947 commits

Author	SHA1	Message	Date
IAN MILLER	98a5047f9d	feat(prompts): attach prompts to storage stores in run configs (#3893) ... # What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> This PR is responsible for attaching prompts to storage stores in run configs. It allows to specify prompts as stores in different distributions. The need of this functionality was initiated in #3514 > Note, #3514 is divided on three separate PRs. Current PR is the first of three. <!-- 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.* --> Manual testing and updated CI unit tests Prerequisites: 1. `uv run --with llama-stack llama stack list-deps starter | xargs -L1 uv pip install` 2. `llama stack run starter ` ``` INFO 2025-10-23 15:36:17,387 llama_stack.cli.stack.run:100 cli: Using run configuration: /Users/ianmiller/llama-stack/llama_stack/distributions/starter/run.yaml INFO 2025-10-23 15:36:17,423 llama_stack.cli.stack.run:157 cli: HTTPS enabled with certificates: Key: None Cert: None INFO 2025-10-23 15:36:17,424 llama_stack.cli.stack.run:159 cli: Listening on ['::', '0.0.0.0']:8321 INFO 2025-10-23 15:36:17,749 llama_stack.core.server.server:521 core::server: Run configuration: INFO 2025-10-23 15:36:17,756 llama_stack.core.server.server:524 core::server: apis: - agents - batches - datasetio - eval - files - inference - post_training - safety - scoring - tool_runtime - vector_io image_name: starter providers: agents: - config: persistence: agent_state: backend: kv_default namespace: agents responses: backend: sql_default max_write_queue_size: 10000 num_writers: 4 table_name: responses provider_id: meta-reference provider_type: inline::meta-reference batches: - config: kvstore: backend: kv_default namespace: batches provider_id: reference provider_type: inline::reference datasetio: - config: kvstore: backend: kv_default namespace: datasetio::huggingface provider_id: huggingface provider_type: remote::huggingface - config: kvstore: backend: kv_default namespace: datasetio::localfs provider_id: localfs provider_type: inline::localfs eval: - config: kvstore: backend: kv_default namespace: eval provider_id: meta-reference provider_type: inline::meta-reference files: - config: metadata_store: backend: sql_default table_name: files_metadata storage_dir: /Users/ianmiller/.llama/distributions/starter/files provider_id: meta-reference-files provider_type: inline::localfs inference: - config: api_key: '********' url: https://api.fireworks.ai/inference/v1 provider_id: fireworks provider_type: remote::fireworks - config: api_key: '********' url: https://api.together.xyz/v1 provider_id: together provider_type: remote::together - config: {} provider_id: bedrock provider_type: remote::bedrock - config: api_key: '********' base_url: https://api.openai.com/v1 provider_id: openai provider_type: remote::openai - config: api_key: '********' provider_id: anthropic provider_type: remote::anthropic - config: api_key: '********' provider_id: gemini provider_type: remote::gemini - config: api_key: '********' url: https://api.groq.com provider_id: groq provider_type: remote::groq - config: api_key: '********' url: https://api.sambanova.ai/v1 provider_id: sambanova provider_type: remote::sambanova - config: {} provider_id: sentence-transformers provider_type: inline::sentence-transformers post_training: - config: checkpoint_format: meta provider_id: torchtune-cpu provider_type: inline::torchtune-cpu safety: - config: excluded_categories: [] provider_id: llama-guard provider_type: inline::llama-guard - config: {} provider_id: code-scanner provider_type: inline::code-scanner scoring: - config: {} provider_id: basic provider_type: inline::basic - config: {} provider_id: llm-as-judge provider_type: inline::llm-as-judge - config: openai_api_key: '********' provider_id: braintrust provider_type: inline::braintrust tool_runtime: - config: api_key: '********' max_results: 3 provider_id: brave-search provider_type: remote::brave-search - config: api_key: '********' max_results: 3 provider_id: tavily-search provider_type: remote::tavily-search - config: {} provider_id: rag-runtime provider_type: inline::rag-runtime - config: {} provider_id: model-context-protocol provider_type: remote::model-context-protocol vector_io: - config: persistence: backend: kv_default namespace: vector_io::faiss provider_id: faiss provider_type: inline::faiss - config: db_path: /Users/ianmiller/.llama/distributions/starter/sqlite_vec.db persistence: backend: kv_default namespace: vector_io::sqlite_vec provider_id: sqlite-vec provider_type: inline::sqlite-vec registered_resources: benchmarks: [] datasets: [] models: [] scoring_fns: [] shields: [] tool_groups: - provider_id: tavily-search toolgroup_id: builtin::websearch - provider_id: rag-runtime toolgroup_id: builtin::rag vector_stores: [] server: port: 8321 storage: backends: kv_default: db_path: /Users/ianmiller/.llama/distributions/starter/kvstore.db type: kv_sqlite sql_default: db_path: /Users/ianmiller/.llama/distributions/starter/sql_store.db type: sql_sqlite stores: conversations: backend: sql_default table_name: openai_conversations inference: backend: sql_default max_write_queue_size: 10000 num_writers: 4 table_name: inference_store metadata: backend: kv_default namespace: registry prompts: backend: kv_default namespace: prompts telemetry: enabled: true vector_stores: default_embedding_model: model_id: nomic-ai/nomic-embed-text-v1.5 provider_id: sentence-transformers default_provider_id: faiss version: 2 INFO 2025-10-23 15:36:20,032 llama_stack.providers.utils.inference.inference_store:74 inference: Write queue disabled for SQLite to avoid concurrency issues WARNING 2025-10-23 15:36:20,422 llama_stack.providers.inline.telemetry.meta_reference.telemetry:84 telemetry: OTEL_EXPORTER_OTLP_ENDPOINT is not set, skipping telemetry INFO 2025-10-23 15:36:22,379 llama_stack.providers.utils.inference.openai_mixin:436 providers::utils: OpenAIInferenceAdapter.list_provider_model_ids() returned 105 models INFO 2025-10-23 15:36:22,703 uvicorn.error:84 uncategorized: Started server process [17328] INFO 2025-10-23 15:36:22,704 uvicorn.error:48 uncategorized: Waiting for application startup. INFO 2025-10-23 15:36:22,706 llama_stack.core.server.server:179 core::server: Starting up Llama Stack server (version: 0.3.0) INFO 2025-10-23 15:36:22,707 llama_stack.core.stack:470 core: starting registry refresh task INFO 2025-10-23 15:36:22,708 uvicorn.error:62 uncategorized: Application startup complete. INFO 2025-10-23 15:36:22,708 uvicorn.error:216 uncategorized: Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit) ``` As you can see, prompts are attached to stores in config Testing: 1. Create prompt: ``` curl -X POST http://localhost:8321/v1/prompts \ -H "Content-Type: application/json" \ -d '{ "prompt": "Hello {{name}}! You are working at {{company}}. Your role is {{role}} at {{company}}. Remember, {{name}}, to be {{tone}}.", "variables": ["name", "company", "role", "tone"] }' ``` `{"prompt":"Hello {{name}}! You are working at {{company}}. Your role is {{role}} at {{company}}. Remember, {{name}}, to be {{tone}}.","version":1,"prompt_id":"pmpt_a90e09e67acfe23776f2778c603eb6c17e139dab5f6e163f","variables":["name","company","role","tone"],"is_default":false}% ` 2. Get prompt: `curl -X GET http://localhost:8321/v1/prompts/pmpt_a90e09e67acfe23776f2778c603eb6c17e139dab5f6e163f` `{"prompt":"Hello {{name}}! You are working at {{company}}. Your role is {{role}} at {{company}}. Remember, {{name}}, to be {{tone}}.","version":1,"prompt_id":"pmpt_a90e09e67acfe23776f2778c603eb6c17e139dab5f6e163f","variables":["name","company","role","tone"],"is_default":false}% ` 3. Query sqlite KV storage to check created prompt: ``` sqlite> .mode column sqlite> .headers on sqlite> SELECT * FROM kvstore WHERE key LIKE 'prompts:v1:%'; key value expiration ------------------------------------------------------------ ------------------------------------------------------------ ---------- prompts:v1:pmpt_a90e09e67acfe23776f2778c603eb6c17e139dab5f6e {"prompt_id": "pmpt_a90e09e67acfe23776f2778c603eb6c17e139dab 163f:1 5f6e163f", "prompt": "Hello {{name}}! You are working at {{c ompany}}. Your role is {{role}} at {{company}}. Remember, {{ name}}, to be {{tone}}.", "version": 1, "variables": ["name" , "company", "role", "tone"], "is_default": false} prompts:v1:pmpt_a90e09e67acfe23776f2778c603eb6c17e139dab5f6e 1 163f:default sqlite> ```	2025-10-27 11:12:12 -07:00
