Commit graph

  • 3f89c736b6 [memory refactor][6/n] Update naming and routes Ashwin Bharambe 2025-01-22 09:11:19 -08:00
  • c9e5578151
    [memory refactor][5/n] Migrate all vector_io providers (#835) Ashwin Bharambe 2025-01-22 10:17:59 -08:00
  • 33ea91364e Update templates Ashwin Bharambe 2025-01-21 22:12:34 -08:00
  • 5605917361 [memory refactor][5/n] Migrate all vector_io providers Ashwin Bharambe 2025-01-21 21:28:57 -08:00
  • 63f37f9b7c
    [memory refactor][4/n] Update the client-sdk test for RAG (#834) Ashwin Bharambe 2025-01-22 10:15:19 -08:00
  • f5ba3a5db8 [memory refactor][4/n] Update the client-sdk test for RAG Ashwin Bharambe 2025-01-21 17:47:16 -08:00
  • 1a7490470a
    [memory refactor][3/n] Introduce RAGToolRuntime as a specialized sub-protocol (#832) Ashwin Bharambe 2025-01-22 10:04:16 -08:00
  • 5297aef9e8 reuse some variables Ashwin Bharambe 2025-01-21 21:19:19 -08:00
  • 89f51a86dd update openapi generator Ashwin Bharambe 2025-01-21 17:09:04 -08:00
  • 460dc8a72a bug fix, generate openapi spec Ashwin Bharambe 2025-01-21 15:56:48 -08:00
  • 039982004d slight rename Ashwin Bharambe 2025-01-21 15:49:22 -08:00
  • 68f2550e1e add a test for rag via curl; this can be generalized Ashwin Bharambe 2025-01-21 15:37:41 -08:00
  • a1433c0899 RAG Agent test passes Ashwin Bharambe 2025-01-21 15:16:17 -08:00
  • 2f76de1643 Introduce RAGToolRuntime as a specialized sub-protocol Ashwin Bharambe 2025-01-21 12:13:44 -08:00
  • 78a481bb22
    [memory refactor][2/n] Update faiss and make it pass tests (#830) Ashwin Bharambe 2025-01-22 10:02:15 -08:00
  • 9282794b16 [memory refactor][2/n] Update faiss and make it pass tests Ashwin Bharambe 2025-01-19 14:02:55 -08:00
  • 3ae8585b65
    [memory refactor][1/n] Rename Memory -> VectorIO, MemoryBanks -> VectorDBs (#828) Ashwin Bharambe 2025-01-22 09:59:30 -08:00
  • 03e61f1bb4 update why llamastack page Hardik Shah 2025-01-22 08:44:12 -08:00
  • fa69992cd5 update readthedocs index Hardik Shah 2025-01-22 08:02:30 -08:00
  • 7ec2d955ee add cerebras and ollama Sixian Yi 2025-01-21 22:59:49 -08:00
  • c24bef1e01 update README.md Hardik Shah 2025-01-21 23:38:28 -08:00
  • 2b71313b0d update README.md Hardik Shah 2025-01-21 23:35:06 -08:00
  • 857e4d69d6 Update README.md Hardik Shah 2025-01-21 23:25:56 -08:00
  • 35a00d004a
    bug fix for distro report generation (#836) Sixian Yi 2025-01-21 21:44:06 -08:00
  • 1ee0790b12 bug fix Sixian Yi 2025-01-21 21:37:31 -08:00
  • 7dc946196d add test report Sixian Yi 2025-01-21 17:37:14 -08:00
  • 684de1e6fd report Sixian Yi 2025-01-21 17:32:34 -08:00
  • edf56884a7
    add pytest option to generate a functional report for distribution (#833) Sixian Yi 2025-01-21 21:18:23 -08:00
  • e9f49a1edd address comment Sixian Yi 2025-01-21 18:50:08 -08:00
  • 447d65dbc2 fix Sixian Yi 2025-01-21 18:23:19 -08:00
