vision_inference.py::test_image_chat_completion_non_streaming[txt=8B:vis=11B] - fireworks.client.error.InvalidRequestError: {'error': {'object': 'error', 'type': 'invalid_request_error', 'message': 'Failed to decode image cannot identify image f...
FAILED tests/integration/inference/test_vision_inference.py::test_image_chat_completion_streaming[txt=8B:vis=11B] - fireworks.client.error.InvalidRequestError: {'error': {'object': 'error', 'type': 'invalid_request_error', 'message': 'Failed to decode image cannot identify image f...
========================================================= 4 failed, 16 passed, 23 xfailed, 17 warnings in 44.36s =========================================================
```
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?
When you re-initialize the library client in a notebook, we were seeing
this error:
```
Getting traces for session_id=5c8d1969-0957-49d2-b852-32cbb8ef8caf
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
[<ipython-input-11-d74bb6cdd3ab>](https://localhost:8080/#) in <cell line: 0>()
7 agent_logs = []
8
----> 9 for span in client.telemetry.query_spans(
10 attribute_filters=[
11 {"key": "session_id", "op": "eq", "value": session_id},
10 frames
[/usr/local/lib/python3.11/dist-packages/llama_stack/providers/inline/telemetry/meta_reference/telemetry.py](https://localhost:8080/#) in query_traces(self, attribute_filters, limit, offset, order_by)
246 ) -> QueryTracesResponse:
247 return QueryTracesResponse(
--> 248 data=await self.trace_store.query_traces(
249 attribute_filters=attribute_filters,
250 limit=limit,
AttributeError: 'TelemetryAdapter' object has no attribute 'trace_store'
```
This is happening because the we were skipping some required steps for
the object state as part of the global _TRACE_PROVIDER check. This PR
moves the initialization of the object state out of the TRACE_PROVIDER
init.
# What does this PR do?
Changes Telemetry API to follow more idiomatic REST
- [ ] Addresses issue (#issue)
## Test Plan
TBD, once i get an approval for rest endpoints
# What does this PR do?
This PR changes our API to follow more idiomatic REST API approaches of
having paths being resources and methods indicating the action being
performed.
Changes made to generator:
1) removed the prefix check of "get" as its not required and is actually
needed for other method types too
2) removed _ check on path since variables can have "_"
## Test Plan
LLAMA_STACK_BASE_URL=http://localhost:5000 pytest -v
tests/client-sdk/agents/test_agents.py
# What does this PR do?
Since we maintain global state in our telemetry pipeline,
reinstantiating lib cli will cause us to add duplicate span processors
causing sqlite to lock out because of constraint violations since we now
have two span processor writing to sqlite. This PR changes the telemetry
adapter for otel to only instantiate the provider once and add the span
processsors only once.
Also fixes an issue llama stack build
## Test Plan
tested with notebook at
https://colab.research.google.com/drive/1ck7hXQxRl6UvT-ijNRZ-gMZxH1G3cN2d#scrollTo=9496f75c
We cannot use recursive types because not only does our OpenAPI
generator not like them, even if it did, it is not easy for all client
languages to automatically construct proper APIs (especially considering
garbage collection) around them. For now, we can return a `Dict[str,
SpanWithStatus]` instead of `SpanWithChildren` and rely on the client to
reconstruct the tree.
Also fixed a super subtle issue with the OpenAPI generation process
(monkey-patching of json_schema_type wasn't working because of import
reordering.)
# What does this PR do?
#525 introduced a telemetry configuration named jaeger, but what it
really is pointing to is an OTLP HTTP endpoint which is supported by
most servers in the ecosystem, including raw opentelemetry collectors,
several APMs, and even https://github.com/ymtdzzz/otel-tui
I chose to rename this to "otel" as it will bring in more people to the
ecosystem vs feeling it only works with jaeger. Later, we can use the
[standard
ENV](https://opentelemetry.io/docs/specs/otel/protocol/exporter/) to
configure this if we like so that you can override things with variables
people might expect.
Note: I also added to the README that you have to install conda.
Depending on experience level of the user, and especially with miniforge
vs other ways, I felt this helps.
## Test Plan
I would like to test this, but actually got a little lost. The previous
PRs referenced yaml which doesn't seem published anywhere. It would be
nice to have a pre-canned setup that uses ollama and turns on otel, but
would also appreciate a hand on instructions meanwhile.
## Sources
https://github.com/meta-llama/llama-stack/pull/525
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [x] Ran pre-commit to handle lint / formatting issues.