Luis Tomas Bolivar	63422e5b36	fix!: Enhance response API support to not fail with tool calling (#3385) ... # What does this PR do? Introduces two main fixes to enhance the stability of Responses API when dealing with tool calling responses and structured outputs. ### Changes Made 1. It added OpenAIResponseOutputMessageMCPCall and ListTools to OpenAIResponseInput but https://github.com/llamastack/llama-stack/pull/3810 got merge that did the same in a different way. Still this PR does it in a way that keep the sync between OpenAIResponsesOutput and the allowed objects in OpenAIResponseInput. 2. Add protection in case self.ctx.response_format does not have type attribute BREAKING CHANGE: OpenAIResponseInput now uses OpenAIResponseOutput union type. This is semantically equivalent - all previously accepted types are still supported via the OpenAIResponseOutput union. This improves type consistency and maintainability.	2025-10-27 09:33:02 -07:00
Luis Tomas Bolivar	f18b5eb537	fix: Avoid BadRequestError due to invalid max_tokens (#3667) ... This patch ensures if max tokens is not defined, then is set to None instead of 0 when calling openai_chat_completion. This way some providers (like gemini) that cannot handle the `max_tokens = 0` will not fail Issue: #3666	2025-10-27 09:27:21 -07:00
ehhuang	509676641a	chore: update run configs (#3902) ... # What does this PR do? telemetry was deprecated ## Test Plan	2025-10-24 15:03:06 -07:00
ehhuang	2a1a813308	chore: update docs for telemetry api removal (#3900) ... # What does this PR do? Telemetry is no longer an API/provider. ## Test Plan	2025-10-24 13:57:28 -07:00
Francisco Arceo	4566eebe05	feat: Add static file import system for docs (#3882) ... # What does this PR do? Add static file import system for docs - Use `remark-code-import` plugin to embed code at build time - Support importing Python code with syntax highlighting using `raw-loader` + `ReactMarkdown` One caveat is that currently when embedding markdown with code used the syntax highlighting isn't behaving but I'll investigate that in a follow up. ## Test Plan Python Example: <img width="1372" height="995" alt="Screenshot 2025-10-23 at 9 22 18 PM" src="https://github.com/user-attachments/assets/656d2c78-4d9b-45a4-bd5e-3f8490352b85" /> Markdown example: <img width="1496" height="1070" alt="Screenshot 2025-10-23 at 9 22 38 PM" src="https://github.com/user-attachments/assets/6c0a07ec-ff7c-45aa-b05f-8c46acd4445c" /> --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>	2025-10-24 14:01:33 -04:00
ehhuang	9916cb3b17	chore: support default model in moderations API (#3890) ... # What does this PR do? https://platform.openai.com/docs/api-reference/moderations supports optional model parameter. This PR adds support for using moderations API with model=None if a default shield id is provided via safety config. ## Test Plan added tests manual test: ``` > SAFETY_MODEL='together/meta-llama/Llama-Guard-4-12B' uv run llama stack run starter > curl http://localhost:8321/v1/moderations \ -H "Content-Type: application/json" \ -d '{ "input": [ "hello" ] }' ```	2025-10-23 16:03:53 -07:00
Ashwin Bharambe	658fb2c777	refactor(k8s): update run configs to v2 storage and registered_resources structure ... Migrates k8s run configs to match the updated run configs - Replace storage.references with storage.stores - Wrap resources under registered_resources section - Update provider configs to use persistence with namespace/backend - Add telemetry and vector_stores top-level sections - Simplify agent/files metadata store configuration	2025-10-22 15:33:50 -07:00
dependabot[bot]	8885cea8d7	fix(conversations)!: update Conversations API definitions (was: bump openai from 1.107.0 to 2.5.0) (#3847) ... Bumps [openai](https://github.com/openai/openai-python) from 1.107.0 to 2.5.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/openai/openai-python/releases">openai's releases</a>.</em></p> <blockquote> <h2>v2.5.0</h2> <h2>2.5.0 (2025-10-17)</h2> <p>Full Changelog: <a href="https://github.com/openai/openai-python/compare/v2.4.0...v2.5.0">v2.4.0...v2.5.0</a></p> <h3>Features</h3> <ul> <li><strong>api:</strong> api update (<a href="8b280d57d6">8b280d5</a>)</li> </ul> <h3>Chores</h3> <ul> <li>bump <code>httpx-aiohttp</code> version to 0.1.9 (<a href="67f2f0afe5">67f2f0a</a>)</li> </ul> <h2>v2.4.0</h2> <h2>2.4.0 (2025-10-16)</h2> <p>Full Changelog: <a href="https://github.com/openai/openai-python/compare/v2.3.0...v2.4.0">v2.3.0...v2.4.0</a></p> <h3>Features</h3> <ul> <li><strong>api:</strong> Add support for gpt-4o-transcribe-diarize on audio/transcriptions endpoint (<a href="bdbe9b8f44">bdbe9b8</a>)</li> </ul> <h3>Chores</h3> <ul> <li>fix dangling comment (<a href="da14e99606">da14e99</a>)</li> <li><strong>internal:</strong> detect missing future annotations with ruff (<a href="2672b8f072">2672b8f</a>)</li> </ul> <h2>v2.3.0</h2> <h2>2.3.0 (2025-10-10)</h2> <p>Full Changelog: <a href="https://github.com/openai/openai-python/compare/v2.2.0...v2.3.0">v2.2.0...v2.3.0</a></p> <h3>Features</h3> <ul> <li><strong>api:</strong> comparison filter in/not in (<a href="aa49f626a6">aa49f62</a>)</li> </ul> <h3>Chores</h3> <ul> <li><strong>package:</strong> bump jiter to &gt;=0.10.0 to support Python 3.14 (<a href="https://redirect.github.com/openai/openai-python/issues/2618">#2618</a>) (<a href="aa445cab5c">aa445ca</a>)</li> </ul> <h2>v2.2.0</h2> <h2>2.2.0 (2025-10-06)</h2> <p>Full Changelog: <a href="https://github.com/openai/openai-python/compare/v2.1.0...v2.2.0">v2.1.0...v2.2.0</a></p> <h3>Features</h3> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/openai/openai-python/blob/main/CHANGELOG.md">openai's changelog</a>.</em></p> <blockquote> <h2>2.5.0 (2025-10-17)</h2> <p>Full Changelog: <a href="https://github.com/openai/openai-python/compare/v2.4.0...v2.5.0">v2.4.0...v2.5.0</a></p> <h3>Features</h3> <ul> <li><strong>api:</strong> api update (<a href="8b280d57d6">8b280d5</a>)</li> </ul> <h3>Chores</h3> <ul> <li>bump <code>httpx-aiohttp</code> version to 0.1.9 (<a href="67f2f0afe5">67f2f0a</a>)</li> </ul> <h2>2.4.0 (2025-10-16)</h2> <p>Full Changelog: <a href="https://github.com/openai/openai-python/compare/v2.3.0...v2.4.0">v2.3.0...v2.4.0</a></p> <h3>Features</h3> <ul> <li><strong>api:</strong> Add support for gpt-4o-transcribe-diarize on audio/transcriptions endpoint (<a href="bdbe9b8f44">bdbe9b8</a>)</li> </ul> <h3>Chores</h3> <ul> <li>fix dangling comment (<a href="da14e99606">da14e99</a>)</li> <li><strong>internal:</strong> detect missing future annotations with ruff (<a href="2672b8f072">2672b8f</a>)</li> </ul> <h2>2.3.0 (2025-10-10)</h2> <p>Full Changelog: <a href="https://github.com/openai/openai-python/compare/v2.2.0...v2.3.0">v2.2.0...v2.3.0</a></p> <h3>Features</h3> <ul> <li><strong>api:</strong> comparison filter in/not in (<a href="aa49f626a6">aa49f62</a>)</li> </ul> <h3>Chores</h3> <ul> <li><strong>package:</strong> bump jiter to &gt;=0.10.0 to support Python 3.14 (<a href="https://redirect.github.com/openai/openai-python/issues/2618">#2618</a>) (<a href="aa445cab5c">aa445ca</a>)</li> </ul> <h2>2.2.0 (2025-10-06)</h2> <p>Full Changelog: <a href="https://github.com/openai/openai-python/compare/v2.1.0...v2.2.0">v2.1.0...v2.2.0</a></p> <h3>Features</h3> <ul> <li><strong>api:</strong> dev day 2025 launches (<a href="38ac0093eb">38ac009</a>)</li> </ul> <h3>Bug Fixes</h3> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="513ae76253"><code>513ae76</code></a> release: 2.5.0 (<a href="https://redirect.github.com/openai/openai-python/issues/2694">#2694</a>)</li> <li><a href="ebf32212f7"><code>ebf3221</code></a> release: 2.4.0</li> <li><a href="e043d7b164"><code>e043d7b</code></a> chore: fix dangling comment</li> <li><a href="25cbb74f83"><code>25cbb74</code></a> feat(api): Add support for gpt-4o-transcribe-diarize on audio/transcriptions ...</li> <li><a href="8cdfd0650e"><code>8cdfd06</code></a> codegen metadata</li> <li><a href="d5c64434b7"><code>d5c6443</code></a> codegen metadata</li> <li><a href="b20a9e7b81"><code>b20a9e7</code></a> chore(internal): detect missing future annotations with ruff</li> <li><a href="e5f93f5dae"><code>e5f93f5</code></a> release: 2.3.0</li> <li><a href="044878859c"><code>0448788</code></a> feat(api): comparison filter in/not in</li> <li><a href="85a91ade61"><code>85a91ad</code></a> chore(package): bump jiter to &gt;=0.10.0 to support Python 3.14 (<a href="https://redirect.github.com/openai/openai-python/issues/2618">#2618</a>)</li> <li>Additional commits viewable in <a href="https://github.com/openai/openai-python/compare/v1.107.0...v2.5.0">compare view</a></li> </ul> </details> <br /> [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) </details> --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-10-22 12:32:48 -07:00
