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

  • 5d7b611336
         Add JSON structured outputs to Ollama Provider (#680) Aidan Do 2025-01-03 04:05:51 +11:00
  • 8146dce11e
         Add missing newlines before printing the Dockerfile content (#700) Yuan Tang 2025-01-02 11:04:29 -06:00
  • c1987d6143
         Fix failing flake8 E226 check (#701) Yuan Tang 2025-01-02 11:04:07 -06:00
  • eee25db11d
         Add missing "inline::" prefix for providers in building_distro.md (#702) Yuan Tang 2025-01-02 11:03:30 -06:00
  • a6c206ea66
         [bugfix] fix prompt_adapter interleaved_content_convert_to_raw (#696) Xi Yan 2024-12-30 16:40:36 -08:00
  • 7c1e3daa75
         [bugfix] fix meta-reference agents w/ safety multiple model loading pytest (#694) Xi Yan 2024-12-30 16:25:46 -08:00
  • 8ba29b19f2
         Minor Quick Start documentation updates. (#692) Derek Slager 2024-12-30 14:19:05 -08:00
  • 694adb1501
         [bugfix] fix broken vision inference, change serialization for bytes (#693) Xi Yan 2024-12-30 13:57:41 -08:00
  • 79f8bc8416
         Update index.md raghotham 2024-12-30 11:32:28 -08:00
  • 54f8aab61e copy getting_started Xi Yan 2024-12-30 10:42:28 -08:00
  • 0e098c483b link getting started Xi Yan 2024-12-30 09:47:10 -08:00
  • 3c72c034e6
         [remove import *] clean up import *'s (#689) Xi Yan 2024-12-27 15:45:44 -08:00
  • 70db039ff4 fix client-sdk memory/safety test Xi Yan 2024-12-26 15:48:28 -08:00
  • b6aca4c8bb fix client-sdk agents/inference test Xi Yan 2024-12-26 15:44:34 -08:00
  • 4e1d0a2fc5 update playground doc video Xi Yan 2024-12-26 14:50:19 -08:00
  • 28ce511986 fix --endpoint docs Xi Yan 2024-12-26 14:32:07 -08:00
  • 7ba95a8e74
         docs: update evals_reference/index.md (#675) Ikko Eltociear Ashimine 2024-12-27 04:32:37 +09:00
  • 21fb92d7cf
         Add 3.3 70B to Ollama inference provider (#681) Aidan Do 2024-12-26 17:15:58 +11:00
  • fa371fdc9e
         Removed unnecessary CONDA_PREFIX env var in installation guide (#683) Yuan Tang 2024-12-23 16:17:30 -05:00
  • 987e651755
         Add missing venv option in --image-type (#677) Yuan Tang 2024-12-22 00:10:13 -05:00
  • bae197c37e
         Fix post training apis broken by torchtune release (#674) Botao Chen 2024-12-20 16:12:02 -08:00
  • 06cb0c837e
         [torchtune integration] post training + eval (#670) Botao Chen 2024-12-20 13:43:13 -08:00
  • c8be0bf1c9
         Tools API with brave and MCP providers (#639) Dinesh Yeduguru 2024-12-19 21:25:17 -08:00
  • 17fdb47e5e
         Add Llama 70B 3.3 to fireworks (#654) Aidan Do 2024-12-20 12:32:49 +11:00
  • 8b8d1c1ef4
         fix trace starting in library client (#655) Dinesh Yeduguru 2024-12-19 16:13:52 -08:00
  • ddf37ea467
         Fixed imports for inference (#661) cdgamarose-nv 2024-12-19 14:19:36 -08:00
  • 540fc4d717
         Fix Meta reference GPU implementation (#663) Ashwin Bharambe 2024-12-19 14:09:45 -08:00
  • f19eb8eee3 Update types in parallel_utils for meta-refernece-gpu impl Ashwin Bharambe 2024-12-19 13:58:20 -08:00
  • b33086d632 Adding @vladimirivic to the owners file Vladimir Ivic 2024-12-19 11:32:05 -08:00
