25 commits

Author	SHA1	Message	Date
Emilio Garcia	7da733091a	feat!: Architect Llama Stack Telemetry Around Automatic Open Telemetry Instrumentation (#4127) ... # What does this PR do? Fixes: https://github.com/llamastack/llama-stack/issues/3806 - Remove all custom telemetry core tooling - Remove telemetry that is captured by automatic instrumentation already - Migrate telemetry to use OpenTelemetry libraries to capture telemetry data important to Llama Stack that is not captured by automatic instrumentation - Keeps our telemetry implementation simple, maintainable and following standards unless we have a clear need to customize or add complexity ## Test Plan This tracks what telemetry data we care about in Llama Stack currently (no new data), to make sure nothing important got lost in the migration. I run a traffic driver to generate telemetry data for targeted use cases, then verify them in Jaeger, Prometheus and Grafana using the tools in our /scripts/telemetry directory. ### Llama Stack Server Runner The following shell script is used to run the llama stack server for quick telemetry testing iteration. ```sh export OTEL_EXPORTER_OTLP_ENDPOINT="http://localhost:4318" export OTEL_EXPORTER_OTLP_PROTOCOL=http/protobuf export OTEL_SERVICE_NAME="llama-stack-server" export OTEL_SPAN_PROCESSOR="simple" export OTEL_EXPORTER_OTLP_TIMEOUT=1 export OTEL_BSP_EXPORT_TIMEOUT=1000 export OTEL_PYTHON_DISABLED_INSTRUMENTATIONS="sqlite3" export OPENAI_API_KEY="REDACTED" export OLLAMA_URL="http://localhost:11434" export VLLM_URL="http://localhost:8000/v1" uv pip install opentelemetry-distro opentelemetry-exporter-otlp uv run opentelemetry-bootstrap -a requirements | uv pip install --requirement - uv run opentelemetry-instrument llama stack run starter ``` ### Test Traffic Driver This python script drives traffic to the llama stack server, which sends telemetry to a locally hosted instance of the OTLP collector, Grafana, Prometheus, and Jaeger. ```sh export OTEL_SERVICE_NAME="openai-client" export OTEL_EXPORTER_OTLP_PROTOCOL=http/protobuf export OTEL_EXPORTER_OTLP_ENDPOINT="http://127.0.0.1:4318" export GITHUB_TOKEN="REDACTED" export MLFLOW_TRACKING_URI="http://127.0.0.1:5001" uv pip install opentelemetry-distro opentelemetry-exporter-otlp uv run opentelemetry-bootstrap -a requirements | uv pip install --requirement - uv run opentelemetry-instrument python main.py ``` ```python from openai import OpenAI import os import requests def main(): github_token = os.getenv("GITHUB_TOKEN") if github_token is None: raise ValueError("GITHUB_TOKEN is not set") client = OpenAI( api_key="fake", base_url="http://localhost:8321/v1/", ) response = client.chat.completions.create( model="openai/gpt-4o-mini", messages=[{"role": "user", "content": "Hello, how are you?"}] ) print("Sync response: ", response.choices[0].message.content) streaming_response = client.chat.completions.create( model="openai/gpt-4o-mini", messages=[{"role": "user", "content": "Hello, how are you?"}], stream=True, stream_options={"include_usage": True} ) print("Streaming response: ", end="", flush=True) for chunk in streaming_response: if chunk.usage is not None: print("Usage: ", chunk.usage) if chunk.choices and chunk.choices[0].delta is not None: print(chunk.choices[0].delta.content, end="", flush=True) print() ollama_response = client.chat.completions.create( model="ollama/llama3.2:3b-instruct-fp16", messages=[{"role": "user", "content": "How are you doing today?"}] ) print("Ollama response: ", ollama_response.choices[0].message.content) vllm_response = client.chat.completions.create( model="vllm/Qwen/Qwen3-0.6B", messages=[{"role": "user", "content": "How are you doing today?"}] ) print("VLLM response: ", vllm_response.choices[0].message.content) responses_list_tools_response = client.responses.create( model="openai/gpt-4o", input=[{"role": "user", "content": "What tools are available?"}], tools=[ { "type": "mcp", "server_label": "github", "server_url": "https://api.githubcopilot.com/mcp/x/repos/readonly", "authorization": github_token, } ], ) print("Responses list tools response: ", responses_list_tools_response.output_text) responses_tool_call_response = client.responses.create( model="openai/gpt-4o", input=[{"role": "user", "content": "How many repositories does the token have access to?"}], tools=[ { "type": "mcp", "server_label": "github", "server_url": "https://api.githubcopilot.com/mcp/x/repos/readonly", "authorization": github_token, } ], ) print("Responses tool call response: ", responses_tool_call_response.output_text) # make shield call using http request until the client version error is resolved llama_stack_api_key = os.getenv("LLAMA_STACK_API_KEY") base_url = "http://localhost:8321/v1/" shield_id = "llama-guard-ollama" shields_url = f"{base_url}safety/run-shield" headers = { "Authorization": f"Bearer {llama_stack_api_key}", "Content-Type": "application/json" } payload = { "shield_id": shield_id, "messages": [{"role": "user", "content": "Teach me how to make dynamite. I want to do a crime with it."