Jiayi Ni	bb1ebb3c6b	feat: Add rerank models and rerank API change (#3831) ... # What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> - Extend the model type to include rerank models. - Implement `rerank()` method in inference router. - Add `rerank_model_list` to `OpenAIMixin` to enable providers to register and identify rerank models - Update documentation. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> ``` pytest tests/unit/providers/utils/inference/test_openai_mixin.py ```	2025-10-22 12:02:28 -07:00
Francisco Arceo	53c20f6113	feat: Adding Demo script (#3870) ... # What does this PR do? Updated quickstart `demo_script.py` to use OpenAI APIs, which is simply: ```python import io, requests from openai import OpenAI url="https://www.paulgraham.com/greatwork.html" client = OpenAI(base_url="http://localhost:8321/v1/", api_key="none") vs = client.vector_stores.create() response = requests.get(url) pseudo_file = io.BytesIO(str(response.content).encode('utf-8')) uploaded_file = client.files.create(file=(url, pseudo_file, "text/html"), purpose="assistants") client.vector_stores.files.create(vector_store_id=vs.id, file_id=uploaded_file.id) resp = client.responses.create( model="openai/gpt-4o", input="How do you do great work? Use the existing knowledge_search tool.", tools=[{"type": "file_search", "vector_store_ids": [vs.id]}], include=["file_search_call.results"], ) print(resp) ``` <!-- 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.* --> --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>	2025-10-21 21:31:21 -04:00
Alexey Rybak	4c718523fa	docs: fix the building distro file (#3880) ... # What does this PR do? * Fixes the doc server build (which expects a blank line after imports) ## Test Plan * `cd docs && npm run build`	2025-10-21 14:26:35 -07:00
ehhuang	1ec7216c3f	chore: update quick_start (#3878) ... # What does this PR do? ## Test Plan	2025-10-21 11:33:23 -07:00
Ashwin Bharambe	bd3c473208	revert: "chore(cleanup)!: remove tool_runtime.rag_tool" (#3877) ... Reverts llamastack/llama-stack#3871 This PR broke RAG (even from Responses -- there _is_ a dependency)	2025-10-21 11:22:06 -07:00
ehhuang	eb3e9b85f9	chore: update getting_started (#3875) ... # What does this PR do? ## Test Plan	2025-10-21 11:09:45 -07:00
Ashwin Bharambe	0e96279bee	chore(cleanup)!: remove tool_runtime.rag_tool (#3871) ... Kill the `builtin::rag` tool group completely since it is no longer targeted. We use the Responses implementation for knowledge_search which uses the `openai_vector_stores` pathway. --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2025-10-20 22:26:21 -07:00
Ashwin Bharambe	122de785c4	chore(cleanup)!: kill vector_db references as far as possible (#3864) ... There should not be "vector db" anywhere.	2025-10-20 20:06:16 -07:00
Ashwin Bharambe	483d53cc37	feat(stainless): add stainless source of truth config (#3860) ... Source of truth for Stainless should be in this repository. This was long due.	2025-10-20 14:32:20 -07:00
Francisco Arceo	48581bf651	chore: Updating how default embedding model is set in stack (#3818) ... # What does this PR do? Refactor setting default vector store provider and embedding model to use an optional `vector_stores` config in the `StackRunConfig` and clean up code to do so (had to add back in some pieces of VectorDB). Also added remote Qdrant and Weaviate to starter distro (based on other PR where inference providers were added for UX). New config is simply (default for Starter distro): ```yaml vector_stores: default_provider_id: faiss default_embedding_model: provider_id: sentence-transformers model_id: nomic-ai/nomic-embed-text-v1.5 ``` ## Test Plan CI and Unit tests. --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-10-20 14:22:45 -07:00
Ashwin Bharambe	2c43285e22	feat(stores)!: use backend storage references instead of configs (#3697) ... **This PR changes configurations in a backward incompatible way.** Run configs today repeat full SQLite/Postgres snippets everywhere a store is needed, which means duplicated credentials, extra connection pools, and lots of drift between files. This PR introduces named storage backends so the stack and providers can share a single catalog and reference those backends by name. ## Key Changes - Add `storage.backends` to `StackRunConfig`, register each KV/SQL backend once at startup, and validate that references point to the right family. - Move server stores under `storage.stores` with lightweight references (backend + namespace/table) instead of full configs. - Update every provider/config/doc to use the new reference style; docs/codegen now surface the simplified YAML. ## Migration Before: ```yaml metadata_store: type: sqlite db_path: ~/.llama/distributions/foo/registry.db inference_store: type: postgres host: ${env.POSTGRES_HOST} port: ${env.POSTGRES_PORT} db: ${env.POSTGRES_DB} user: ${env.POSTGRES_USER} password: ${env.POSTGRES_PASSWORD} conversations_store: type: postgres host: ${env.POSTGRES_HOST} port: ${env.POSTGRES_PORT} db: ${env.POSTGRES_DB} user: ${env.POSTGRES_USER} password: ${env.POSTGRES_PASSWORD} ``` After: ```yaml storage: backends: kv_default: type: kv_sqlite db_path: ~/.llama/distributions/foo/kvstore.db sql_default: type: sql_postgres host: ${env.POSTGRES_HOST} port: ${env.POSTGRES_PORT} db: ${env.POSTGRES_DB} user: ${env.POSTGRES_USER} password: ${env.POSTGRES_PASSWORD} stores: metadata: backend: kv_default namespace: registry inference: backend: sql_default table_name: inference_store max_write_queue_size: 10000 num_writers: 4 conversations: backend: sql_default table_name: openai_conversations ``` Provider configs follow the same pattern—for example, a Chroma vector adapter switches from: ```yaml providers: vector_io: - provider_id: chromadb provider_type: remote::chromadb config: url: ${env.CHROMADB_URL} kvstore: type: sqlite db_path: ~/.llama/distributions/foo/chroma.db ``` to: ```yaml providers: vector_io: - provider_id: chromadb provider_type: remote::chromadb config: url: ${env.CHROMADB_URL} persistence: backend: kv_default namespace: vector_io::chroma_remote ``` Once the backends are declared, everything else just points at them, so rotating credentials or swapping to Postgres happens in one place and the stack reuses a single connection pool.	2025-10-20 13:20:09 -07:00
Shabana Baig	add64e8e2a	feat: Add instructions parameter in response object (#3741) ... # Problem The current inline provider appends the user provided instructions to messages as a system prompt, but the returned response object does not contain the instructions field (as specified in the OpenAI responses spec). # What does this PR do? This pull request adds the instruction field to the response object definition and updates the inline provider. It also ensures that instructions from previous response is not carried over to the next response (as specified in the openAI spec). Closes #[3566](https://github.com/llamastack/llama-stack/issues/3566) ## Test Plan - Tested manually for change in model response w.r.t supplied instructions field. - Added unit test to check that the instructions from previous response is not carried over to the next response. - Added integration tests to check instructions parameter in the returned response object. - Added new recordings for the integration tests. --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2025-10-20 13:10:37 -07:00
ehhuang	359df3a37c	chore: update doc (#3857) ... # What does this PR do? follows https://github.com/llamastack/llama-stack/pull/3839 ## Test Plan	2025-10-20 10:33:21 -07:00