  • 8ad0e31359 add test report Sixian Yi 2025-01-21 17:37:14 -08:00
  • 4a0f1c55e9 report Sixian Yi 2025-01-21 17:32:34 -08:00
  • e41873f268
    [ez] structured output for /completion ollama & enable tests (#822) Sixian Yi 2025-01-21 21:10:24 -08:00
  • 7a4b382ae9
    add section for mcp tool usage in notebook (#831) Dinesh Yeduguru 2025-01-21 13:10:42 -08:00
  • d7b135bae1 add notebook for mcp Dinesh Yeduguru 2025-01-17 16:25:13 -08:00
  • e294de58d9 move directories from memory -> vector_io Ashwin Bharambe 2025-01-19 13:27:19 -08:00
  • 138003fe92 [memory refactor][1/n] Rename Memory -> VectorIO, MemoryBanks -> VectorDBs Ashwin Bharambe 2025-01-19 10:15:29 -08:00
  • 75a2694daa Refactor the API enum to an independent file into llama_stack/apis/ Ashwin Bharambe 2025-01-19 12:22:40 -08:00
  • bd0db384e7 correct parameter order of build_model_alias call in inference.py Aidan Ryan 2025-01-18 20:10:47 -05:00
  • 74f6af8bbe
    [CICD] add simple test step for docker build workflow, fix prefix bug (#821) Xi Yan 2025-01-18 15:16:05 -08:00
  • 55067fa81d
    test report for v0.1 (#814) Sixian Yi 2025-01-18 07:50:45 -08:00
  • 7e667b66d8 add test Aidan Do 2025-01-18 09:25:51 +00:00
  • 09fc3800b9 Add vllm completions Aidan Do 2025-01-18 19:35:17 +11:00
  • 81be602f88 actual prod workflow Xi Yan 2025-01-17 23:56:31 -08:00
  • 20b96e30bc bugfix Xi Yan 2025-01-17 23:50:31 -08:00
  • ee19565035 bugfix Xi Yan 2025-01-17 23:49:36 -08:00
  • f48a658d52 edit compose Xi Yan 2025-01-17 23:44:32 -08:00
  • b471e73d9d network debug Xi Yan 2025-01-17 23:35:58 -08:00
  • 5c1ecc9ff5 network debug Xi Yan 2025-01-17 23:31:26 -08:00
  • dfa675ea9a cd Xi Yan 2025-01-17 23:22:31 -08:00
  • 39e8bc1631 hmm Xi Yan 2025-01-17 23:18:35 -08:00
  • 531e165a7b install pytest Xi Yan 2025-01-17 23:13:45 -08:00
  • 4a45c9e714 revert run change Xi Yan 2025-01-17 23:11:29 -08:00
  • 83aaf2fb8f don't release test pypi Xi Yan 2025-01-17 23:09:15 -08:00
  • ff55bacf95 try test docker Xi Yan 2025-01-17 23:08:23 -08:00
  • d140b73371 tmp publish testpypi Xi Yan 2025-01-17 22:49:19 -08:00
  • e19840379b tmp workflow Xi Yan 2025-01-17 22:48:49 -08:00
  • 1787008251 structured output for /completion API ollama Sixian Yi 2025-01-17 22:41:29 -08:00
  • 8c342e1876 remove print Xi Yan 2025-01-17 22:21:13 -08:00
  • 6b07f80d59 fix docker build name prefix Xi Yan 2025-01-17 22:18:16 -08:00
  • 5379eca9fd
    Fix incorrect image type in publish-to-docker workflow (#819) Yuan Tang 2025-01-18 00:33:03 -05:00
  • 5a63d0ff1d
    Fix incorrect RunConfigSettings due to the removal of conda_env (#801) Yuan Tang 2025-01-18 00:30:57 -05:00
  • f5edd07b29
    Merge branch 'main' into patch-1 Yuan Tang 2025-01-17 23:49:05 -05:00
  • db4bf3369f
    Fix incorrect image type in publish-to-docker workflow Yuan Tang 2025-01-17 22:59:42 -05:00
  • 3a9468ce9b
