# What does this PR do?
It may not always be desirable to listen on all interfaces, which is the
default. As an example, by listening instead only on a loopback
interface, the server cannot be reached except from within the host it
is run on. This PR makes this configurable, through a CLI option, an env
var or an entry on the config file.
## Test Plan
I ran a server with and without the added CLI argument to verify that
the argument is used if provided, but the default is as it was before if
not.
Signed-off-by: Gordon Sim <gsim@redhat.com>
# What does this PR do?
fixes#2121
this implementation splits reponsibility between litellm and openai
libraries -
| Inference Method | Implementation Source |
|----------------------------|--------------------------|
| completion | LiteLLMOpenAIMixin |
| chat_completion | LiteLLMOpenAIMixin |
| embedding | LiteLLMOpenAIMixin |
| batch_completion | LiteLLMOpenAIMixin |
| batch_chat_completion | LiteLLMOpenAIMixin |
| openai_completion | AsyncOpenAI |
| openai_chat_completion | AsyncOpenAI |
## Test Plan
smoke test with -
```
$ OPENAI_API_KEY=$LLAMA_API_KEY OPENAI_BASE_URL=https://api.llama.com/compat/v1 llama stack build --image-type conda --image-name openai --providers inference=remote::openai --run
$ llama-stack-client models register Llama-4-Scout-17B-16E-Instruct-FP8
$ curl "http://localhost:8321/v1/openai/v1/chat/completions" -H "Content-Type: application/json" \ -d '{
"model": "Llama-4-Scout-17B-16E-Instruct-FP8",
"messages": [
{"role": "user", "content": "Hello Llama! Can you give me a quick intro?"}
]
}'
{"id":"AmPwrrkc5JgVjejPdIPrpT2","choices":[{"finish_reason":"stop","index":0,"logprobs":{"content":null,"refusal":null},"message":{"content":"Hello! I'm Llama, a Meta-designed model that adapts to your conversational style. Whether you need quick answers, deep dives into ideas, or just want to vent, joke, or brainstorm—I'm here for it. What’s on your mind?","refusal":"","role":"assistant","annotations":null,"audio":null,"function_call":null,"tool_calls":null,"id":"AmPwrrkc5JgVjejPdIPrpT2"}}],"created":1747410061,"model":"Llama-4-Scout-17B-16E-Instruct-FP8","object":"chat.completions","service_tier":null,"system_fingerprint":null,"usage":{"completion_tokens":54,"prompt_tokens":22,"total_tokens":76,"completion_tokens_details":null,"prompt_tokens_details":null}}
```
and run full test suite.
# What does this PR do?
## Test Plan
LLAMA_STACK_CONFIG=http://localhost:8321 pytest
tests/integration/tool_runtime/test_rag_tool.py --embedding-model
text-embedding-3-small
# What does this PR do?
This PR adds a few enhancements:
- Dark mode
- A dark mode icon
- Adds a link to the API documentation
- Adds prettier and a linter to the code
- Aligning the default text
- Linted the code
## Before:
## After (dark mode):
[//]: # (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)
Related to https://github.com/meta-llama/llama-stack/issues/2085
---------
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
We want this to be a "flagship" distribution we can advertize to a
segment of users to get started quickly. This distro should package a
bunch of remote providers and some cheap inline providers so they get a
solid "AI Platform in a box" setup instantly.
# What does this PR do?
This fixes an issue in how we used the tool_call_buf from streaming tool
calls in the remote-vllm provider where it would end up concatenating
parameters from multiple different tool call results instead of
aggregating the results from each tool call separately.
It also fixes an issue found while digging into that where we were
accidentally mixing the json string form of tool call parameters with
the string representation of the python form, which mean we'd end up
with single quotes in what should be double-quoted json strings.
Closes#1120
## Test Plan
The following tests are now passing 100% for the remote-vllm provider,
where some of the test_text_inference were failing before this change:
```
VLLM_URL="http://localhost:8000/v1" INFERENCE_MODEL="RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic" LLAMA_STACK_CONFIG=remote-vllm python -m pytest -v tests/integration/inference/test_text_inference.py --text-model "RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic"
VLLM_URL="http://localhost:8000/v1" INFERENCE_MODEL="RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic" LLAMA_STACK_CONFIG=remote-vllm python -m pytest -v tests/integration/inference/test_vision_inference.py --vision-model "RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic"
```
All but one of the agent tests are passing (including the multi-tool
one). See the PR at https://github.com/vllm-project/vllm/pull/17917 and
a gist at
https://gist.github.com/bbrowning/4734240ce96b4264340caa9584e47c9e for
changes needed there, which will have to get made upstream in vLLM.