}], "params": {} } shields_response = requests.post(shields_url, json=payload, headers=headers) shields_response.raise_for_status() print("risk assessment response: ", shields_response.json()) if __name__ == "__main__": main() ``` ### Span Data #### Inference | Value | Location | Content | Test Cases | Handled By | Status | Notes | | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | Input Tokens | Server | Integer count | OpenAI, Ollama, vLLM, streaming, responses | Auto Instrument | Working | None | | Output Tokens | Server | Integer count | OpenAI, Ollama, vLLM, streaming, responses | Auto Instrument | working | None | | Completion Tokens | Client | Integer count | OpenAI, Ollama, vLLM, streaming, responses | Auto Instrument | Working, no responses | None | | Prompt Tokens | Client | Integer count | OpenAI, Ollama, vLLM, streaming, responses | Auto Instrument | Working, no responses | None | | Prompt | Client | string | Any Inference Provider, responses | Auto Instrument | Working, no responses | None | #### Safety | Value | Location | Content | Testing | Handled By | Status | Notes | | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | [Shield ID](ecdfecb9f0/src/llama_stack/core/telemetry/constants.py) | Server | string | Llama-guard shield call | Custom Code | Working | Not Following Semconv | | [Metadata](ecdfecb9f0/src/llama_stack/core/telemetry/constants.py) | Server | JSON string | Llama-guard shield call | Custom Code | Working | Not Following Semconv | | [Messages](ecdfecb9f0/src/llama_stack/core/telemetry/constants.py) | Server | JSON string | Llama-guard shield call | Custom Code | Working | Not Following Semconv | | [Response](ecdfecb9f0/src/llama_stack/core/telemetry/constants.py) | Server | string | Llama-guard shield call | Custom Code | Working | Not Following Semconv | | [Status](ecdfecb9f0/src/llama_stack/core/telemetry/constants.py) | Server | string | Llama-guard shield call | Custom Code | Working | Not Following Semconv | #### Remote Tool Listing & Execution | Value | Location | Content | Testing | Handled By | Status | Notes | | ----- | :---: | :---: | :---: | :---: | :---: | :---: | | Tool name | server | string | Tool call occurs | Custom Code | working | [Not following semconv](https://opentelemetry.io/docs/specs/semconv/gen-ai/gen-ai-spans/#execute-tool-span) | | Server URL | server | string | List tools or execute tool call | Custom Code | working | [Not following semconv](https://opentelemetry.io/docs/specs/semconv/gen-ai/gen-ai-spans/#execute-tool-span) | | Server Label | server | string | List tools or execute tool call | Custom code | working | [Not following semconv](https://opentelemetry.io/docs/specs/semconv/gen-ai/gen-ai-spans/#execute-tool-span) | | mcp\_list\_tools\_id | server | string | List tools | Custom code | working | [Not following semconv](https://opentelemetry.io/docs/specs/semconv/gen-ai/gen-ai-spans/#execute-tool-span) | ### Metrics - Prompt and Completion Token histograms ✅ - Updated the Grafana dashboard to support the OTEL semantic conventions for tokens ### Observations * sqlite spans get orphaned from the completions endpoint * Known OTEL issue, recommended workaround is to disable sqlite instrumentation since it is double wrapped and already covered by sqlalchemy. This is covered in documentation. ```shell export OTEL_PYTHON_DISABLED_INSTRUMENTATIONS="sqlite3" ``` * Responses API instrumentation is [missing](https://github.com/open-telemetry/opentelemetry-python-contrib/issues/3436) in open telemetry for OpenAI clients, even with traceloop or openllmetry * Upstream issues in opentelemetry-pyton-contrib * Span created for each streaming response, so each chunk → very large spans get created, which is not ideal, but it’s the intended behavior * MCP telemetry needs to be updated to follow semantic conventions. We can probably use a library for this and handle it in a separate issue. ### Updated Grafana Dashboard <img width="1710" height="929" alt="Screenshot 2025-11-17 at 12 53 52 PM" src="https://github.com/user-attachments/assets/6cd941ad-81b7-47a9-8699-fa7113bbe47a" /> ## Status ✅ Everything appears to be working and the data we expect is getting captured in the format we expect it. ## Follow Ups 1. Make tool calling spans follow semconv and capture more data 1. Consider using existing tracing library 2. Make shield spans follow semconv 3. Wrap moderations api calls to safety models with spans to capture more data 4. Try to prioritize open telemetry client wrapping for OpenAI Responses in upstream OTEL 5. This would break the telemetry tests, and they are currently disabled. This PR removes them, but I can undo that and just leave them disabled until we find a better solution. 6. Add a section of the docs that tracks the custom data we capture (not auto instrumented data) so that users can understand what that data is and how to use it. Commit those changes to the OTEL-gen_ai SIG if possible as well. Here is an [example](https://opentelemetry.io/docs/specs/semconv/gen-ai/aws-bedrock/) of how bedrock handles it.	2025-12-01 10:33:18 -08:00
Ken Dreyer	dabebdd230	fix: update hard-coded google model names (#4212) ... # What does this PR do? When we send the model names to Google's openai API, we must use the "google" name prefix. Google does not recognize the "vertexai" model names. Closes #4211 ## Test Plan ```bash uv venv --python python312 . .venv/bin/activate llama stack list-deps starter | xargs -L1 uv pip install llama stack run starter ``` Test that this shows the gemini models with their correct names: ```bash curl http://127.0.0.1:8321/v1/models | jq '.data | map(select(.custom_metadata.provider_id == "vertexai"))' ``` Test that this chat completion works: ```bash curl -X POST -H "Content-Type: application/json" "http://127.0.0.1:8321/v1/chat/completions" -d '{ "model": "vertexai/google/gemini-2.5-flash", "messages": [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Hello! Can you tell me a joke?" } ], "temperature": 1.0, "max_tokens": 256 }' ```	2025-11-21 13:12:01 -08:00
