phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Commit graph

  • 9e03df983e
         fix(rag-example): add provider_id to avoid llama_stack_client 400 error (#1114) Alessandro Sangiorgi 2025-02-19 17:37:25 -06:00
  • 034ece0011 Ensure that deprecations for fields follow through to OpenAPI Ashwin Bharambe 2025-02-19 13:54:04 -08:00
  • 31a5ba5268 Add title to the json schemas Ashwin Bharambe 2025-02-19 13:26:39 -08:00
  • 5e7904ef6c Kill the older strong_typing code Ashwin Bharambe 2025-02-19 12:24:21 -08:00
  • a66b4c4c81
         test: Enable test_text_chat_completion_with_tool_choice_required for remote::vllm (#1148) Yuan Tang 2025-02-18 23:52:15 -05:00
  • 8de7cf103b
         feat: support tool_choice = {required, none, <function>} (#1059) ehhuang 2025-02-18 20:25:15 -08:00
  • 37cf60b732
         style: remove prints in codebase (#1146) Xi Yan 2025-02-18 19:41:37 -08:00
  • e8cb9e0adb
         fix: direct client pydantic type casting (#1145) Xi Yan 2025-02-18 16:07:54 -08:00
  • 8585b95a28 rename Xi Yan 2025-02-18 16:02:44 -08:00
  • 4e76d312fa
         fix: modify the model id title for model list (#1095) Reid 2025-02-19 02:26:41 +08:00
  • d9f5beb15a
         style: update download help text (#1135) Reid 2025-02-19 02:24:31 +08:00
  • 92aefec191
         style: update verify-download help text (#1134) Reid 2025-02-19 02:15:26 +08:00
  • 89d37687dd
         chore: remove --no-list-templates option (#1121) Reid 2025-02-19 02:13:46 +08:00
  • 6b1773d530
         docs: Fix incorrect link and command for generating API reference (#1124) Yuan Tang 2025-02-15 22:05:23 -05:00
  • 743f434860
         fix: Ensure a tool call can be converted before adding to buffer (#1119) Yuan Tang 2025-02-15 00:19:16 -05:00
  • ab2b46e528
         feat: log start, complete time to Agent steps (#1116) ehhuang 2025-02-14 17:48:06 -08:00
  • 8dc1cac333
         style: fix the capitalization issue (#1117) Reid 2025-02-15 09:16:26 +08:00
  • ab210ec59e
         Update README.md Hardik Shah 2025-02-14 15:45:08 -08:00
  • df864ee575
         Update index.md to refer to v0.1.3 Hardik Shah 2025-02-14 14:29:17 -08:00
  • 00613d9014
         build: resync uv and deps on 0.1.3 (#1108) Sébastien Han 2025-02-14 21:26:04 +01:00
  • 9b2fe6beb1 Bump version to 0.1.3 v0.1.3 github-actions[bot] 2025-02-14 19:57:18 +00:00
  • 3d88b81ccf
         fix: remove the empty line (#1097) v0.1.3rc3 v0.1.3rc2 Reid 2025-02-15 01:33:20 +08:00
  • 369cc513cb
         fix: improve stack build on venv (#980) Sébastien Han 2025-02-14 18:22:03 +01:00
  • 64328bfe62
         fix: enable_session_persistence in AgentConfig should be optional (#1012) Yuan Tang 2025-02-14 12:19:53 -05:00
  • 314ee09ae3
         chore: move all Llama Stack types from llama-models to llama-stack (#1098) Ashwin Bharambe 2025-02-14 09:10:59 -08:00
  • c0ee512980
         build: configure ruff from pyproject.toml (#1100) Sébastien Han 2025-02-14 18:01:57 +01:00
  • a3cb039e83
         docs: Add region parameter to Bedrock provider (#1103) raghotham 2025-02-14 08:55:22 -08:00
  • 406465622e
         fix: Update QdrantConfig to QdrantVectorIOConfig (#1104) Ben Browning 2025-02-14 09:31:00 -05:00
  • 2f7268b790
         fix: add the missed help description info (#1096) Reid 2025-02-14 13:31:36 +08:00
  • b27c41fe39
         fix: disable sqlite-vec test (#1090) v0.1.3rc1 Xi Yan 2025-02-13 18:40:16 -08:00
  • b0b696cb4f
         fix: regex pattern matching to support :path suffix in the routes (#1089) Hardik Shah 2025-02-13 18:18:23 -08:00
  • da53dc3f5f
         fix: openapi for eval-task (#1085) Xi Yan 2025-02-13 17:10:45 -08:00
  • 2a8e199e10 fix notebook Xi Yan 2025-02-13 16:52:46 -08:00
  • 8b655e3cd2
         fix!: update eval-tasks -> benchmarks (#1032) Xi Yan 2025-02-13 16:40:58 -08:00
  • 225dd38e5c