Agent tests:
```
VLLM_URL="http://localhost:8000/v1" INFERENCE_MODEL="RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic" LLAMA_STACK_CONFIG=remote-vllm python -m pytest -v tests/integration/agents/test_agents.py --text-model "RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic"
````
---------
Signed-off-by: Ben Browning <bbrownin@redhat.com>
# What does this PR do?
We added:
* make sure docstrings are present with 'params' and 'returns'
* fail if someone sets 'returns: None'
* fix the failing APIs
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
currently the "default" dir for external providers is
`/etc/llama-stack/providers.d`
This dir is not used anywhere nor created.
Switch to a more friendly `~/.llama/providers.d/`
This allows external providers to actually create this dir and/or
populate it upon installation, `pip` cannot create directories in `etc`.
If a user does not specify a dir, default to this one
see https://github.com/containers/ramalama-stack/issues/36
Signed-off-by: Charlie Doern <cdoern@redhat.com>
# What does this PR do?
Currently the website only displays the "latest" version. This is
because our config and workflow do not include version information. This
PR adds missing version info.
---------
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
# What does this PR do?
This allows users to print the usage information for this script:
```
📚 Llama-Stack Deployment Script
Description:
This script sets up and deploys Llama-Stack with Ollama integration in containers.
It handles both Docker and Podman runtimes and includes automatic platform detection.
Usage:
install.sh [OPTIONS]
Options:
-p, --port PORT Server port for Llama-Stack (default: 8321)
-o, --ollama-port PORT Ollama service port (default: 11434)
-m, --model MODEL Model alias to use (default: llama3.2:3b)
-i, --image IMAGE Server image (default: llamastack/distribution-ollama:0.2.2)
-t, --timeout SECONDS Service wait timeout in seconds (default: 300)
-h, --help Show this help message
For more information:
Documentation: https://llama-stack.readthedocs.io/
GitHub: https://github.com/meta-llama/llama-stack
Report issues:
https://github.com/meta-llama/llama-stack/issues
```
---------
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
Co-authored-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
his PR allows users to customize the template used for chunks when
inserted into the context. Additionally, this enables metadata injection
into the context of an LLM for RAG. This makes a naive and crude
assumption that each chunk should include the metadata, this is
obviously redundant when multiple chunks are returned from the same
document. In order to remove any sort of duplication of chunks, we'd
have to make much more significant changes so this is a reasonable first
step that unblocks users requesting this enhancement in
https://github.com/meta-llama/llama-stack/issues/1767.
In the future, this can be extended to support citations.
List of Changes:
- `llama_stack/apis/tools/rag_tool.py`
- Added `chunk_template` field in `RAGQueryConfig`.
- Added `field_validator` to validate the `chunk_template` field in
`RAGQueryConfig`.
- Ensured the `chunk_template` field includes placeholders `{index}` and
`{chunk.content}`.
- Updated the `query` method to use the `chunk_template` for formatting
chunk text content.
- `llama_stack/providers/inline/tool_runtime/rag/memory.py`
- Modified the `insert` method to pass `doc.metadata` for chunk
creation.
- Enhanced the `query` method to format results using `chunk_template`
and exclude unnecessary metadata fields like `token_count`.
- `llama_stack/providers/utils/memory/vector_store.py`
- Updated `make_overlapped_chunks` to include metadata serialization and
token count for both content and metadata.
- Added error handling for metadata serialization issues.
- `pyproject.toml`
- Added `pydantic.field_validator` as a recognized `classmethod`
decorator in the linting configuration.
- `tests/integration/tool_runtime/test_rag_tool.py`
- Refactored test assertions to separate `assert_valid_chunk_response`
and `assert_valid_text_response`.
- Added integration tests to validate `chunk_template` functionality
with and without metadata inclusion.
- Included a test case to ensure `chunk_template` validation errors are
raised appropriately.
- `tests/unit/rag/test_vector_store.py`
- Added unit tests for `make_overlapped_chunks`, verifying chunk
creation with overlapping tokens and metadata integrity.