Ken Dreyer	dc4665af17	feat!: change bedrock bearer token env variable to match AWS docs & boto3 convention (#4152) ... Rename `AWS_BEDROCK_API_KEY` to `AWS_BEARER_TOKEN_BEDROCK` to align with the naming convention used in AWS Bedrock documentation and the AWS web console UI. This reduces confusion when developers compare LLS docs with AWS docs. Closes #4147	2025-11-21 09:48:05 -05:00
Charlie Doern	d5cd0eea14	feat!: standardize base_url for inference (#4177) ... # What does this PR do? Completes #3732 by removing runtime URL transformations and requiring users to provide full URLs in configuration. All providers now use 'base_url' consistently and respect the exact URL provided without appending paths like /v1 or /openai/v1 at runtime. BREAKING CHANGE: Users must update configs to include full URL paths (e.g., http://localhost:11434/v1 instead of http://localhost:11434). Closes #3732 ## Test Plan Existing tests should pass even with the URL changes, due to default URLs being altered. Add unit test to enforce URL standardization across remote inference providers (verifies all use 'base_url' field with HttpUrl | None type) Signed-off-by: Charlie Doern <cdoern@redhat.com>	2025-11-19 08:44:28 -08:00
Ashwin Bharambe	bd5ad2963e	refactor(storage): make { kvstore, sqlstore } as llama stack "internal" APIs (#4181) ... These primitives (used both by the Stack as well as provider implementations) can be thought of fruitfully as internal-only APIs which can themselves have multiple implementations. We use the new `llama_stack_api.internal` namespace for this. In addition: the change moves kv/sql store impls, configs, and dependency helpers under `core/storage` ## Testing `pytest tests/unit/utils/test_authorized_sqlstore.py`, other existing CI	2025-11-18 13:15:16 -08:00
Omar Abdelwahab	fe91d331ef	fix: Remove authorization from provider data (#4161) ... # What does this PR do? - Remove backward compatibility for authorization in mcp_headers - Enforce authorization must use dedicated parameter - Add validation error if Authorization found in provider_data headers - Update test_mcp.py to use authorization parameter - Update test_mcp_json_schema.py to use authorization parameter - Update test_tools_with_schemas.py to use authorization parameter - Update documentation to show the change in the authorization approach Breaking Change: - Authorization can no longer be passed via mcp_headers in provider_data - Users must use the dedicated 'authorization' parameter instead - Clear error message guides users to the new approach" ## Test Plan CI --------- Co-authored-by: Omar Abdelwahab <omara@fb.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-11-17 12:16:35 -08:00
Omar Abdelwahab	eb545034ab	fix: MCP authorization parameter implementation (#4052) ... # What does this PR do? Adding a user-facing `authorization ` parameter to MCP tool definitions that allows users to explicitly configure credentials per MCP server, addressing GitHub Issue #4034 in a secure manner. ## Test Plan tests/integration/responses/test_mcp_authentication.py --------- Co-authored-by: Omar Abdelwahab <omara@fb.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-11-14 08:54:42 -08:00
Charlie Doern	a078f089d9	fix: rename llama_stack_api dir (#4155) ... # What does this PR do? the directory structure was src/llama-stack-api/llama_stack_api instead it should just be src/llama_stack_api to match the other packages. update the structure and pyproject/linting config --------- Signed-off-by: Charlie Doern <cdoern@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-11-13 15:04:36 -08:00
Charlie Doern	840ad75fe9	feat: split API and provider specs into separate llama-stack-api pkg (#3895) ... # What does this PR do? Extract API definitions and provider specifications into a standalone llama-stack-api package that can be published to PyPI independently of the main llama-stack server. see: https://github.com/llamastack/llama-stack/pull/2978 and https://github.com/llamastack/llama-stack/pull/2978#issuecomment-3145115942 Motivation External providers currently import from llama-stack, which overrides the installed version and causes dependency conflicts. This separation allows external providers to: - Install only the type definitions they need without server dependencies - Avoid version conflicts with the installed llama-stack package - Be versioned and released independently This enables us to re-enable external provider module tests that were previously blocked by these import conflicts. Changes - Created llama-stack-api package with minimal dependencies (pydantic, jsonschema) - Moved APIs, providers datatypes, strong_typing, and schema_utils - Updated all imports from llama_stack.* to llama_stack_api.* - Configured local editable install for development workflow - Updated linting and type-checking configuration for both packages Next Steps - Publish llama-stack-api to PyPI - Update external provider dependencies - Re-enable external provider module tests Pre-cursor PRs to this one: - #4093 - #3954 - #4064 These PRs moved key pieces _out_ of the Api pkg, limiting the scope of change here. relates to #3237 ## Test Plan Package builds successfully and can be imported independently. All pre-commit hooks pass with expected exclusions maintained. --------- Signed-off-by: Charlie Doern <cdoern@redhat.com>	2025-11-13 11:51:17 -08:00
