Commit graph

  • c6403706b4 use task and async generator instead of a thread Matthew Farrellee 2025-09-12 16:41:48 -04:00
  • a673484e21 make sure the mock method identifies as a coroutine Matthew Farrellee 2025-09-12 13:13:13 -04:00
  • a14f42f1b8 chore(recorder, tests): add support for openai /v1/models Matthew Farrellee 2025-09-12 12:12:12 -04:00
  • 4e096bab96 feat: introduce api leveling documentation Charlie Doern 2025-09-03 10:25:01 -04:00
  • fa7144163e refactor(vector-db): remove redundant fallback assignment for provider_vector_db_id Habeb Nawatha 2025-09-12 12:26:22 +03:00
  • f67081d2d6
    feat: migrate to FIPS-validated cryptographic algorithms (#3423) Doug Edgar 2025-09-12 02:18:19 -07:00
  • d31e641d69
    fix: Improve pre-commit workflow error handling and feedback (#3400) Akram Ben Aissi 2025-09-12 10:10:59 +01:00
  • 48dda8bed8 chore(recorder, tests): add test for openai /v1/models Matthew Farrellee 2025-09-12 05:05:05 -04:00
  • f9b423b607
    Update chat_format.py reisnfz 2025-09-12 09:39:50 +08:00
  • c8b008c5cf Release candidate 0.0.0.dev20250912001446 rc-0.0.0.dev20250912001446 github-actions[bot] 2025-09-12 00:15:29 +00:00
  • aaea9fed12
    Merge branch 'main' into chroma Bwook (Byoungwook) Kim 2025-09-12 08:56:46 +09:00
  • f7e4395380 feat: migrate to FIPS-validated cryptographic algorithms Doug Edgar 2025-09-11 15:11:00 -07:00
  • 4271f7352e minor fix fix-fireworks-provider Swapna Lekkala 2025-09-11 16:10:23 -07:00
  • f9348a6bdf test-fireworks-fix Swapna Lekkala 2025-09-11 15:58:38 -07:00
  • 69a52213a1
    fix: oasdiff enhancements and stability (#3419) Charlie Doern 2025-09-11 16:30:09 -04:00
  • a14a164585 fix: Improve pre-commit workflow error handling and feedback Akram Ben Aissi 2025-09-10 13:09:43 +02:00
  • 4532a2f639 fix: oasdiff enhancements and stability Charlie Doern 2025-09-11 11:52:15 -04:00
  • c7ef1f13df
    feat: Add langchain llamastack Integration example notebook (#3314) slekkala1 2025-09-11 11:10:41 -07:00
  • 4375764074
    Merge branch 'main' into crewai Kai Wu 2025-09-11 09:27:27 -07:00
  • 72387b4bd2
    chore(unit tests): remove network use, update async test (#3418) Matthew Farrellee 2025-09-11 11:45:16 -04:00
  • 0afc4d10fa
    Update llama_stack/providers/utils/inference/openai_mixin.py Matthew Farrellee 2025-09-11 11:14:22 -04:00
  • fcda5e976c chore(unit tests): remove network use, update async test Matthew Farrellee 2025-09-11 10:32:04 -04:00
  • 571f998c78
    delete pre-commit in pyproject.toml kimbwook 2025-09-11 23:13:14 +09:00
  • f3bd532461
    delete blank line in vector_utils.py kimbwook 2025-09-11 23:11:24 +09:00
  • bfc8a3b99d
    change exception log parse to chunk kimbwook 2025-09-11 23:09:31 +09:00
  • 729e0f3fcb
    Merge branch 'main' into chroma Bwook (Byoungwook) Kim 2025-09-11 22:59:26 +09:00
  • 8ef1189be7
    chore: update the vLLM inference impl to use OpenAIMixin for openai-compat functions (#3404) Matthew Farrellee 2025-09-11 09:04:38 -04:00
  • 8ed3527a64 revert from Qwen/Qwen3-0.6B Matthew Farrellee 2025-09-11 08:57:43 -04:00
  • 897be1376e
    change Reranker to WeightedInMemoryAggregator kimbwook 2025-09-11 21:40:21 +09:00
  • 60318b659d
    Merge branch 'main' into chroma Bwook (Byoungwook) Kim 2025-09-11 21:30:50 +09:00
  • 6bdcfc2627
    Merge branch 'main' into chroma Bwook (Byoungwook) Kim 2025-09-11 20:51:31 +09:00
  • 11c71c958e
    Merge branch 'main' into chroma Bwook (Byoungwook) Kim 2025-09-11 20:46:53 +09:00
  • ee3df99de4
    feat: add Azure OpenAI inference provider support Sébastien Han 2025-09-01 16:41:30 +02:00
  • 736d734098
    Merge 8da9ff352c into 2838d5a20f Ashwin Bharambe 2025-09-11 13:09:31 +02:00
  • 4084158faa
    Merge branch 'main' into fix/vector-db-mandatory-provider-id Habeb Nawatha 2025-09-11 13:09:58 +03:00
  • 4374da02f3