- Added tests to handle metadata serialization errors, ensuring proper
exception handling.
- `docs/_static/llama-stack-spec.html`
- Added a new `chunk_template` field of type `string` with a default
template for formatting retrieved chunks in RAGQueryConfig.
- Updated the `required` fields to include `chunk_template`.
- `docs/_static/llama-stack-spec.yaml`
- Introduced `chunk_template` field with a default value for
RAGQueryConfig.
- Updated the required configuration list to include `chunk_template`.
- `docs/source/building_applications/rag.md`
- Documented the `chunk_template` configuration, explaining how to
customize metadata formatting in RAG queries.
- Added examples demonstrating the usage of the `chunk_template` field
in RAG tool queries.
- Highlighted default values for `RAG` agent configurations.
# Resolves https://github.com/meta-llama/llama-stack/issues/1767
## Test Plan
Updated both `test_vector_store.py` and `test_rag_tool.py` and tested
end-to-end with a script.
I also tested the quickstart to enable this and specified this metadata:
```python
document = RAGDocument(
document_id="document_1",
content=source,
mime_type="text/html",
metadata={"author": "Paul Graham", "title": "How to do great work"},
)
```
Which produced the output below:
This highlights the usefulness of the additional metadata. Notice how
the metadata is redundant for different chunks of the same document. I
think we can update that in a subsequent PR.
# Documentation
I've added a brief comment about this in the documentation to outline
this to users and updated the API documentation.
---------
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
# What does this PR do?
Introduces scaffolding for Llama Stack's UI. Created with next.js and
https://ui.shadcn.com/.
1. Initialized directory with `npx shadcn@latest init`
2. Added sidebar component `npx shadcn@latest add sidebar` and added
menu items for chat completions and responses.
3. Placeholder pages for each.
## Test Plan
`npm run dev`
<img width="1058" alt="image"
src="https://github.com/user-attachments/assets/5695a53f-e22e-418e-80d1-5bf0ae9b6fe8"
/>
# What does this PR do?
In the Responses API, we convert incoming response requests to chat
completion requests. When streaming the resulting chunks of those chat
completion requests, inference providers that use OpenAI clients will
often return a `type=None` value in the tool call parts of the response.
This causes issues when we try to dump and load that response into our
pydantic model, because type cannot be None in the Responses API model
we're loading these into.
So, strip the "type" field, if present, off those chat completion tool
call results before dumping and loading them as our typed pydantic
models, which will apply our default value for that type field.
## Test Plan
This was found via manual testing of the Responses API with codex, where
I was getting errors in some tool call situations. I added a unit test
to simulate this scenario and verify the fix, as well as manual codex
testing to verify the fix.
Signed-off-by: Ben Browning <bbrownin@redhat.com>
note: the openai provider exposes the litellm specific model names to
the user. this change is compatible with that. the litellm names should
be deprecated.
# What does this PR do?
Closes#2113.
Closes#1783.
Fixes a bug in handling the end of tool execution request stream where
no `finish_reason` is provided by the model.
## Test Plan
1. Ran existing unit tests
2. Added a dedicated test verifying correct behavior in this edge case
3. Ran the code snapshot from #2113
[//]: # (## Documentation)
# What does this PR do?
most third-party actions use hashes for pinning but not all
do proper hash pinning on all remaining actions using tags
Signed-off-by: Nathan Weinberg <nweinber@redhat.com>
# What does this PR do?
Closes#2111.
Fixes an error causing Llama Stack to just return `<tool_call>` and
complete the turn without actually executing the tool. See the issue
description for more detail.
## Test Plan
1) Ran existing unit tests
2) Added a dedicated test verifying correct behavior in this edge case
3) Ran the code snapshot from #2111
The provider selling point *is* using the same provider for both.
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
Prevent it from returning results about
'LT Wright Maverick Scout' knives. Ultimatly
we want the word "model" in the returned results
putting llm in the search term make this more likely.
Closes: #2150
Signed-off-by: Derek Higgins <derekh@redhat.com>
# What does this PR do?
This is a combination of what was previously 3 separate PRs - #2069,
#2075, and #2083. It turns out all 3 of those are needed to land a
working function calling Responses implementation. The web search
builtin tool was already working, but this wires in support for custom
function calling.