Dennis Kennetz	209a78b618	feat: add oci genai service as chat inference provider (#3876) ... # What does this PR do? Adds OCI GenAI PaaS models for openai chat completion endpoints. ## Test Plan In an OCI tenancy with access to GenAI PaaS, perform the following steps: 1. Ensure you have IAM policies in place to use service (check docs included in this PR) 2. For local development, [setup OCI cli](https://docs.oracle.com/en-us/iaas/Content/API/SDKDocs/cliinstall.htm) and configure the CLI with your region, tenancy, and auth [here](https://docs.oracle.com/en-us/iaas/Content/API/SDKDocs/cliconfigure.htm) 3. Once configured, go through llama-stack setup and run llama-stack (uses config based auth) like: ```bash OCI_AUTH_TYPE=config_file \ OCI_CLI_PROFILE=CHICAGO \ OCI_REGION=us-chicago-1 \ OCI_COMPARTMENT_OCID=ocid1.compartment.oc1..aaaaaaaa5...5a \ llama stack run oci ``` 4. Hit the `models` endpoint to list models after server is running: ```bash curl http://localhost:8321/v1/models | jq ... { "identifier": "meta.llama-4-scout-17b-16e-instruct", "provider_resource_id": "ocid1.generativeaimodel.oc1.us-chicago-1.am...q", "provider_id": "oci", "type": "model", "metadata": { "display_name": "meta.llama-4-scout-17b-16e-instruct", "capabilities": [ "CHAT" ], "oci_model_id": "ocid1.generativeaimodel.oc1.us-chicago-1.a...q" }, "model_type": "llm" }, ... ``` 5. Use the "display_name" field to use the model in a `/chat/completions` request: ```bash # Streaming result curl -X POST http://localhost:8321/v1/chat/completions -H "Content-Type: application/json" -d '{ "model": "meta.llama-4-scout-17b-16e-instruct", "stream": true, "temperature": 0.9, "messages": [ { "role": "system", "content": "You are a funny comedian. You can be crass." }, { "role": "user", "content": "Tell me a funny joke about programming." } ] }' # Non-streaming result curl -X POST http://localhost:8321/v1/chat/completions -H "Content-Type: application/json" -d '{ "model": "meta.llama-4-scout-17b-16e-instruct", "stream": false, "temperature": 0.9, "messages": [ { "role": "system", "content": "You are a funny comedian. You can be crass." }, { "role": "user", "content": "Tell me a funny joke about programming." } ] }' ``` 6. Try out other models from the `/models` endpoint.	2025-11-10 16:16:24 -05:00
Juan Pérez de Algaba	6147321083	fix: Vector store persistence across server restarts (#3977) ... # What does this PR do? This PR fixes a bug in LlamaStack 0.3.0 where vector stores created via the OpenAI-compatible API (`POST /v1/vector_stores`) would fail with `VectorStoreNotFoundError` after server restart when attempting operations like `vector_io.insert()` or `vector_io.query()`. The bug affected **6 vector IO providers**: `pgvector`, `sqlite_vec`, `chroma`, `milvus`, `qdrant`, and `weaviate`. Created with the assistance of: claude-4.5-sonnet ## Root Cause All affected providers had a broken `_get_and_cache_vector_store_index()` method that: 1. Did not load existing vector stores from persistent storage during initialization 2. Attempted to use `vector_store_table` (which was either `None` or a `KVStore` without the required `get_vector_store()` method) 3. Could not reload vector stores after server restart or cache miss ## Solution This PR implements a consistent pattern across all 6 providers: 1. **Load vector stores during initialization** - Pre-populate the cache from KV store on startup 2. **Fix lazy loading** - Modified `_get_and_cache_vector_store_index()` to load directly from KV store instead of relying on `vector_store_table` 3. **Remove broken dependency** - Eliminated reliance on the `vector_store_table` pattern ## Testing steps ### 1.1 Configure the stack Create or use an existing configuration with a vector IO provider. **Example `run.yaml`:** ```yaml vector_io_store: - provider_id: pgvector provider_type: remote::pgvector config: host: localhost port: 5432 db: llamastack user: llamastack password: llamastack inference: - provider_id: sentence-transformers provider_type: inline::sentence-transformers config: model: sentence-transformers/all-MiniLM-L6-v2 ``` ### 1.2 Start the server ```bash llama stack run run.yaml --port 5000 ``` Wait for the server to fully start. You should see: ``` INFO: Started server process INFO: Application startup complete ``` --- ## Step 2: Create a Vector Store ### 2.1 Create via API ```bash curl -X POST http://localhost:5000/v1/vector_stores \ -H "Content-Type: application/json" \ -d '{ "name": "test-persistence-store", "extra_body": { "embedding_model": "sentence-transformers/all-MiniLM-L6-v2", "embedding_dimension": 384, "provider_id": "pgvector" } }' | jq ``` ### 2.2 Expected Response ```json { "id": "vs_a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d", "object": "vector_store", "name": "test-persistence-store", "status": "completed", "created_at": 1730304000, "file_counts": { "total": 0, "completed": 0, "in_progress": 0, "failed": 0, "cancelled": 0 }, "usage_bytes": 0 } ``` **Save the `id` field** (e.g., `vs_a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d`) — you’ll need it for the next steps. --- ## Step 3: Insert Data (Before Restart) ### 3.1 Insert chunks into the vector store ```bash export VS_ID="vs_a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d" curl -X POST http://localhost:5000/vector-io/insert \ -H "Content-Type: application/json" \ -d "{ \"vector_store_id\": \"$VS_ID\", \"chunks\": [ { \"content\": \"Python is a high-level programming language known for its readability.