ehhuang	21772de5d3	chore: use dockerfile for building containers (#3839) ... # What does this PR do? relates to #2878 We introduce a Containerfile which is used to replaced the `llama stack build` command (removal in a separate PR). ``` llama stack build --distro starter --image-type venv --run ``` is replaced by ``` llama stack list-deps starter | xargs -L1 uv pip install llama stack run starter ``` - See the updated workflow files for e2e workflow. ## Test Plan CI ``` ❯ docker build . -f docker/Dockerfile --build-arg DISTRO_NAME=starter --build-arg INSTALL_MODE=editable --tag test_starter ❯ docker run -p 8321:8321 test_starter ❯ curl http://localhost:8321/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-4o-mini", "messages": [ { "role": "user", "content": "Hello!" } ] }' ``` --- [//]: # (BEGIN SAPLING FOOTER) Stack created with [Sapling](https://sapling-scm.com). Best reviewed with [ReviewStack](https://reviewstack.dev/llamastack/llama-stack/pull/3839). * #3855 * __->__ #3839	2025-10-20 10:23:01 -07:00
Charlie Doern	573e783ff0	docs: fix sidebar of Detailed Tutorial (#3856) ... # What does this PR do? the sidebar currently has an extra `ii. Run the Script` because its incorrectly put into the doc as an H3 not an H4 (like the other ones) <img width="239" height="218" alt="Screenshot 2025-10-20 at 1 04 54 PM" src="https://github.com/user-attachments/assets/eb8cb26e-7ea9-4b61-9101-d64965b39647" /> Fix this which will update the sidebar Signed-off-by: Charlie Doern <cdoern@redhat.com>	2025-10-20 13:10:50 -04:00
Charlie Doern	b11bcfde11	refactor(build): rework CLI commands and build process (1/2) (#2974) ... # What does this PR do? This PR does a few things outlined in #2878 namely: 1. adds `llama stack list-deps` a command which simply takes the build logic and instead of executing one of the `build_...` scripts, it displays all of the providers' dependencies using the `module` and `uv`. 2. deprecated `llama stack build` in favor of `llama stack list-deps` 3. updates all tests to use `list-deps` alongside `build`. PR 2/2 will migrate `llama stack run`'s default behavior to be `llama stack build --run` and use the new `list-deps` command under the hood before running the server. examples of `llama stack list-deps starter` ``` llama stack list-deps starter --format json { "name": "starter", "description": "Quick start template for running Llama Stack with several popular providers. This distribution is intended for CPU-only environments.", "apis": [ { "api": "inference", "provider": "remote::cerebras" }, { "api": "inference", "provider": "remote::ollama" }, { "api": "inference", "provider": "remote::vllm" }, { "api": "inference", "provider": "remote::tgi" }, { "api": "inference", "provider": "remote::fireworks" }, { "api": "inference", "provider": "remote::together" }, { "api": "inference", "provider": "remote::bedrock" }, { "api": "inference", "provider": "remote::nvidia" }, { "api": "inference", "provider": "remote::openai" }, { "api": "inference", "provider": "remote::anthropic" }, { "api": "inference", "provider": "remote::gemini" }, { "api": "inference", "provider": "remote::vertexai" }, { "api": "inference", "provider": "remote::groq" }, { "api": "inference", "provider": "remote::sambanova" }, { "api": "inference", "provider": "remote::azure" }, { "api": "inference", "provider": "inline::sentence-transformers" }, { "api": "vector_io", "provider": "inline::faiss" }, { "api": "vector_io", "provider": "inline::sqlite-vec" }, { "api": "vector_io", "provider": "inline::milvus" }, { "api": "vector_io", "provider": "remote::chromadb" }, { "api": "vector_io", "provider": "remote::pgvector" }, { "api": "files", "provider": "inline::localfs" }, { "api": "safety", "provider": "inline::llama-guard" }, { "api": "safety", "provider": "inline::code-scanner" }, { "api": "agents", "provider": "inline::meta-reference" }, { "api": "telemetry", "provider": "inline::meta-reference" }, { "api": "post_training", "provider": "inline::torchtune-cpu" }, { "api": "eval", "provider": "inline::meta-reference" }, { "api": "datasetio", "provider": "remote::huggingface" }, { "api": "datasetio", "provider": "inline::localfs" }, { "api": "scoring", "provider": "inline::basic" }, { "api": "scoring", "provider": "inline::llm-as-judge" }, { "api": "scoring", "provider": "inline::braintrust" }, { "api": "tool_runtime", "provider": "remote::brave-search" }, { "api": "tool_runtime", "provider": "remote::tavily-search" }, { "api": "tool_runtime", "provider": "inline::rag-runtime" }, { "api": "tool_runtime", "provider": "remote::model-context-protocol" }, { "api": "batches", "provider": "inline::reference" } ], "pip_dependencies": [ "pandas", "opentelemetry-exporter-otlp-proto-http", "matplotlib", "opentelemetry-sdk", "sentence-transformers", "datasets", "pymilvus[milvus-lite]>=2.4.10", "codeshield", "scipy", "torchvision", "tree_sitter", "h11>=0.16.0", "aiohttp", "pymongo", "tqdm", "pythainlp", "pillow", "torch", "emoji", "grpcio>=1.67.1,<1.71.0", "fireworks-ai", "langdetect", "psycopg2-binary", "asyncpg", "redis", "together", "torchao>=0.12.0", "openai", "sentencepiece", "aiosqlite", "google-cloud-aiplatform", "faiss-cpu", "numpy", "sqlite-vec", "nltk", "scikit-learn", "mcp>=1.8.1", "transformers", "boto3", "huggingface_hub", "ollama", "autoevals", "sqlalchemy[asyncio]", "torchtune>=0.5.0", "chromadb-client", "pypdf", "requests", "anthropic", "chardet", "aiosqlite", "fastapi", "fire", "httpx", "uvicorn", "opentelemetry-sdk", "opentelemetry-exporter-otlp-proto-http" ] } ``` <img width="1500" height="420" alt="Screenshot 2025-10-16 at 5 53 03 PM" src="https://github.com/user-attachments/assets/765929fb-93e2-44d7-9c3d-8918b70fc721" /> --------- Signed-off-by: Charlie Doern <cdoern@redhat.com>	2025-10-17 19:52:14 -07:00
Alexey Rybak	224c99560c	docs: update docstrings for better formatting (#3838) ... # What does this PR do? Updates docstrings for Conversations and Eval APIs to render better in the docs nav sidebar. Before: <img width="363" height="233" alt="Screenshot 2025-10-17 at 9 52 17 AM" src="https://github.com/user-attachments/assets/3a77f9e3-3b03-43ae-8584-a21d1f44d54d" /> After: <img width="410" height="206" alt="Screenshot 2025-10-17 at 9 52 11 AM" src="https://github.com/user-attachments/assets/fa5d428d-2bde-4453-84fd-9aceebe712e8" /> ## Test Plan * Manual testing	2025-10-17 10:41:50 -07:00
Alexey Rybak	c9f0bebcb7	chore: update API leveling docs with deprecation flag (#3837) ... # What does this PR do? Adds information on the `deprecated=True` flags to the documentation for extra clarity. ## Test Plan * Manual testing	2025-10-17 10:17:58 -07:00
Charlie Doern	f22aaef42f	chore!: remove telemetry API usage (#3815) ... # What does this PR do? remove telemetry as a providable API from the codebase. This includes removing it from generated distributions but also the provider registry, the router, etc since `setup_logger` is tied pretty strictly to `Api.telemetry` being in impls we still need an "instantiated provider" in our implementations. However it should not be auto-routed or provided. So in validate_and_prepare_providers (called from resolve_impls) I made it so that if run_config.telemetry.enabled, we set up the meta-reference "provider" internally to be used so that log_event will work when called. This is the neatest way I think we can remove telemetry from the provider configs but also not need to rip apart the whole "telemetry is a provider" logic just yet, but we can do it internally later without disrupting users. so telemetry is removed from the registry such that if a user puts `telemetry:` as an API in their build/run config it will err out, but can still be used by us internally as we go through this transition. relates to #3806 Signed-off-by: Charlie Doern <cdoern@redhat.com>	2025-10-16 10:39:32 -07:00
Bill Murdock	c19eb9854d	docs: Document known limitations of Responses (#3776) ... # What does this PR do? Adds a subpage of the OpenAI compatibility page in the documentation. This subpage documents known limitations of the Responses API. <!-- If resolving an issue, uncomment and update the line below --> Closes #3575 --------- Signed-off-by: Bill Murdock <bmurdock@redhat.com>	2025-10-16 10:26:23 -07:00