         test: add test for Agent.create_turn non-streaming response (#1078) ehhuang 2025-02-13 16:17:50 -08:00
  • 32d1e50a6f
         test: Add qdrant to provider tests (#1039) Bill Murdock 2025-02-13 18:44:55 -05:00
  • 5858777ff0
         fix: Update VectorIO config classes in registry (#1079) Yuan Tang 2025-02-13 18:39:13 -05:00
  • aebd130b08
         docs: Fix url to the llama-stack-spec yaml/html files (#1081) Anil Vishnoi 2025-02-13 20:39:26 +00:00
  • efdd60014d
         test: Enable logprobs top_k tests for remote::vllm (#1080) Yuan Tang 2025-02-13 13:44:57 -05:00
  • 8ff27b58fa
         chore: Consistent naming for VectorIO providers (#1023) Yuan Tang 2025-02-13 13:15:49 -05:00
  • e4a1579e63
         build: format codebase imports using ruff linter (#1028) Sébastien Han 2025-02-13 19:06:21 +01:00
  • 1527c30107
         fix: remove :path in agents (#1077) Xi Yan 2025-02-13 10:04:43 -08:00
  • f9ca441974
         chore: Link to Groq docs in the warning message for preview model (#1060) Yuan Tang 2025-02-13 12:14:57 -05:00
  • 2fa9e3c941
         fix: make backslash work in GET /models/{model_id:path} (#1068) Xi Yan 2025-02-13 08:46:43 -08:00
  • 47fccf0d03
         style: update model id in model list title (#1072) Reid 2025-02-14 00:33:11 +08:00
  • 418645696a
         fix: improve signal handling and update dependencies (#1044) Sébastien Han 2025-02-13 17:07:59 +01:00
  • dd1a366347
         fix: logprobs support in remote-vllm provider (#1074) Ben Browning 2025-02-13 11:00:00 -05:00
  • 8c01b7f05a
         docs: Mention convential commits format in CONTRIBUTING.md (#1075) Ben Browning 2025-02-13 10:57:30 -05:00
  • cc700b2f68
         feat: support listing all for llama stack list-providers (#1056) Ihar Hrachyshka 2025-02-13 01:03:28 -05:00
  • 119fe8742a
         feat: Adding sqlite-vec as a vectordb (#1040) Francisco Arceo 2025-02-12 13:50:03 -05:00
  • 025f615868
         feat: add support for running in a venv (#1018) Charlie Doern 2025-02-12 11:13:04 -05:00
  • 5f88ff0b6a
         fix: show proper help text (#1065) Charlie Doern 2025-02-12 09:38:25 -05:00
  • 5e97dd9919
         feat: Support tool calling for streaming chat completion in remote vLLM provider (#1063) Yuan Tang 2025-02-12 09:17:21 -05:00
  • bf11cc0450
         chore: update return type to Optional[str] (#982) Sébastien Han 2025-02-12 07:10:28 +01:00
  • 66d7e15c93
         perf: ensure ToolCall in ChatCompletionResponse is subset of ChatCompletionRequest.tools (#1041) Xi Yan 2025-02-11 18:31:35 -08:00
  • dd37e58868
         feat: Support tool calling for non-streaming chat completion in remote vLLM provider (#1034) Yuan Tang 2025-02-11 21:08:29 -05:00
  • 24385cfd03
         fix: filter out remote::sample providers when listing (#1057) Ihar Hrachyshka 2025-02-11 19:12:46 -05:00
  • d8a20e034b
         feat: make telemetry attributes be dict[str,PrimitiveType] (#1055) Dinesh Yeduguru 2025-02-11 15:10:17 -08:00
  • ab7f802698
         feat: add MetricResponseMixin to chat completion response types (#1050) Dinesh Yeduguru 2025-02-11 14:58:12 -08:00
  • 96c88397da
         fix: agent config validation (#1053) ehhuang 2025-02-11 14:48:42 -08:00
  • 6ad272927d
         docs: reflect actual number of spaces for indent (#1052) Ihar Hrachyshka 2025-02-11 17:07:26 -05:00
  • afb81da91a feat: add optional metrics to all responses inject-metrics-response-v2 Dinesh Yeduguru 2025-02-11 10:36:27 -08:00
  • 71cae67d7b
         docs: remove changelog mention from PR template (#1049) Sébastien Han 2025-02-11 19:24:53 +01:00
  • d947ddd255
         docs: Updating wording and nits in the README.md (#992) Kelly Brown 2025-02-11 09:53:26 -05:00
  • d954f2752e
         fix: Added missing tool_config arg in SambaNova chat_completion() (#1042) Yuan Tang 2025-02-11 00:20:50 -05:00
  • b34c1dd8ad