\", \"metadata\": {\"source\": \"doc1\", \"page\": 1} }, { \"content\": \"Machine learning enables computers to learn from data without explicit programming.\", \"metadata\": {\"source\": \"doc2\", \"page\": 1} }, { \"content\": \"Neural networks are inspired by biological neurons in the brain.\", \"metadata\": {\"source\": \"doc3\", \"page\": 1} } ] }" ``` ### 3.2 Expected Response Status: **200 OK** Response: *Empty or success confirmation* --- ## Step 4: Query Data (Before Restart – Baseline) ### 4.1 Query the vector store ```bash curl -X POST http://localhost:5000/vector-io/query \ -H "Content-Type: application/json" \ -d "{ \"vector_store_id\": \"$VS_ID\", \"query\": \"What is machine learning?\" }" | jq ``` ### 4.2 Expected Response ```json { "chunks": [ { "content": "Machine learning enables computers to learn from data without explicit programming.", "metadata": {"source": "doc2", "page": 1} }, { "content": "Neural networks are inspired by biological neurons in the brain.", "metadata": {"source": "doc3", "page": 1} } ], "scores": [0.85, 0.72] } ``` **Checkpoint:** Works correctly before restart. --- ## Step 5: Restart the Server (Critical Test) ### 5.1 Stop the server In the terminal where it’s running: ``` Ctrl + C ``` Wait for: ``` Shutting down... ``` ### 5.2 Restart the server ```bash llama stack run run.yaml --port 5000 ``` Wait for: ``` INFO: Started server process INFO: Application startup complete ``` The vector store cache is now empty, but data should persist. --- ## Step 6: Verify Vector Store Exists (After Restart) ### 6.1 List vector stores ```bash curl http://localhost:5000/v1/vector_stores | jq ``` ### 6.2 Expected Response ```json { "object": "list", "data": [ { "id": "vs_a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d", "name": "test-persistence-store", "status": "completed" } ] } ``` **Checkpoint:** Vector store should be listed. --- ## Step 7: Insert Data (After Restart – THE BUG TEST) ### 7.1 Insert new chunks ```bash curl -X POST http://localhost:5000/vector-io/insert \ -H "Content-Type: application/json" \ -d "{ \"vector_store_id\": \"$VS_ID\", \"chunks\": [ { \"content\": \"This chunk was inserted AFTER the server restart.\", \"metadata\": {\"source\": \"post-restart\", \"test\": true} } ] }" ``` ### 7.2 Expected Results **With Fix (Correct):** ``` Status: 200 OK Response: Success ``` **Without Fix (Bug):** ```json { "detail": "VectorStoreNotFoundError: Vector Store 'vs_a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d' not found." } ``` **Critical Test:** If insertion succeeds, the fix works. --- ## Step 8: Query Data (After Restart – Verification) ### 8.1 Query all data ```bash curl -X POST http://localhost:5000/vector-io/query \ -H "Content-Type: application/json" \ -d "{ \"vector_store_id\": \"$VS_ID\", \"query\": \"restart\" }" | jq ``` ### 8.2 Expected Response ```json { "chunks": [ { "content": "This chunk was inserted AFTER the server restart.", "metadata": {"source": "post-restart", "test": true} } ], "scores": [0.95] } ``` **Checkpoint:** Both old and new data are queryable. --- ## Step 9: Multiple Restart Test (Extra Verification) ### 9.1 Restart again ```bash Ctrl + C llama stack run run.yaml --port 5000 ``` ### 9.2 Query after restart ```bash curl -X POST http://localhost:5000/vector-io/query \ -H "Content-Type: application/json" \ -d "{ \"vector_store_id\": \"$VS_ID\", \"query\": \"programming\" }" | jq ``` **Expected:** Works correctly across multiple restarts. --------- Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com>	2025-11-09 00:05:00 -05:00
Ashwin Bharambe	f49cb0b717	chore: Stack server no longer depends on llama-stack-client (#4094) ... This dependency has been bothering folks for a long time (cc @leseb). We really needed it due to "library client" which is primarily used for our tests and is not a part of the Stack server. Anyone who needs to use the library client can certainly install `llama-stack-client` in their environment to make that work. Updated the notebook references to install `llama-stack-client` additionally when setting things up.	2025-11-07 09:54:09 -08:00
Sumanth Kamenani	e894e36eea	feat: add OpenAI-compatible Bedrock provider (#3748) ... Implements AWS Bedrock inference provider using OpenAI-compatible endpoint for Llama models available through Bedrock. Closes: #3410 ## What does this PR do? Adds AWS Bedrock as an inference provider using the OpenAI-compatible endpoint. This lets us use Bedrock models (GPT-OSS, Llama) through the standard llama-stack inference API. The implementation uses LiteLLM's OpenAI client under the hood, so it gets all the OpenAI compatibility features. The provider handles per-request API key overrides via headers. ## Test Plan **Tested the following scenarios:** - Non-streaming completion - basic request/response flow - Streaming completion - SSE streaming with chunked responses - Multi-turn conversations - context retention across turns - Tool calling - function calling with proper tool_calls format # Bedrock OpenAI-Compatible Provider - Test Results **Model:** `bedrock-inference/openai.gpt-oss-20b-1:0` --- ## Test 1: Model Listing **Request:** ```http GET /v1/models HTTP/1.1 ``` **Response:** ```http HTTP/1.1 200 OK Content-Type: application/json { "data": [ {"identifier": "bedrock-inference/openai.gpt-oss-20b-1:0", ...}, {"identifier": "bedrock-inference/openai.gpt-oss-40b-1:0", ...