    Merge branch 'main' into fix/vector-db-mandatory-provider-id Habeb Nawatha 2025-09-11 12:02:37 +03:00
  • e6a5ad5e35 chore(pre-commit): apply codegen and permissions fixes Habeb Nawatha 2025-09-11 11:57:07 +03:00
  • c3fc859257 feat: add dynamic model registration support to TGI inference Matthew Farrellee 2025-09-11 02:02:02 -04:00
  • d15368a302
    chore: Updating documentation, adding exception handling for Vector Stores in RAG Tool, more tests on migration, and migrate off of inference_api for context_retriever for RAG (#3367) Francisco Arceo 2025-09-11 06:20:11 -06:00
  • f31bcc11bc
    feat: add Azure OpenAI inference provider support (#3396) Sébastien Han 2025-09-11 13:48:38 +02:00
  • c2d281e01b
    chore(replay): improve replay robustness with un-validated construction (#3414) Matthew Farrellee 2025-09-11 07:48:19 -04:00
  • 2838d5a20f
    fix: AWS Bedrock inference profile ID conversion for region-specific endpoints (#3386) Sumanth Kamenani 2025-09-11 05:41:53 -04:00
  • 8e05c68d15
    chore: remove openai dependency from providers (#3398) Sébastien Han 2025-09-11 10:19:59 +02:00
  • b0364572b2 chore(replay): improve replay robustness with un-validated construction Matthew Farrellee 2025-09-11 01:01:01 -04:00
  • ad1ea895cb
    Merge branch 'main' into ragtool-migration Francisco Arceo 2025-09-10 18:44:44 -06:00
  • 670793b2e6 remove logs Kai Wu 2025-09-10 14:59:03 -07:00
  • f0966efec4 lint Kai Wu 2025-09-10 14:58:17 -07:00
  • 0c7f49490c
    fix(inference_store): on duplicate chat completion IDs, replace (#3408) Ashwin Bharambe 2025-09-10 14:34:18 -07:00
  • cc658506ad add comment Ashwin Bharambe 2025-09-10 14:28:28 -07:00
  • 7eedb88edc fix(inference_store): on duplicate chat completion IDs, replace Ashwin Bharambe 2025-09-10 12:25:04 -07:00
  • ff9fd7c4b5 Add support for application/json MIME type in agent document processing copilot-swe-agent[bot] 2025-09-10 20:49:53 +00:00
  • b80fb507a0 Initial plan copilot-swe-agent[bot] 2025-09-10 20:44:07 +00:00
  • 0b27182037
    Merge branch 'main' into ragtool-migration Francisco Arceo 2025-09-10 14:42:06 -06:00
  • c04f1c1e8c
    chore: move benchmarking related code (#3406) ehhuang 2025-09-10 13:19:44 -07:00
  • d2f88a10fb
    chore: telemetry test (#3405) ehhuang 2025-09-10 13:19:36 -07:00
  • d4e45cd5f1
    chore(ui-deps): bump tailwindcss from 4.1.6 to 4.1.13 in /llama_stack/ui (#3362) dependabot[bot] 2025-09-10 13:18:14 -07:00
  • 438c037b1f
    chore(python-deps): bump openai from 1.102.0 to 1.106.1 (#3356) dependabot[bot] 2025-09-10 13:17:43 -07:00
  • 369083c069
    chore(python-deps): bump locust from 2.39.1 to 2.40.1 (#3358) dependabot[bot] 2025-09-10 13:17:28 -07:00
  • a844c4f6e1
    chore(python-deps): bump pytest from 8.4.1 to 8.4.2 (#3359) dependabot[bot] 2025-09-10 13:17:02 -07:00
  • c6e980a993 refactor(agents): migrate to OpenAI chat completions API Aakanksha Duggal 2025-08-11 14:27:30 -04:00
  • 9b27f81b75
    Merge branch 'main' into ragtool-migration Francisco Arceo 2025-09-10 13:58:57 -06:00
  • ff0bd414b1 chore: Updating documentation and adding exception handling for Vector Stores in RAG Tool and updating inference to use openai and updating memory implementation to use existing libraries Francisco Javier Arceo 2025-09-07 13:52:39 -04:00
  • 7394828c7a
    docs: horizontal nav bar (#3407) Alexey Rybak 2025-09-10 12:43:36 -07:00
  • 5d12e4f893
    Merge branch 'main' into docs-nav-bar Alexey Rybak 2025-09-10 12:13:47 -07:00
  • e2bfb1b59e chore: move benchmarking related code Eric Huang 2025-09-10 12:08:07 -07:00
  • 9bd1814d5b chore: telemetry test Eric Huang 2025-09-10 12:10:23 -07:00
  • e6d382dd0e (docs): horizontal nav bar Alexey Rybak 2025-09-10 12:03:20 -07:00
  • e980436a2e
    chore: introduce write queue for inference_store (#3383) ehhuang 2025-09-10 11:57:42 -07:00
  • e6edc1f934