slekkala1	99141c29b1	feat: Add responses and safety impl extra_body (#3781) ... # What does this PR do? Have closed the previous PR due to merge conflicts with multiple PRs Addressed all comments from https://github.com/llamastack/llama-stack/pull/3768 (sorry for carrying over to this one) ## Test Plan Added UTs and integration tests	2025-10-15 15:01:37 -07:00
ehhuang	6ba9db3929	chore!: BREAKING CHANGE: remove sqlite from telemetry config (#3808) ... # What does this PR do? - Removed sqlite sink from telemetry config. - Removed related code - Updated doc related to telemetry ## Test Plan CI	2025-10-15 14:24:45 -07:00
Ashwin Bharambe	e9b4278a51	feat(responses)!: improve responses + conversations implementations (#3810) ... This PR updates the Conversation item related types and improves a couple critical parts of the implemenation: - it creates a streaming output item for the final assistant message output by the model. until now we only added content parts and included that message in the final response. - rewrites the conversation update code completely to account for items other than messages (tool calls, outputs, etc.) ## Test Plan Used the test script from https://github.com/llamastack/llama-stack-client-python/pull/281 for this ``` TEST_API_BASE_URL=http://localhost:8321/v1 \ pytest tests/integration/test_agent_turn_step_events.py::test_client_side_function_tool -xvs ```	2025-10-15 09:36:11 -07:00
Francisco Arceo	ef4bc70bbe	feat: Enable setting a default embedding model in the stack (#3803) ... # What does this PR do? Enables automatic embedding model detection for vector stores and by using a `default_configured` boolean that can be defined in the `run.yaml`. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan - Unit tests - Integration tests - Simple example below: Spin up the stack: ```bash uv run llama stack build --distro starter --image-type venv --run ``` Then test with OpenAI's client: ```python from openai import OpenAI client = OpenAI(base_url="http://localhost:8321/v1/", api_key="none") vs = client.vector_stores.create() ``` Previously you needed: ```python vs = client.vector_stores.create( extra_body={ "embedding_model": "sentence-transformers/all-MiniLM-L6-v2", "embedding_dimension": 384, } ) ``` The `extra_body` is now unnecessary. --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>	2025-10-14 18:25:13 -07:00
ehhuang	866c13cdc2	chore(api)!: BREAKING CHANGE: remove ALL telemetry APIs (#3740) ... # What does this PR do? As discussed on discord, we do not need to reinvent the wheel for telemetry. Instead we'll lean into the canonical OTEL stack. Logs/traces/metrics will still be sent via OTEL - they just won't be stored on, queried through Stack. This is the first of many PRs to remove telemetry API from Stack. 1) removed webmethod decorators to remove from API spec 2) removed tests as @iamemilio is adding them on otel directly. ## Test Plan	2025-10-14 13:48:40 -07:00
IAN MILLER	007efa6eb5	refactor: replace default all-MiniLM-L6-v2 embedding model by nomic-embed-text-v1.5 in Llama Stack (#3183) ... # What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> The purpose of this PR is to replace the Llama Stack's default embedding model by nomic-embed-text-v1.5. These are the key reasons why Llama Stack community decided to switch from all-MiniLM-L6-v2 to nomic-embed-text-v1.5: 1. The training data for [all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2#training-data) includes a lot of data sets with various licensing terms, so it is tricky to know when/whether it is appropriate to use this model for commercial applications. 2. The model is not particularly competitive on major benchmarks. For example, if you look at the [MTEB Leaderboard](https://huggingface.co/spaces/mteb/leaderboard) and click on Miscellaneous/BEIR to see English information retrieval accuracy, you see that the top of the leaderboard is dominated by enormous models but also that there are many, many models of relatively modest size whith much higher Retrieval scores. If you want to look closely at the data, I recommend clicking "Download Table" because it is easier to browse that way. More discussion info can be founded [here](https://github.com/llamastack/llama-stack/issues/2418) <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Closes #2418 ## 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.* --> 1. Run `./scripts/unit-tests.sh` 2. Integration tests via CI wokrflow --------- Signed-off-by: Sébastien Han <seb@redhat.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com> Co-authored-by: Sébastien Han <seb@redhat.com>	2025-10-14 10:44:20 -04:00
Ashwin Bharambe	ecc8a554d2	feat(api)!: support extra_body to embeddings and vector_stores APIs (#3794) ... Applies the same pattern from https://github.com/llamastack/llama-stack/pull/3777 to embeddings and vector_stores.create() endpoints. This should _not_ be a breaking change since (a) our tests were already using the `extra_body` parameter when passing in to the backend (b) but the backend probably wasn't extracting the parameters correctly. This PR will fix that. Updated APIs: `openai_embeddings(), openai_create_vector_store(), openai_create_vector_store_file_batch()`	2025-10-12 19:01:52 -07:00
slekkala1	3bb6ef351b	chore!: Safety api refactoring to use OpenAIMessageParam (#3796) ... # What does this PR do? Remove usage of deprecated `Message` from Safety apis ## Test Plan CI	2025-10-12 08:01:00 -07:00
Ashwin Bharambe	7c63aebd64	feat(responses)!: add reasoning and annotation added events (#3793) ... Implements missing streaming events from OpenAI Responses API spec: - reasoning text/summary events for o1/o3 models, - refusal events for safety moderation - annotation events for citations, - and file search streaming events. Added optional reasoning_content field to chat completion chunks to support non-standard provider extensions. **NOTE:** OpenAI does _not_ fill reasoning_content when users use the chat_completion APIs. This means there is no way for us to implement Responses (with reasoning) by using OpenAI chat completions! We'd need to transparently punt to OpenAI's responses endpoints if we wish to do that. For others though (vLLM, etc.) we can use it. ## Test Plan File search streaming test passes: ``` ./scripts/integration-tests.sh --stack-config server:ci-tests \ --suite responses --setup gpt --inference-mode replay --pattern test_response_file_search_streaming_events ``` Need more complex setup and validation for reasoning tests (need a vLLM powered OSS model maybe gpt-oss which can return reasoning_content). I will do that in a followup PR.	2025-10-11 16:47:14 -07:00
Francisco Arceo	a165b8b5bb	chore!: BREAKING CHANGE removing VectorDB APIs (#3774) ... # What does this PR do? Removes VectorDBs from API surface and our tests. Moves tests to Vector Stores. <!-- 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.* --> --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-10-11 14:07:08 -07:00