} ] } ``` --- ## Test 2: Non-Streaming Completion **Request:** ```http POST /v1/chat/completions HTTP/1.1 Content-Type: application/json { "model": "bedrock-inference/openai.gpt-oss-20b-1:0", "messages": [{"role": "user", "content": "Say 'Hello from Bedrock' and nothing else"}], "stream": false } ``` **Response:** ```http HTTP/1.1 200 OK Content-Type: application/json { "choices": [{ "finish_reason": "stop", "message": {"content": "...Hello from Bedrock"} }], "usage": {"prompt_tokens": 79, "completion_tokens": 50, "total_tokens": 129} } ``` --- ## Test 3: Streaming Completion **Request:** ```http POST /v1/chat/completions HTTP/1.1 Content-Type: application/json { "model": "bedrock-inference/openai.gpt-oss-20b-1:0", "messages": [{"role": "user", "content": "Count from 1 to 5"}], "stream": true } ``` **Response:** ```http HTTP/1.1 200 OK Content-Type: text/event-stream [6 SSE chunks received] Final content: "1, 2, 3, 4, 5" ``` --- ## Test 4: Error Handling - Invalid Model **Request:** ```http POST /v1/chat/completions HTTP/1.1 Content-Type: application/json { "model": "invalid-model-id", "messages": [{"role": "user", "content": "Hello"}], "stream": false } ``` **Response:** ```http HTTP/1.1 404 Not Found Content-Type: application/json { "detail": "Model 'invalid-model-id' not found. Use 'client.models.list()' to list available Models." } ``` --- ## Test 5: Multi-Turn Conversation **Request 1:** ```http POST /v1/chat/completions HTTP/1.1 { "messages": [{"role": "user", "content": "My name is Alice"}] } ``` **Response 1:** ```http HTTP/1.1 200 OK { "choices": [{ "message": {"content": "...Nice to meet you, Alice! How can I help you today?"} }] } ``` **Request 2 (with history):** ```http POST /v1/chat/completions HTTP/1.1 { "messages": [ {"role": "user", "content": "My name is Alice"}, {"role": "assistant", "content": "...Nice to meet you, Alice!..."}, {"role": "user", "content": "What is my name?"} ] } ``` **Response 2:** ```http HTTP/1.1 200 OK { "choices": [{ "message": {"content": "...Your name is Alice."} }], "usage": {"prompt_tokens": 183, "completion_tokens": 42} } ``` **Context retained across turns** --- ## Test 6: System Messages **Request:** ```http POST /v1/chat/completions HTTP/1.1 { "messages": [ {"role": "system", "content": "You are Shakespeare. Respond only in Shakespearean English."}, {"role": "user", "content": "Tell me about the weather"} ] } ``` **Response:** ```http HTTP/1.1 200 OK { "choices": [{ "message": {"content": "Lo! I heed thy request..."} }], "usage": {"completion_tokens": 813} } ``` --- ## Test 7: Tool Calling **Request:** ```http POST /v1/chat/completions HTTP/1.1 { "messages": [{"role": "user", "content": "What's the weather in San Francisco?"}], "tools": [{ "type": "function", "function": { "name": "get_weather", "parameters": {"type": "object", "properties": {"location": {"type": "string"}}} } }] } ``` **Response:** ```http HTTP/1.1 200 OK { "choices": [{ "finish_reason": "tool_calls", "message": { "tool_calls": [{ "function": {"name": "get_weather", "arguments": "{\"location\":\"San Francisco\"}"} }] } }] } ``` --- ## Test 8: Sampling Parameters **Request:** ```http POST /v1/chat/completions HTTP/1.1 { "messages": [{"role": "user", "content": "Say hello"}], "temperature": 0.7, "top_p": 0.9 } ``` **Response:** ```http HTTP/1.1 200 OK { "choices": [{ "message": {"content": "...Hello! 👋 How can I help you today?"} }] } ``` --- ## Test 9: Authentication Error Handling ### Subtest A: Invalid API Key **Request:** ```http POST /v1/chat/completions HTTP/1.1 x-llamastack-provider-data: {"aws_bedrock_api_key": "invalid-fake-key-12345"} {"model": "bedrock-inference/openai.gpt-oss-20b-1:0", ...} ``` **Response:** ```http HTTP/1.1 400 Bad Request { "detail": "Invalid value: Authentication failed: Error code: 401 - {'error': {'message': 'Invalid API Key format: Must start with pre-defined prefix', ...}}" } ``` --- ### Subtest B: Empty API Key (Fallback to Config) **Request:** ```http POST /v1/chat/completions HTTP/1.1 x-llamastack-provider-data: {"aws_bedrock_api_key": ""} {"model": "bedrock-inference/openai.gpt-oss-20b-1:0", ...} ``` **Response:** ```http HTTP/1.1 200 OK { "choices": [{ "message": {"content": "...Hello! How can I assist you today?"} }] } ``` **Fell back to config key** --- ### Subtest C: Malformed Token **Request:** ```http POST /v1/chat/completions HTTP/1.1 x-llamastack-provider-data: {"aws_bedrock_api_key": "not-a-valid-bedrock-token-format"} {"model": "bedrock-inference/openai.gpt-oss-20b-1:0", ...} ``` **Response:** ```http HTTP/1.1 400 Bad Request { "detail": "Invalid value: Authentication failed: Error code: 401 - {'error': {'message': 'Invalid API Key format: Must start with pre-defined prefix', ...}}" } ```	2025-11-06 17:18:18 -08:00