    fix again vllm for non base64 (#818) Xi Yan 2025-01-17 18:33:40 -08:00
  • 9a0fa89e9a fix again vllm Xi Yan 2025-01-17 17:50:25 -08:00
  • f2ddf02fb6 fix again vllm Xi Yan 2025-01-17 17:46:42 -08:00
  • b1a38ad1b0 test Sixian Yi 2025-01-17 17:42:24 -08:00
  • 8277730f10 test Sixian Yi 2025-01-17 17:34:13 -08:00
  • f2686275a3 test Sixian Yi 2025-01-17 17:31:10 -08:00
  • c6427ed32f always execute integration test even if previous notebook tests failed Sixian Yi 2025-01-17 03:48:35 -08:00
  • ac5b3451b7 rebase Sixian Yi 2025-01-16 18:02:48 -08:00
  • 7debd78459 tgi update Sixian Yi 2025-01-17 17:16:37 -08:00
  • 2dd09875d4 Update llama_stack/providers/tests/test_report.md Sixian Yi 2025-01-17 17:07:56 -08:00
  • 9ae7c3ad24 add tgi Sixian Yi 2025-01-17 16:39:48 -08:00
  • 5c5b8fe6b5 test report Sixian Yi 2025-01-17 15:12:08 -08:00
  • 3e7496e835
    fix vllm base64 image inference (#815) Xi Yan 2025-01-17 17:07:28 -08:00
  • 97053ba9d6 add local image Xi Yan 2025-01-17 17:06:20 -08:00
  • 3d4c53dfec
    add mcp runtime as default to all providers (#816) Dinesh Yeduguru 2025-01-17 16:40:58 -08:00
  • 6da3053c0e
    More generic image type for OCI-compliant container technologies (#802) Yuan Tang 2025-01-17 19:37:42 -05:00
  • acaa92fa24 add mcp runtime as default to all providers Dinesh Yeduguru 2025-01-17 16:22:00 -08:00
  • 12141a00e3 fix Xi Yan 2025-01-17 16:20:39 -08:00
  • 6d21da6e48 fix vllm base64 Xi Yan 2025-01-17 16:17:15 -08:00
  • 9d005154d7
    fix vllm template (#813) Xi Yan 2025-01-17 15:34:29 -08:00
  • eb60f04f86
    optional api dependencies (#793) Ashwin Bharambe 2025-01-17 15:26:53 -08:00
  • 76e08cfde0 PR tool call followups Aidan Do 2025-01-18 09:07:42 +11:00
  • 9659fe6792 check if dep is available before dfs Dinesh Yeduguru 2025-01-17 14:59:45 -08:00
  • 3ef1f0e1e2 add optional deps to dep__ for ordering Dinesh Yeduguru 2025-01-17 14:24:00 -08:00
  • 65e64f6877 optional api dependencies Ashwin Bharambe 2025-01-16 15:13:42 -08:00
  • e5fcdf8aa5 fix agent test w/ shields Xi Yan 2025-01-17 14:54:12 -08:00
  • 8cf7f72116 fix vllm template Xi Yan 2025-01-17 14:40:51 -08:00
  • 1f60c0286d
    cannot import name 'GreedySamplingStrategy' (#806) Aidan Do 2025-01-18 09:34:29 +11:00
  • d662f8a1f6 . Aidan Do 2025-01-18 08:55:41 +11:00
  • e1decaec9d
    Fixing small typo in quick start guide (#807) Paul McCarthy 2025-01-17 19:15:55 +00:00
  • 53b5f6b24a
    add json_schema_type to ParamType deps (#808) Dinesh Yeduguru 2025-01-17 11:02:25 -08:00
  • 06de2d686d add json_schema_type to ParamType deps Dinesh Yeduguru 2025-01-17 10:55:03 -08:00
  • adfa2c3413
    Some leftovers Yuan Tang 2025-01-17 12:16:04 -05:00
  • a1fb23b268 Fixing small typo in quick start guide Paul McCarthy 2025-01-17 14:31:57 +00:00
  • b37afca357 . Aidan Do 2025-01-17 10:43:02 +00:00
  • 403ebc6b59 Fix greedy import Aidan Do 2025-01-17 10:36:17 +00:00