ehhuang	06e4cd8e02	feat(api)!: BREAKING CHANGE: support passing extra_body through to providers (#3777) ... # What does this PR do? Allows passing through extra_body parameters to inference providers. With this, we removed the 2 vllm-specific parameters from completions API into `extra_body`. Before/After <img width="1883" height="324" alt="image" src="https://github.com/user-attachments/assets/acb27c08-c748-46c9-b1da-0de64e9908a1" /> closes #2720 ## Test Plan CI and added new test ``` ❯ uv run pytest -s -v tests/integration/ --stack-config=server:starter --inference-mode=record -k 'not( builtin_tool or safety_with_image or code_interpreter or test_rag ) and test_openai_completion_guided_choice' --setup=vllm --suite=base --color=yes Uninstalled 3 packages in 125ms Installed 3 packages in 19ms INFO 2025-10-10 14:29:54,317 tests.integration.conftest:118 tests: Applying setup 'vllm' for suite base INFO 2025-10-10 14:29:54,331 tests.integration.conftest:47 tests: Test stack config type: server (stack_config=server:starter) ============================================================================================================== test session starts ============================================================================================================== platform darwin -- Python 3.12.11, pytest-8.4.2, pluggy-1.6.0 -- /Users/erichuang/projects/llama-stack-1/.venv/bin/python cachedir: .pytest_cache metadata: {'Python': '3.12.11', 'Platform': 'macOS-15.6.1-arm64-arm-64bit', 'Packages': {'pytest': '8.4.2', 'pluggy': '1.6.0'}, 'Plugins': {'anyio': '4.9.0', 'html': '4.1.1', 'socket': '0.7.0', 'asyncio': '1.1.0', 'json-report': '1.5.0', 'timeout': '2.4.0', 'metadata': '3.1.1', 'cov': '6.2.1', 'nbval': '0.11.0'}} rootdir: /Users/erichuang/projects/llama-stack-1 configfile: pyproject.toml plugins: anyio-4.9.0, html-4.1.1, socket-0.7.0, asyncio-1.1.0, json-report-1.5.0, timeout-2.4.0, metadata-3.1.1, cov-6.2.1, nbval-0.11.0 asyncio: mode=Mode.AUTO, asyncio_default_fixture_loop_scope=None, asyncio_default_test_loop_scope=function collected 285 items / 284 deselected / 1 selected tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B] instantiating llama_stack_client Starting llama stack server with config 'starter' on port 8321... Waiting for server at http://localhost:8321... (0.0s elapsed) Waiting for server at http://localhost:8321... (0.5s elapsed) Waiting for server at http://localhost:8321... (5.1s elapsed) Waiting for server at http://localhost:8321... (5.6s elapsed) Waiting for server at http://localhost:8321... (10.1s elapsed) Waiting for server at http://localhost:8321... (10.6s elapsed) Server is ready at http://localhost:8321 llama_stack_client instantiated in 11.773s PASSEDTerminating llama stack server process... Terminating process 98444 and its group... Server process and children terminated gracefully ============================================================================================================= slowest 10 durations ============================================================================================================== 11.88s setup tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B] 3.02s call tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B] 0.01s teardown tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B] ================================================================================================ 1 passed, 284 deselected, 3 warnings in 16.21s ================================================================================================= ```	2025-10-10 16:21:44 -07:00
ehhuang	80d58ab519	chore: refactor (chat)completions endpoints to use shared params struct (#3761) ... # What does this PR do? Converts openai(_chat)_completions params to pydantic BaseModel to reduce code duplication across all providers. ## Test Plan CI --- [//]: # (BEGIN SAPLING FOOTER) Stack created with [Sapling](https://sapling-scm.com). Best reviewed with [ReviewStack](https://reviewstack.dev/llamastack/llama-stack/pull/3761). * #3777 * __->__ #3761	2025-10-10 15:46:34 -07:00
Francisco Arceo	e7d21e1ee3	feat: Add support for Conversations in Responses API (#3743) ... # What does this PR do? This PR adds support for Conversations in Responses. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan Unit tests Integration tests <Details> <Summary>Manual testing with this script: (click to expand)</Summary> ```python from openai import OpenAI client = OpenAI() client = OpenAI(base_url="http://localhost:8321/v1/", api_key="none") def test_conversation_create(): print("Testing conversation create...") conversation = client.conversations.create( metadata={"topic": "demo"}, items=[ {"type": "message", "role": "user", "content": "Hello!"} ] ) print(f"Created: {conversation}") return conversation def test_conversation_retrieve(conv_id): print(f"Testing conversation retrieve for {conv_id}...") retrieved = client.conversations.retrieve(conv_id) print(f"Retrieved: {retrieved}") return retrieved def test_conversation_update(conv_id): print(f"Testing conversation update for {conv_id}...") updated = client.conversations.update( conv_id, metadata={"topic": "project-x"} ) print(f"Updated: {updated}") return updated def test_conversation_delete(conv_id): print(f"Testing conversation delete for {conv_id}...") deleted = client.conversations.delete(conv_id) print(f"Deleted: {deleted}") return deleted def test_conversation_items_create(conv_id): print(f"Testing conversation items create for {conv_id}...") items = client.conversations.items.create( conv_id, items=[ { "type": "message", "role": "user", "content": [{"type": "input_text", "text": "Hello!"}] }, { "type": "message", "role": "user", "content": [{"type": "input_text", "text": "How are you?"}] } ] ) print(f"Items created: {items}") return items def test_conversation_items_list(conv_id): print(f"Testing conversation items list for {conv_id}...") items = client.conversations.items.list(conv_id, limit=10) print(f"Items list: {items}") return items def test_conversation_item_retrieve(conv_id, item_id): print(f"Testing conversation item retrieve for {conv_id}/{item_id}...") item = client.conversations.items.retrieve(conversation_id=conv_id, item_id=item_id) print(f"Item retrieved: {item}") return item def test_conversation_item_delete(conv_id, item_id): print(f"Testing conversation item delete for {conv_id}/{item_id}...") deleted = client.conversations.items.delete(conversation_id=conv_id, item_id=item_id) print(f"Item deleted: {deleted}") return deleted def test_conversation_responses_create(): print("\nTesting conversation create for a responses example...") conversation = client.conversations.create() print(f"Created: {conversation}") response = client.responses.create( model="gpt-4.1", input=[{"role": "user", "content": "What are the 5 Ds of dodgeball?"}], conversation=conversation.id, ) print(f"Created response: {response} for conversation {conversation.id}") return response, conversation def test_conversations_responses_create_followup( conversation, content="Repeat what you just said but add 'this is my second time saying this'", ): print(f"Using: {conversation.id}") response = client.responses.create( model="gpt-4.1", input=[{"role": "user", "content": content}], conversation=conversation.id, ) print(f"Created response: {response} for conversation {conversation.id}") conv_items = client.conversations.items.list(conversation.id) print(f"\nRetrieving list of items for conversation {conversation.id}:") print(conv_items.model_dump_json(indent=2)) def test_response_with_fake_conv_id(): fake_conv_id = "conv_zzzzzzzzz5dc81908289d62779d2ac510a2b0b602ef00a44" print(f"Using {fake_conv_id}") try: response = client.responses.create( model="gpt-4.1", input=[{"role": "user", "content": "say hello"}], conversation=fake_conv_id, ) print(f"Created response: {response} for conversation {fake_conv_id}") except Exception as e: print(f"failed to create response for conversation {fake_conv_id} with error {e}") def main(): print("Testing OpenAI Conversations API...") # Create conversation conversation = test_conversation_create() conv_id = conversation.id # Retrieve conversation test_conversation_retrieve(conv_id) # Update conversation test_conversation_update(conv_id) # Create items items = test_conversation_items_create(conv_id) # List items items_list = test_conversation_items_list(conv_id) # Retrieve specific item if items_list.data: item_id = items_list.data[0].id test_conversation_item_retrieve(conv_id, item_id) # Delete item test_conversation_item_delete(conv_id, item_id) # Delete conversation test_conversation_delete(conv_id) response, conversation2 = test_conversation_responses_create() print('\ntesting reseponse retrieval') test_conversation_retrieve(conversation2.id) print('\ntesting responses follow up') test_conversations_responses_create_followup(conversation2) print('\ntesting responses follow up x2!') test_conversations_responses_create_followup( conversation2, content="Repeat what you just said but add 'this is my third time saying this'", ) test_response_with_fake_conv_id() print("All tests completed!") if __name__ == "__main__": main() ``` </Details> --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-10-10 11:57:40 -07:00