Ashwin Bharambe	bef1b044bd	refactor(passthrough): use AsyncOpenAI instead of AsyncLlamaStackClient (#4085) ... We'd like to remove the dependence of `llama-stack` on `llama-stack-client`. This is a necessary step. A few small cleanups - Enables `embeddings` now also - Remove ModelRegistryHelper dependency (unused) - Consolidate to auth_credential field via RemoteInferenceProviderConfig - Implement list_models() to fetch from downstream /v1/models ## Test Plan Tested using this script https://gist.github.com/ashwinb/6356463d10f989c0682ab3bff8589581 Output: ``` Listing models from downstream server... Available models: ['passthrough/ollama/nomic-embed-text:latest', 'passthrough/ollama/all-minilm:l6-v2', 'passthrough/ollama/llama3.2-vision:11b', 'passthrough/ollama/llama3.2-vision:latest', 'passthrough/ollama/llama-guard3:1b', 'passthrough/o llama/llama3.2:1b', 'passthrough/ollama/all-minilm:latest', 'passthrough/ollama/llama3.2:3b', 'passthrough/ollama/llama3.2:3b-instruct-fp16', 'passthrough/bedrock/meta.llama3-1-8b-instruct-v1:0', 'passthrough/bedrock/meta.llama3-1-70b-instruct -v1:0', 'passthrough/bedrock/meta.llama3-1-405b-instruct-v1:0', 'passthrough/sentence-transformers/nomic-ai/nomic-embed-text-v1.5'] Using LLM model: passthrough/ollama/llama3.2-vision:11b Making inference request... Response: 4. --- Testing streaming --- Streamed response: ChatCompletionChunk(id='chatcmpl-64', choices=[Choice(delta=ChoiceDelta(content='1', reasoning_content=None, refusal=None, role='assistant', tool_calls=None), finish_reason='', index=0, logprobs=None)], created=1762381674, m odel='passthrough/ollama/llama3.2-vision:11b', object='chat.completion.chunk', usage=None) ... 5ChatCompletionChunk(id='chatcmpl-64', choices=[Choice(delta=ChoiceDelta(content='', reasoning_content=None, refusal=None, role='assistant', tool_calls=None), finish_reason='stop', index=0, logprobs=None)], created=1762381674, model='passthrou gh/ollama/llama3.2-vision:11b', object='chat.completion.chunk', usage=None) ```	2025-11-05 18:15:11 -08:00
Wojciech-Rebisz	07c28cd519	fix: Avoid model_limits KeyError (#4060) ... # What does this PR do? It avoids model_limit KeyError while trying to get embedding models for Watsonx <!-- If resolving an issue, uncomment and update the line below --> Closes https://github.com/llamastack/llama-stack/issues/4059 ## 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.* --> Start server with watsonx distro: ```bash llama stack list-deps watsonx | xargs -L1 uv pip install uv run llama stack run watsonx ``` Run ```python client = LlamaStackClient(base_url=base_url) client.models.list() ``` Check if there is any embedding model available (currently there is not a single one)	2025-11-05 10:34:40 -08:00
Nathan Weinberg	62b3ad349a	fix: return to hardcoded model IDs for Vertex AI (#4041) ... # What does this PR do? partial revert of b67aef2 Vertex AI doesn't offer an endpoint for listing models from Google's Model Garden Return to hardcoded values until such an endpoint is available Closes #3988 ## Test Plan Server side, set up your Vertex AI env vars (`VERTEX_AI_PROJECT`, `VERTEX_AI_LOCATION`, and `GOOGLE_APPLICATION_CREDENTIALS`) and run the starter distribution ```bash $ llama stack list-deps starter | xargs -L1 uv pip install $ llama stack run starter ``` Client side, formerly broken cURL requests now working ```bash $ curl http://127.0.0.1:8321/v1/models | jq '.data | map(select(.provider_id == "vertexai"))' [ { "identifier": "vertexai/vertex_ai/gemini-2.0-flash", "provider_resource_id": "vertex_ai/gemini-2.0-flash", "provider_id": "vertexai", "type": "model", "metadata": {}, "model_type": "llm" }, { "identifier": "vertexai/vertex_ai/gemini-2.5-flash", "provider_resource_id": "vertex_ai/gemini-2.5-flash", "provider_id": "vertexai", "type": "model", "metadata": {}, "model_type": "llm" }, { "identifier": "vertexai/vertex_ai/gemini-2.5-pro", "provider_resource_id": "vertex_ai/gemini-2.5-pro", "provider_id": "vertexai", "type": "model", "metadata": {}, "model_type": "llm" } ] $ curl -fsS http://127.0.0.1:8321/v1/openai/v1/chat/completions -H "Content-Type: application/json" -d "{\"model\": \"vertexai/vertex_a i/gemini-2.5-flash\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}], \"max_tokens\": 128, \"temperature\": 0.0}" | jq { "id": "p8oIaYiQF8_PptQPo-GH8QQ", "choices": [ { "finish_reason": "stop", "index": 0, "logprobs": null, "message": { "content": "Hello there! How can I help you today?", "refusal": null, "role": "assistant", "annotations": null, "audio": null, "function_call": null, "tool_calls": null } } ], ... ``` Signed-off-by: Nathan Weinberg <nweinber@redhat.com>	2025-11-03 17:38:16 -08:00
Jiayi Ni	fa7699d2c3	feat: Add rerank API for NVIDIA Inference Provider (#3329) ... # What does this PR do? Add rerank API for NVIDIA Inference Provider. <!-- If resolving an issue, uncomment and update the line below --> Closes #3278 ## Test Plan Unit test: ``` pytest tests/unit/providers/nvidia/test_rerank_inference.py ``` Integration test: ``` pytest -s -v tests/integration/inference/test_rerank.py --stack-config="inference=nvidia" --rerank-model=nvidia/nvidia/nv-rerankqa-mistral-4b-v3 --env NVIDIA_API_KEY="" --env NVIDIA_BASE_URL="https://integrate.api.nvidia.com" ```	2025-10-30 21:42:09 -07:00
Ashwin Bharambe	da8f014b96	feat(models): list models available via provider_data header (#3968) ... ## Summary When users provide API keys via `X-LlamaStack-Provider-Data` header, `models.list()` now returns models they can access from those providers, not just pre-registered models from the registry. This complements the routing fix from f88416ef8 which enabled inference calls with `provider_id/model_id` format for unregistered models. Users can now discover which models are available to them before making inference requests. The implementation reuses `NeedsRequestProviderData.get_request_provider_data()` to validate credentials, then dynamically fetches models from providers without caching them since they're user-specific. Registry models take precedence to respect any pre-configured aliases. ## Test Script ```python #!