         test: replace blocked image URLs with GitHub-hosted (#1025) Sébastien Han 2025-02-11 04:38:11 +01:00
  • 3856927ee8
         fix: Update Qdrant support post-refactor (#1022) Bill Murdock 2025-02-10 18:08:33 -05:00
  • 36d35406a7
         fix: a bad newline in ollama docs (#1036) Ellis Tarn 2025-02-10 14:27:17 -08:00
  • afca9d92f9
         fix: Readthedocs cannot parse comments, resulting in docs bugs (#1033) Ellis Tarn 2025-02-10 13:35:16 -08:00
  • ab9516c789
         fix: Gaps in doc codegen (#1035) Ellis Tarn 2025-02-10 13:24:15 -08:00
  • 371f11a569
         build: update uv lock to sync package versions (#1026) Sébastien Han 2025-02-10 17:42:30 +01:00
  • 076213165c
         docs: update rag.md example code to prevent errors (#1009) Michael Clifford 2025-02-10 09:25:30 -05:00
  • 8186c88021
         docs: Render check marks correctly on PyPI (#1024) Yuan Tang 2025-02-09 22:26:36 -05:00
  • 162cfb280e added note of the image understanding working with LS 0.1.0 and 0.1.2 jeff/getting_started Jeff Tang 2025-02-09 09:27:15 -08:00
  • 44f1a4fd5c fix of the agent image understanding example error for LS 0.1.2 Jeff Tang 2025-02-09 09:24:15 -08:00
  • b981b49bfa
         test: Use JSON tool prompt format for remote::vllm provider (#1019) Yuan Tang 2025-02-08 23:42:57 -05:00
  • 80ba9deab1
         chore: Updated requirements.txt (#1017) Sarthak Deshpande 2025-02-09 01:20:35 +05:30
  • 413099ef6a
         test: Make text-based chat completion tests run 10x faster (#1016) Yuan Tang 2025-02-08 14:49:46 -05:00
  • 7766e68e92
         docs: update index.md for 0.1.2 (#1013) raghotham 2025-02-07 15:36:20 -08:00
  • a229de6d1e
         Getting started notebook update (#936) Jeff Tang 2025-02-07 15:36:15 -08:00
  • ddd06105a4 Bump version to 0.1.2 v0.1.2 github-actions[bot] 2025-02-07 21:52:50 +00:00
  • c335ed8765 raise when client initialize fails v0.1.2rc4 Hardik Shah 2025-02-07 12:24:07 -08:00
  • 62e5461da7 No spaces in ipynb tests Ashwin Bharambe 2025-02-07 11:56:22 -08:00
  • a8820597ee Minor clean up of notebook Ashwin Bharambe 2025-02-07 11:36:29 -08:00
  • 10bda65b94 Nuke use_proxy from code execution v0.1.2rc3 Ashwin Bharambe 2025-02-07 09:55:48 -08:00
  • 316c43fdaf
         refactor(ollama): model availability check (#986) Sébastien Han 2025-02-07 18:52:16 +01:00
  • 2a4a612373
         fix: Ensure a better error stack trace when llama-stack is not built (#950) Charlie Doern 2025-02-07 12:47:02 -05:00
  • 0b7098493a
         test: encode image data as base64 (#1003) Sébastien Han 2025-02-07 18:44:16 +01:00
  • f8f2f7f9bb
         feat: Add HTTPS serving option (#1000) Ashwin Bharambe 2025-02-07 09:39:08 -08:00
  • c97e05f75e
         test: Split inference tests to text and vision (#1008) Yuan Tang 2025-02-07 12:35:49 -05:00
  • a9950ce806
         test: remove flaky agent test (#1006) ehhuang 2025-02-07 09:35:38 -08:00
  • 657f24b964
         chore: add missing ToolConfig import in groq.py (#983) Sébastien Han 2025-02-07 18:35:00 +01:00
  • e6c9f2a485 Delete CHANGELOG.md Ashwin Bharambe 2025-02-07 09:03:35 -08:00
  • 3f9764d50c
         fix: List providers command prints out non-existing APIs from registry. Fixes #966 (#969) Yuan Tang 2025-02-07 12:02:15 -05:00
  • 840344975d
         test: rm unused exception alias in pytest.raises (#991) Sébastien Han 2025-02-07 17:04:25 +01:00
  • d0d568c5ba
         test: fix flaky agent test (#1002) ehhuang 2025-02-06 20:19:38 -08:00
  • af15426ad7
         doc: getting started notebook (#996) ehhuang 2025-02-06 17:30:21 -08:00
  • 7ec79c0297 Add Terry to CODEOWNERS Ashwin Bharambe 2025-02-06 16:23:23 -08:00
  • 28a0fe57cc
         fix: Update rag examples to use fresh faiss index every time (#998) Hardik Shah 2025-02-06 16:12:29 -08:00
  • 06e5af1435 update test Xi Yan 2025-02-06 16:11:00 -08:00