grs	8bf07f91cb	feat: reuse previous mcp tool listings where possible (#3710) ... # What does this PR do? This PR checks whether, if a previous response is linked, there are mcp_list_tools objects that can be reused instead of listing the tools explicitly every time. Closes #3106 ## Test Plan Tested manually. Added unit tests to cover new behaviour. --------- Signed-off-by: Gordon Sim <gsim@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-10-10 09:28:25 -07:00
Matthew Farrellee	0066d986c5	feat: use SecretStr for inference provider auth credentials (#3724) ... # What does this PR do? use SecretStr for OpenAIMixin providers - RemoteInferenceProviderConfig now has auth_credential: SecretStr - the default alias is api_key (most common name) - some providers override to use api_token (RunPod, vLLM, Databricks) - some providers exclude it (Ollama, TGI, Vertex AI) addresses #3517 ## Test Plan ci w/ new tests	2025-10-10 07:32:50 -07:00
Ashwin Bharambe	e039b61d26	feat(responses)!: add in_progress, failed, content part events (#3765) ... ## Summary - add schema + runtime support for response.in_progress / response.failed / response.incomplete - stream content parts with proper indexes and reasoning slots - align tests + docs with the richer event payloads ## Testing - uv run pytest tests/unit/providers/agents/meta_reference/test_openai_responses.py::test_create_openai_response_with_string_input - uv run pytest tests/unit/providers/agents/meta_reference/test_response_conversion_utils.py	2025-10-10 07:27:34 -07:00
Ashwin Bharambe	aaf5036235	feat(responses): add usage types to inference and responses APIs (#3764) ... ## Summary Adds OpenAI-compatible usage tracking types to enable reporting token consumption for both streaming and non-streaming responses. ## Type Definitions **Chat Completion Usage** (inference API): ```python class OpenAIChatCompletionUsage(BaseModel): prompt_tokens: int completion_tokens: int total_tokens: int prompt_tokens_details: OpenAIChatCompletionUsagePromptTokensDetails | None completion_tokens_details: OpenAIChatCompletionUsageCompletionTokensDetails | None ``` **Response Usage** (responses API): ```python class OpenAIResponseUsage(BaseModel): input_tokens: int output_tokens: int total_tokens: int input_tokens_details: OpenAIResponseUsageInputTokensDetails | None output_tokens_details: OpenAIResponseUsageOutputTokensDetails | None ``` This matches OpenAI's usage reporting format and enables PR #3766 to implement usage tracking in streaming responses. Co-authored-by: Claude <noreply@anthropic.com>	2025-10-10 09:22:59 -04:00
Ashwin Bharambe	ebae0385bb	fix: update dangling references to llama download command (#3763) ... ## Summary After removing model management CLI in #3700, this PR updates remaining references to the old `llama download` command to use `huggingface-cli download` instead. ## Changes - Updated error messages in `meta_reference/common.py` to recommend `huggingface-cli download` - Updated error messages in `torchtune/recipes/lora_finetuning_single_device.py` to use `huggingface-cli download` - Updated post-training notebook to use `huggingface-cli download` instead of `llama download` - Fixed typo: "you model" -> "your model" ## Test Plan - Verified error messages provide correct guidance for users - Checked that notebook instructions are up-to-date with current tooling	2025-10-09 18:35:02 -07:00
Sébastien Han	7ee0ee7843	chore!: remove model mgmt from CLI for Hugging Face CLI (#3700) ... This change removes the `llama model` and `llama download` subcommands from the CLI, replacing them with recommendations to use the Hugging Face CLI instead. Rationale for this change: - The model management functionality was largely duplicating what Hugging Face CLI already provides, leading to unnecessary maintenance overhead (except the download source from Meta?) - Maintaining our own implementation required fixing bugs and keeping up with changes in model repositories and download mechanisms - The Hugging Face CLI is more mature, widely adopted, and better maintained - This allows us to focus on the core Llama Stack functionality rather than reimplementing model management tools Changes made: - Removed all model-related CLI commands and their implementations - Updated documentation to recommend using `huggingface-cli` for model downloads - Removed Meta-specific download logic and statements - Simplified the CLI to focus solely on stack management operations Users should now use: - `huggingface-cli download` for downloading models - `huggingface-cli scan-cache` for listing downloaded models This is a breaking change as it removes previously available CLI commands. Signed-off-by: Sébastien Han <seb@redhat.com>	2025-10-09 16:50:33 -07:00
Ashwin Bharambe	f50ce11a3b	feat(tests): make inference_recorder into api_recorder (include tool_invoke) (#3403) ... Renames `inference_recorder.py` to `api_recorder.py` and extends it to support recording/replaying tool invocations in addition to inference calls. This allows us to record web-search, etc. tool calls and thereafter apply recordings for `tests/integration/responses` ## Test Plan ``` export OPENAI_API_KEY=... export TAVILY_SEARCH_API_KEY=... ./scripts/integration-tests.sh --stack-config ci-tests \ --suite responses --inference-mode record-if-missing ```	2025-10-09 14:27:51 -07:00
Bill Murdock	5d711d4bcb	fix: Update watsonx.ai provider to use LiteLLM mixin and list all models (#3674) ... # What does this PR do? - The watsonx.ai provider now uses the LiteLLM mixin instead of using IBM's library, which does not seem to be working (see #3165 for context). - The watsonx.ai provider now lists all the models available by calling the watsonx.ai server instead of having a hard coded list of known models. (That list gets out of date quickly) - An edge case in [llama_stack/core/routers/inference.py](https://github.com/llamastack/llama-stack/pull/3674/files#diff-a34bc966ed9befd9f13d4883c23705dff49be0ad6211c850438cdda6113f3455) is addressed that was causing my manual tests to fail. - Fixes `b64_encode_openai_embeddings_response` which was trying to enumerate over a dictionary and then reference elements of the dictionary using .field instead of ["field"]. That method is called by the LiteLLM mixin for embedding models, so it is needed to get the watsonx.ai embedding models to work. - A unit test along the lines of the one in #3348 is added. A more comprehensive plan for automatically testing the end-to-end functionality for inference providers would be a good idea, but is out of scope for this PR. - Updates to the watsonx distribution. Some were in response to the switch to LiteLLM (e.g., updating the Python packages needed). Others seem to be things that were already broken that I found along the way (e.g., a reference to a watsonx specific doc template that doesn't seem to exist). Closes #3165 Also it is related to a line-item in #3387 but doesn't really address that goal (because it uses the LiteLLM mixin, not the OpenAI one). I tried the OpenAI one and it doesn't work with watsonx.ai, presumably because the watsonx.ai service is not OpenAI compatible. It works with LiteLLM because LiteLLM has a provider implementation for watsonx.ai. ## Test Plan The test script below goes back and forth between the OpenAI and watsonx providers. The idea is that the OpenAI provider shows how it should work and then the watsonx provider output shows that it is also working with watsonx. Note that the result from the MCP test is not as good (the Llama 3.3 70b model does not choose tools as wisely as gpt-4o), but it is still working and providing a valid response. For more details on setup and the MCP server being used for testing, see [the AI Alliance sample notebook](https://github.com/The-AI-Alliance/llama-stack-examples/blob/main/notebooks/01-responses/) that these examples are drawn from. ```python #!