- [x] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.
---------
Signed-off-by: Adrian Cole <adrian.cole@elastic.co>
This PR adds two new methods to the telemetry API:
1) Gives the ability to query spans directly instead of first querying
traces and then using that to get spans
2) Another method save_spans_to_dataset, which builds on the query spans
to save it on dataset.
This give the ability to saves spans that are part of an agent session
to a dataset.
The unique aspect of this API is that we dont require each provider of
telemetry to implement this method. Hence, its implemented in the
protocol class itself. This required the protocol check to be slightly
modified.
# What does this PR do?
Change the Telemetry API to be able to support different use cases like
returning traces for the UI and ability to export for Evals.
Other changes:
* Add a new trace_protocol decorator to decorate all our API methods so
that any call to them will automatically get traced across all impls.
* There is some issue with the decorator pattern of span creation when
using async generators, where there are multiple yields with in the same
context. I think its much more explicit by using the explicit context
manager pattern using with. I moved the span creations in agent instance
to be using with
* Inject session id at the turn level, which should quickly give us all
traces across turns for a given session
Addresses #509
## Test Plan
```
llama stack run /Users/dineshyv/.llama/distributions/llamastack-together/together-run.yaml
PYTHONPATH=. python -m examples.agents.rag_with_memory_bank localhost 5000
curl -X POST 'http://localhost:5000/alpha/telemetry/query-traces' \
-H 'Content-Type: application/json' \
-d '{
"attribute_filters": [
{
"key": "session_id",
"op": "eq",
"value": "dd667b87-ca4b-4d30-9265-5a0de318fc65" }],
"limit": 100,
"offset": 0,
"order_by": ["start_time"]
}' | jq .
[
{
"trace_id": "6902f54b83b4b48be18a6f422b13e16f",
"root_span_id": "5f37b85543afc15a",
"start_time": "2024-12-04T08:08:30.501587",
"end_time": "2024-12-04T08:08:36.026463"
},
{
"trace_id": "92227dac84c0615ed741be393813fb5f",
"root_span_id": "af7c5bb46665c2c8",
"start_time": "2024-12-04T08:08:36.031170",
"end_time": "2024-12-04T08:08:41.693301"
},
{
"trace_id": "7d578a6edac62f204ab479fba82f77b6",
"root_span_id": "1d935e3362676896",
"start_time": "2024-12-04T08:08:41.695204",
"end_time": "2024-12-04T08:08:47.228016"
},
{
"trace_id": "dbd767d76991bc816f9f078907dc9ff2",
"root_span_id": "f5a7ee76683b9602",
"start_time": "2024-12-04T08:08:47.234578",
"end_time": "2024-12-04T08:08:53.189412"
}
]
curl -X POST 'http://localhost:5000/alpha/telemetry/get-span-tree' \
-H 'Content-Type: application/json' \
-d '{ "span_id" : "6cceb4b48a156913", "max_depth": 2, "attributes_to_return": ["input"] }' | jq .
% Total % Received % Xferd Average Speed Time Time Time Current
Dload Upload Total Spent Left Speed
100 875 100 790 100 85 18462 1986 --:--:-- --:--:-- --:--:-- 20833
{
"span_id": "6cceb4b48a156913",
"trace_id": "dafa796f6aaf925f511c04cd7c67fdda",
"parent_span_id": "892a66d726c7f990",
"name": "retrieve_rag_context",
"start_time": "2024-12-04T09:28:21.781995",
"end_time": "2024-12-04T09:28:21.913352",
"attributes": {
"input": [
"{\"role\":\"system\",\"content\":\"You are a helpful assistant\"}",
"{\"role\":\"user\",\"content\":\"What are the top 5 topics that were explained in the documentation? Only list succinct bullet points.\",\"context\":null}"
]
},
"children": [
{
"span_id": "1a2df181854064a8",
"trace_id": "dafa796f6aaf925f511c04cd7c67fdda",
"parent_span_id": "6cceb4b48a156913",
"name": "MemoryRouter.query_documents",
"start_time": "2024-12-04T09:28:21.787620",
"end_time": "2024-12-04T09:28:21.906512",
"attributes": {
"input": null
},
"children": [],
"status": "ok"
}
],
"status": "ok"
}
```
<img width="1677" alt="Screenshot 2024-12-04 at 9 42 56 AM"
src="https://github.com/user-attachments/assets/4d3cea93-05ce-415a-93d9-4b1628631bf8">