    fix: unbound variable error in schedule-record-workflow.sh (#3401) Derek Higgins 2025-09-10 19:54:10 +01:00
  • a6b1588dc6
    revert: Fireworks chat completion broken due to telemetry (#3402) Francisco Arceo 2025-09-10 12:53:38 -06:00
  • f6bf36343d
    chore: logging perf improvments (#3393) ehhuang 2025-09-10 11:52:23 -07:00
  • e721ca9730 chore: introduce write queue for inference_store Eric Huang 2025-09-10 11:43:26 -07:00
  • 8928ecfca0 chore: logging perf improvments Eric Huang 2025-09-10 11:43:05 -07:00
  • 8da9ff352c feat(tests): make inference_recorder into api_recorder (include tool_invoke) Ashwin Bharambe 2025-09-09 17:14:35 -07:00
  • 14bb7d6200
    Revert "fix: Fireworks chat completion broken due to telemetry (#3392)" Francisco Arceo 2025-09-10 12:16:30 -04:00
  • 0b75f63def fix: unbound variable error in schedule-record-workflow.sh Derek Higgins 2025-09-10 16:58:57 +01:00
  • 935b8e28de
    fix: Fireworks chat completion broken due to telemetry (#3392) slekkala1 2025-09-10 08:48:01 -07:00
  • baeaf7dfe0 chore: update the ollama inference impl to use OpenAIMixin for openai-compat functions Matthew Farrellee 2025-09-09 13:45:58 -04:00
  • c2a9c65fff chore: update the vLLM inference impl to use OpenAIMixin for openai-compat functions Matthew Farrellee 2025-09-10 10:10:10 -04:00
  • c86e45496e
    ci: Re-enable pre-commit to fail (#3399) Sébastien Han 2025-09-10 16:00:46 +02:00
  • e716e25ea0
    ci: re-enable pre-commit to fail CI Sébastien Han 2025-09-10 15:52:47 +02:00
  • cae696553c
    fix: convert to string on return Sébastien Han 2025-09-10 15:51:57 +02:00
  • 23f29d0798
    chore: remove openai dependency from providers Sébastien Han 2025-09-10 15:48:19 +02:00
  • 295d8b99c3 refactor(client): replace all AsyncMilvusClient usage of has_collection() with list_collections() Mustafa Elbehery 2025-09-09 22:20:02 +02:00
  • 5482396459 Revert "fix(test): chrome db test fails due to reusing deleted collection" Mustafa Elbehery 2025-09-09 21:49:35 +02:00
  • 733d0c70fe fix(integration): init AsyncMilvusClient before MilvusIndex Mustafa Elbehery 2025-09-08 22:00:59 +02:00
  • e7444c1d9b chore: remove irrelevant comments Mustafa Elbehery 2025-09-08 18:28:19 +02:00
  • 5a6c20313d fix(test): chrome db test fails due to reusing deleted collection Mustafa Elbehery 2025-09-08 18:13:03 +02:00
  • 142bd248e7 feat(client): migrate MilvusClient to AsyncMilvusClient Mustafa Elbehery 2025-09-08 17:19:42 +02:00
  • 0e27016cf2
    chore: update the vertexai inference impl to use openai-python for openai-compat functions (#3377) Matthew Farrellee 2025-09-10 09:39:29 -04:00
  • c836fa29e3
    fix: pre-commit issues: non executable shebang file and removal of @pytest.mark.asyncio decorator (#3397) Akram Ben Aissi 2025-09-10 15:27:35 +02:00
  • b9961c8735
    fix: add token to the openai request Sébastien Han 2025-09-10 15:17:37 +02:00
  • 2f18194978
    chore: update the vertexai inference impl to use openai-python for openai-compat functions Matthew Farrellee 2025-09-08 13:16:53 -04:00
  • c752209ee4 fix bedrock inference profile IDs for AWS regions skamenan7 2025-09-09 09:23:00 -04:00
  • 73e99b6eab
    fix: add token to the openai request mattf-use-openai-for-vertexai Sébastien Han 2025-09-10 15:17:37 +02:00
  • f73d126d52 fix: Remove @pytest.mark.asyncio decorator from test_rag_query.py Akram Ben Aissi 2025-09-10 13:01:19 +02:00
  • 340dc7f464 fix: Make scripts/get_setup_env.py executable Akram Ben Aissi 2025-09-10 13:01:54 +02:00
  • 23628c5115
    Merge branch 'main' into fix-fireworks Francisco Arceo 2025-09-10 06:58:15 -06:00
  • 3442f8865c
    fix: Add missing files_api parameter to MemoryToolRuntimeImpl test (#3394) Akram Ben Aissi 2025-09-10 12:55:57 +02:00
  • fe517f1ac7
    feat: Add vector_db_id to chunk metadata (#3304) Cesare Pompeiano 2025-09-10 11:19:21 +02:00