I ended up combining all three into one PR because they all had lots of
merge conflicts, both with each other but also with #1806 that just
landed. And, because landing any of them individually would have only
left a partially working implementation merged.
The new things added here are:
* Storing of input items from previous responses and restoring of those
input items when adding previous responses to the conversation state
* Handling of multiple input item messages roles, not just "user"
messages.
* Support for custom tools passed into the Responses API to enable
function calling outside of just the builtin websearch tool.
Closes#2074Closes#2080
## Test Plan
### Unit Tests
Several new unit tests were added, and they all pass. Ran via:
```
python -m pytest -s -v tests/unit/providers/agents/meta_reference/test_openai_responses.py
```
### Responses API Verification Tests
I ran our verification run.yaml against multiple providers to ensure we
were getting a decent pass rate. Specifically, I ensured the new custom
tool verification test passed across multiple providers and that the
multi-turn examples passed across at least some of the providers (some
providers struggle with the multi-turn workflows still).
Running the stack setup for verification testing:
```
llama stack run --image-type venv tests/verifications/openai-api-verification-run.yaml
```
Together, passing 100% as an example:
```
pytest -s -v 'tests/verifications/openai_api/test_responses.py' --provider=together-llama-stack
```
## Documentation
We will need to start documenting the OpenAI APIs, but for now the
Responses stuff is still rapidly evolving so delaying that.
---------
Signed-off-by: Derek Higgins <derekh@redhat.com>
Signed-off-by: Ben Browning <bbrownin@redhat.com>
Co-authored-by: Derek Higgins <derekh@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
# What does this PR do?
reduces duplication and centralizes information to be easier to find for
contributors
Signed-off-by: Nathan Weinberg <nweinber@redhat.com>
# What does this PR do?
While adding other tests, I came across this and wasn’t sure how useful
it is. It doesn’t seem to be exercised anywhere in CI, but I figured I’d
fix it anyway. Happy to remove it if preferred. :)
## Test Plan
Run:
```
uv run pytest tests/integration/inference --stack-config=ollama --report=test_report.md -v --text-model="llama3.2:3b" --embedding-model=all-MiniLM-L6-v2
```
Look at the produced `test_report.md`.
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
This adds a config option for a CA to be specified with which client
certs are verified. If specified client certs are required. This offers
a simple way of securing access to the server.
(Note: at present it is not possible to access the details of the client
certificate using uvicorn (unless it was monkey patched). Though there
is a defined TLS extension for ASGI, this is not implemented in uvicorn
pending a review and likely change to the specification. See
https://github.com/encode/uvicorn/pull/1119 and
https://github.com/django/asgiref/issues/466. Without access to the DN
it isn't possible to set user access attributes for a mutually
authentication tls connection, so more fine grained access control is
not yet possible).
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
Used proposed config option to specify a CA and verified that the server
can only be accessed with a valid client certificate.
[//]: # (## Documentation)
Signed-off-by: Gordon Sim <gsim@redhat.com>
# What does this PR do?
The ollama provider was using an older variant of the code to convert
incoming parameters from the OpenAI API completions and chat completion
endpoints into requests that get sent to the backend provider over its
own OpenAI client. This updates it to use the common
`prepare_openai_completion_params` method used elsewhere, which takes
care of removing stray `None` values even for nested structures.
Without this, some other parameters, even if they have values of `None`,
make their way to ollama and actually influence its inference output as
opposed to when those parameters are not sent at all.
## Test Plan
This passes tests/integration/inference/test_openai_completion.py and
fixes the issue found in #2098, which was tested via manual curl
requests crafted a particular way.
Closes#2098
Signed-off-by: Ben Browning <bbrownin@redhat.com>
# What does this PR do?
This new check will fail if some webmethods are missing the ellipsis:
```
API Method Return Type Validation Errors:
Method Api.eval.job_result does not contain ellipsis (...) in its implementation
Method Api.agents.create_agent_turn does not contain ellipsis (...) in its implementation
Method Api.agents.create_openai_response does not contain ellipsis (...) in its implementation
Method Api.eval.evaluate_rows does not contain ellipsis (...) in its implementation
Method Api.eval.run_eval does not contain ellipsis (...) in its implementation
```
Unless not implemented.
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
This PR adds stubs to the end of functions create_agent_turn,
create_openai_response and job_result.