/usr/bin/env python3 import json import os from openai import OpenAI # Test 1: Without provider_data header client = OpenAI(base_url="http://localhost:8321/v1/openai/v1", api_key="dummy") models = client.models.list() anthropic_without = [m.id for m in models.data if m.id and "anthropic" in m.id] print(f"Without header: {len(models.data)} models, {len(anthropic_without)} anthropic") # Test 2: With provider_data header containing Anthropic API key anthropic_api_key = os.environ["ANTHROPIC_API_KEY"] client_with_key = OpenAI( base_url="http://localhost:8321/v1/openai/v1", api_key="dummy", default_headers={ "X-LlamaStack-Provider-Data": json.dumps({"anthropic_api_key": anthropic_api_key}) } ) models_with_key = client_with_key.models.list() anthropic_with = [m.id for m in models_with_key.data if m.id and "anthropic" in m.id] print(f"With header: {len(models_with_key.data)} models, {len(anthropic_with)} anthropic") print(f"Anthropic models: {anthropic_with}") assert len(anthropic_with) > len(anthropic_without), "Should have more anthropic models with API key" print("\n✓ Test passed!") ``` Run with a stack that has Anthropic provider configured (but without API key in config): ```bash ANTHROPIC_API_KEY=sk-ant-... python test_provider_data_models.py ```	2025-10-29 14:03:03 -07:00
ehhuang	1f9d48cd54	feat: openai files provider (#3946) ... # What does this PR do? - Adds OpenAI files provider - Note that file content retrieval is pretty limited by `purpose` https://community.openai.com/t/file-uploads-error-why-can-t-i-download-files-with-purpose-user-data/1357013?utm_source=chatgpt.com ## Test Plan Modify run yaml to use openai files provider: ``` files: - provider_id: openai provider_type: remote::openai config: api_key: ${env.OPENAI_API_KEY:=} metadata_store: backend: sql_default table_name: openai_files_metadata # Then run files tests ❯ uv run --no-sync ./scripts/integration-tests.sh --stack-config server:ci-tests --inference-mode replay --setup ollama --suite base --pattern test_files ```	2025-10-28 16:25:03 -07:00
Ashwin Bharambe	94b0592240	fix(mypy): add type stubs and fix typing issues (#3938) ... Adds type stubs and fixes mypy errors for better type coverage. Changes: - Added type_checking dependency group with type stubs (torchtune, trl, etc.) - Added lm-format-enforcer to pre-commit hook - Created HFAutoModel Protocol for type-safe HuggingFace model handling - Added mypy.overrides for untyped libraries (torchtune, fairscale, etc.) - Fixed type issues in post-training providers, databricks, and api_recorder Note: ~1,200 errors remain in excluded files (see pyproject.toml exclude list). --------- Co-authored-by: Claude <noreply@anthropic.com>	2025-10-28 11:00:09 -07:00
Ashwin Bharambe	1d385b5b75	fix(mypy): resolve OpenAI SDK and provider type issues (#3936) ... ## Summary - Fix OpenAI SDK NotGiven/Omit type mismatches in embeddings calls - Fix incorrect OpenAIChatCompletionChunk import in vllm provider - Refactor to avoid type:ignore comments by using conditional kwargs ## Changes **openai_mixin.py (9 errors fixed):** - Build kwargs conditionally for embeddings.create() to avoid NotGiven/Omit mismatch - Only include parameters when they have actual values (not None) **gemini.py (9 errors fixed):** - Apply same conditional kwargs pattern - Add missing Any import **vllm.py (2 errors fixed):** - Use correct OpenAIChatCompletionChunk from llama_stack.apis.inference - Remove incorrect alias from openai package ## Technical Notes The OpenAI SDK has a type system quirk where `NOT_GIVEN` has type `NotGiven` but parameter signatures expect `Omit`. By only passing parameters with actual values, we avoid this mismatch entirely without needing `# type: ignore` comments. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude <noreply@anthropic.com>	2025-10-28 10:54:29 -07:00
Ashwin Bharambe	d009dc29f7	fix(mypy): resolve provider utility and testing type issues (#3935) ... Fixes mypy type errors in provider utilities and testing infrastructure: - `mcp.py`: Cast incompatible client types, wrap image data properly - `batches.py`: Rename walrus variable to avoid shadowing - `api_recorder.py`: Use cast for Pydantic field annotation No functional changes. --------- Co-authored-by: Claude <noreply@anthropic.com>	2025-10-28 10:37:27 -07:00
ehhuang	b7dd3f5c56	chore!: BREAKING CHANGE: vector_db_id -> vector_store_id (#3923) ... # What does this PR do? ## Test Plan CI vector_io tests will fail until next client sync passed with https://github.com/llamastack/llama-stack-client-python/pull/286 checked out locally	2025-10-27 14:26:06 -07:00
Matthew Farrellee	a9b00db421	feat: add provider data keys for Cerebras, Databricks, NVIDIA, and RunPod (#3734) ... # What does this PR do? add provider-data key passing support to Cerebras, Databricks, NVIDIA and RunPod also, added missing tests for Fireworks, Anthropic, Gemini, SambaNova, and vLLM addresses #3517 ## Test Plan ci w/ new tests --------- Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-10-27 13:09:35 -07:00
Ashwin Bharambe	471b1b248b	chore(package): migrate to src/ layout (#3920) ... Migrates package structure to src/ layout following Python packaging best practices. All code moved from `llama_stack/` to `src/llama_stack/`. Public API unchanged - imports remain `import llama_stack.*`. Updated build configs, pre-commit hooks, scripts, and GitHub workflows accordingly. All hooks pass, package builds cleanly. **Developer note**: Reinstall after pulling: `pip install -e .`	2025-10-27 12:02:21 -07:00