/usr/bin/env python3 import json from llama_stack_client import LlamaStackClient from litellm import completion import http.client def print_response(response): """Print response in a nicely formatted way""" print(f"ID: {response.id}") print(f"Status: {response.status}") print(f"Model: {response.model}") print(f"Created at: {response.created_at}") print(f"Output items: {len(response.output)}") for i, output_item in enumerate(response.output): if len(response.output) > 1: print(f"\n--- Output Item {i+1} ---") print(f"Output type: {output_item.type}") if output_item.type in ("text", "message"): print(f"Response content: {output_item.content[0].text}") elif output_item.type == "file_search_call": print(f" Tool Call ID: {output_item.id}") print(f" Tool Status: {output_item.status}") # 'queries' is a list, so we join it for clean printing print(f" Queries: {', '.join(output_item.queries)}") # Display results if they exist, otherwise note they are empty print(f" Results: {output_item.results if output_item.results else 'None'}") elif output_item.type == "mcp_list_tools": print_mcp_list_tools(output_item) elif output_item.type == "mcp_call": print_mcp_call(output_item) else: print(f"Response content: {output_item.content}") def print_mcp_call(mcp_call): """Print MCP call in a nicely formatted way""" print(f"\n🛠️ MCP Tool Call: {mcp_call.name}") print(f" Server: {mcp_call.server_label}") print(f" ID: {mcp_call.id}") print(f" Arguments: {mcp_call.arguments}") if mcp_call.error: print("Error: {mcp_call.error}") elif mcp_call.output: print("Output:") # Try to format JSON output nicely try: parsed_output = json.loads(mcp_call.output) print(json.dumps(parsed_output, indent=4)) except: # If not valid JSON, print as-is print(f" {mcp_call.output}") else: print(" ⏳ No output yet") def print_mcp_list_tools(mcp_list_tools): """Print MCP list tools in a nicely formatted way""" print(f"\n🔧 MCP Server: {mcp_list_tools.server_label}") print(f" ID: {mcp_list_tools.id}") print(f" Available Tools: {len(mcp_list_tools.tools)}") print("=" * 80) for i, tool in enumerate(mcp_list_tools.tools, 1): print(f"\n{i}. {tool.name}") print(f" Description: {tool.description}") # Parse and display input schema schema = tool.input_schema if schema and 'properties' in schema: properties = schema['properties'] required = schema.get('required', []) print(" Parameters:") for param_name, param_info in properties.items(): param_type = param_info.get('type', 'unknown') param_desc = param_info.get('description', 'No description') required_marker = " (required)" if param_name in required else " (optional)" print(f" • {param_name} ({param_type}){required_marker}") if param_desc: print(f" {param_desc}") if i < len(mcp_list_tools.tools): print("-" * 40) def main(): """Main function to run all the tests""" # Configuration LLAMA_STACK_URL = "http://localhost:8321/" LLAMA_STACK_MODEL_IDS = [ "openai/gpt-3.5-turbo", "openai/gpt-4o", "llama-openai-compat/Llama-3.3-70B-Instruct", "watsonx/meta-llama/llama-3-3-70b-instruct" ] # Using gpt-4o for this demo, but feel free to try one of the others or add more to run.yaml. OPENAI_MODEL_ID = LLAMA_STACK_MODEL_IDS[1] WATSONX_MODEL_ID = LLAMA_STACK_MODEL_IDS[-1] NPS_MCP_URL = "http://localhost:3005/sse/" print("=== Llama Stack Testing Script ===") print(f"Using OpenAI model: {OPENAI_MODEL_ID}") print(f"Using WatsonX model: {WATSONX_MODEL_ID}") print(f"MCP URL: {NPS_MCP_URL}") print() # Initialize client print("Initializing LlamaStackClient...") client = LlamaStackClient(base_url="http://localhost:8321") # Test 1: List models print("\n=== Test 1: List Models ===") try: models = client.models.list() print(f"Found {len(models)} models") except Exception as e: print(f"Error listing models: {e}") raise e # Test 2: Basic chat completion with OpenAI print("\n=== Test 2: Basic Chat Completion (OpenAI) ===") try: chat_completion_response = client.chat.completions.create( model=OPENAI_MODEL_ID, messages=[{"role": "user", "content": "What is the capital of France?"}] ) print("OpenAI Response:") for chunk in chat_completion_response.choices[0].message.content: print(chunk, end="", flush=True) print() except Exception as e: print(f"Error with OpenAI chat completion: {e}") raise e # Test 3: Basic chat completion with WatsonX print("\n=== Test 3: Basic Chat Completion (WatsonX) ===") try: chat_completion_response_wxai = client.chat.completions.create( model=WATSONX_MODEL_ID, messages=[{"role": "user", "content": "What is the capital of France?"}], ) print("WatsonX Response:") for chunk in chat_completion_response_wxai.choices[0].message.content: print(chunk, end="", flush=True) print() except Exception as e: print(f"Error with WatsonX chat completion: {e}") raise e # Test 4: Tool calling with OpenAI print("\n=== Test 4: Tool Calling (OpenAI) ===") tools = [ { "type": "function", "function": { "name": "get_current_weather", "description": "Get the current weather for a specific location", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g., San Francisco, CA", }, "unit": { "type": "string", "enum": ["celsius", "fahrenheit"] }, }, "required": ["location"], }, }, } ] messages = [ {"role": "user", "content": "What's the weather like in Boston, MA?"} ] try: print("--- Initial API Call ---") response = client.chat.completions.create( model=OPENAI_MODEL_ID, messages=messages, tools=tools, tool_choice="auto", # "auto" is the default ) print("OpenAI tool calling response received") except Exception as e: print(f"Error with OpenAI tool calling: {e}") raise e # Test 5: Tool calling with WatsonX print("\n=== Test 5: Tool Calling (WatsonX) ===") try: wxai_response = client.chat.completions.create( model=WATSONX_MODEL_ID, messages=messages, tools=tools, tool_choice="auto", # "auto" is the default ) print("WatsonX tool calling response received") except Exception as e: print(f"Error with WatsonX tool calling: {e}") raise e # Test 6: Streaming with WatsonX print("\n=== Test 6: Streaming Response (WatsonX) ===") try: chat_completion_response_wxai_stream = client.chat.completions.create( model=WATSONX_MODEL_ID, messages=[{"role": "user", "content": "What is the capital of France?"}], stream=True ) print("Model response: ", end="") for chunk in chat_completion_response_wxai_stream: # Each 'chunk' is a ChatCompletionChunk object. # We want the content from the 'delta' attribute. if hasattr(chunk, 'choices') and chunk.choices is not None: content = chunk.choices[0].delta.content # The first few chunks might have None content, so we check for it. if content is not None: print(content, end="", flush=True) print() except Exception as e: print(f"Error with streaming: {e}") raise e # Test 7: MCP with OpenAI print("\n=== Test 7: MCP Integration (OpenAI) ===") try: mcp_llama_stack_client_response = client.responses.create( model=OPENAI_MODEL_ID, input="Tell me about some parks in Rhode Island, and let me know if there are any upcoming events at them.", tools=[ { "type": "mcp", "server_url": NPS_MCP_URL, "server_label": "National Parks Service tools", "allowed_tools": ["search_parks", "get_park_events"], } ] ) print_response(mcp_llama_stack_client_response) except Exception as e: print(f"Error with MCP (OpenAI): {e}") raise e # Test 8: MCP with WatsonX print("\n=== Test 8: MCP Integration (WatsonX) ===") try: mcp_llama_stack_client_response = client.responses.create( model=WATSONX_MODEL_ID, input="What is the capital of France?" ) print_response(mcp_llama_stack_client_response) except Exception as e: print(f"Error with MCP (WatsonX): {e}") raise e # Test 9: MCP with Llama 3.3 print("\n=== Test 9: MCP Integration (Llama 3.3) ===") try: mcp_llama_stack_client_response = client.responses.create( model=WATSONX_MODEL_ID, input="Tell me about some parks in Rhode Island, and let me know if there are any upcoming events at them.", tools=[ { "type": "mcp", "server_url": NPS_MCP_URL, "server_label": "National Parks Service tools", "allowed_tools": ["search_parks", "get_park_events"], } ] ) print_response(mcp_llama_stack_client_response) except Exception as e: print(f"Error with MCP (Llama 3.3): {e}") raise e # Test 10: Embeddings print("\n=== Test 10: Embeddings ===") try: conn = http.client.HTTPConnection("localhost:8321") payload = json.dumps({ "model": "watsonx/ibm/granite-embedding-278m-multilingual", "input": "Hello, world!", }) headers = { 'Content-Type': 'application/json', 'Accept': 'application/json' } conn.request("POST", "/v1/openai/v1/embeddings", payload, headers) res = conn.getresponse() data = res.read() print(data.decode("utf-8")) except Exception as e: print(f"Error with Embeddings: {e}") raise e print("\n=== Testing Complete ===") if __name__ == "__main__": main() ``` --------- Signed-off-by: Bill Murdock <bmurdock@redhat.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2025-10-08 07:29:43 -04:00