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
Ran provided unit tests
[//]: # (## Documentation)
```
$ INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
CHROMADB_URL=http://localhost:8000 \
llama stack build --image-type conda --image-name llama \
--providers vector_io=remote::chromadb,inference=remote::ollama \
--run
...
File ".../llama_stack/providers/remote/vector_io/chroma/chroma.py", line 31, in <module>
ChromaClientType = chromadb.AsyncHttpClient | chromadb.PersistentClient
TypeError: unsupported operand type(s) for |: 'function' and 'function'
```
issue: AsyncHttpClient and PersistentClient are functions that return
AsyncClientAPI and ClientAPI types, respectively. | cannot be used to
construct a type from functions.
previously the code was Union[AsyncHttpClient, PersistentClient], which
did not trigger an error
# What does this PR do?
Closes#2135
# What does this PR do?
As per docs [1], since python 3.11 wait_for() raises TimeoutError. Since
we currently support python 3.10+, we have to catch both.
[1]:
https://docs.python.org/3.12/library/asyncio-task.html#asyncio.wait_for
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
No explicit testing; just code hardening to reflect docs.
[//]: # (## Documentation)
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
This PR fixes the behavior of the `/tool-runtime/rag-tool/query`
endpoint when invoked with an empty `vector_db_ids` parameter.
As of now, it simply returns an empty result, which leads to a
misleading error message from the server and makes it difficult and
time-consuming to detect the problem with the input parameter.
The proposed fix is to return an indicative error message in this case.
## Test Plan
Running the following script:
```
agent = Agent(
client,
model=MODEL_ID,
instructions=SYSTEM_PROMPT,
tools=[
dict(
name="builtin::rag/knowledge_search",
args={
"vector_db_ids": [],
},
)
],
)
response = agent.create_turn(
messages=[
{
"role": "user",
"content": "How to install OpenShift?",
}
],
session_id=agent.create_session(f"rag-session")
)
```
results in the following error message in the non-patched version:
```
{"type": "function", "name": "knowledge_search", "parameters": {"query": "installing OpenShift"}}400: Invalid value: Tool call result (id: 494b8020-90bb-449b-aa76-10960d6b2cc2, name: knowledge_search) does not have any content
```
and in the following one in the patched version:
```
{"type": "function", "name": "knowledge_search", "parameters": {"query": "installing OpenShift"}}400: Invalid value: No vector DBs were provided to the RAG tool. Please provide at least one DB.
```
# 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?
We are dropping configuration via CLI flag almost entirely. If any
server configuration has to be tweak it must be done through the server
section in the run.yaml.
This is unfortunately a breaking change for whover was using:
* `--tls-*`
* `--disable_ipv6`
`--port` stays around and get a special treatment since we believe, it's
common for user dev to change port for quick experimentations.
Closes: https://github.com/meta-llama/llama-stack/issues/1076
## Test Plan
Simply do `llama stack run <config>` nothing should break :)
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
In our OpenAI API verification tests, some providers were still calling
tools even when `tool_choice="none"` was passed in the chat completion
requests. Because they aren't all respecting `tool_choice` properly,
this adjusts our routing implementation to remove the `tools` and
`tool_choice` from the request if `tool_choice="none"` is passed in so
that it does not attempt to call any of those tools. Adjusting this in
the router fixes this across all providers.
This also cleans up the non-streaming together.ai responses for tools,
ensuring it returns `None` instead of an empty list when there are no
tool calls, to exactly match the OpenAI API responses in that case.
## Test Plan
I observed existing failures in our OpenAI API verification suite - see
https://github.com/bbrowning/llama-stack-tests/blob/main/openai-api-verification/2025-04-27.md#together-llama-stack
for the failing `test_chat_*_tool_choice_none` tests. All streaming and
non-streaming variants were failing across all 3 tested models.
After this change, all of those 6 failing tests are now passing with no
regression in the other tests.
I verified this via:
```
llama stack run --image-type venv \
tests/verifications/openai-api-verification-run.yaml
```
```
python -m pytest -s -v \
'tests/verifications/openai_api/test_chat_completion.py' \
--provider=together-llama-stack
```
The entire verification suite is not 100% on together.ai yet, but it's
getting closer.
This also increased the pass rate for fireworks.ai, and did not regress
the groq or openai tests at all.
Signed-off-by: Ben Browning <bbrownin@redhat.com>