  • 5be2ea37b1 fix context_retriever model->model_id Xi Yan 2024-12-19 12:52:00 -08:00
  • 03607a68c7
         remove unused telemetry related code for console (#659) Dinesh Yeduguru 2024-12-19 11:21:11 -08:00
  • 36b4fe02cc
         [4/n][torchtune integration] support lazy load model during inference (#620) Botao Chen 2024-12-18 16:30:53 -08:00
  • 3b4b2ea30c fix replace_env_vars bug Ashwin Bharambe 2024-12-18 13:48:30 -08:00
  • 12cbed1617 Register Message and ResponseFormat Ashwin Bharambe 2024-12-18 10:32:25 -08:00
  • ceadaf1840 Dont include 3B / 1B models for bedrock since they arent ondemand Ashwin Bharambe 2024-12-18 06:30:02 -08:00
  • c39a3777b5 Make bedrock "just" work Ashwin Bharambe 2024-12-18 06:22:14 -08:00
  • d6fcdefec7 Bump version to 0.0.63 v0.0.63 Ashwin Bharambe 2024-12-17 23:15:27 -08:00
  • f1d6cb22d7 Update URL type to avoid string-ifying and creating complexity Ashwin Bharambe 2024-12-17 22:48:47 -08:00
  • 75e72cf2fc model_type=llm for filering available models for playground Xi Yan 2024-12-17 19:42:38 -08:00
  • 2f9fdb0ea7 Update notebook Ashwin Bharambe 2024-12-17 18:51:51 -08:00
  • 0fb4b7de6f Add more debugging logs to when llama guard fails Ashwin Bharambe 2024-12-17 17:11:21 -08:00
  • eea478618d Bump version to 0.0.62 v0.0.62 Ashwin Bharambe 2024-12-17 18:19:47 -08:00
  • af8f1b3531 model selection playground fix Xi Yan 2024-12-17 18:12:59 -08:00
  • 3700022d6f
         store attributes values in builtin types to avoid otel warnings (#649) Dinesh Yeduguru 2024-12-17 17:10:43 -08:00
  • 0e2a99e223
         Update Cerebras from Llama 3.1 to 3.3 (#645) Henry Tu 2024-12-17 19:28:24 -05:00
  • b7a7caa9a8 Fix conversion to RawMessage everywhere Ashwin Bharambe 2024-12-17 13:38:01 -08:00
  • fbca51d6da Fix to conda env build script Ashwin Bharambe 2024-12-17 12:19:34 -08:00
  • 0452c6a0c7 add missing init file Ashwin Bharambe 2024-12-17 11:48:28 -08:00
  • 8de8eb03c8
         Update the "InterleavedTextMedia" type (#635) Ashwin Bharambe 2024-12-17 11:18:31 -08:00
  • 10eb31badf
         docs: Update getting_started.ipynb link to correct jupyter notebook path in README.md (#636) Arun Brahma 2024-12-18 00:41:13 +05:30
  • 99f331f5c8
         [bugfix] no shield_call when there's no shields configured (#642) Xi Yan 2024-12-17 11:10:19 -08:00
  • c2f7905fa4 Fix bedrock inference impl Ashwin Bharambe 2024-12-16 14:22:34 -08:00
  • eb37fba9da Small fix to library client Ashwin Bharambe 2024-12-16 14:08:30 -08:00
  • 5e08812bcb Add Dinesh to be a code owner Ashwin Bharambe 2024-12-16 13:00:50 -08:00
  • 2e5bfcd42a
         Update Telemetry API so OpenAPI generation can work (#640) Ashwin Bharambe 2024-12-16 13:00:14 -08:00
  • 78e2bfbe7a
         [tests] add client-sdk pytests & delete client.py (#638) Xi Yan 2024-12-16 12:04:56 -08:00
  • cb8a28c128
         Doc: Ollama command references non-existent file (#632) Aidan Do 2024-12-16 01:52:28 +11:00
  • 815f4af6cf
         add colab notebook & update docs (#619) Xi Yan 2024-12-13 19:15:15 -08:00
  • 20383bfea5
         [3/n][torchtune integration] add validation logic (#600) Botao Chen 2024-12-13 16:35:06 -08:00
  • c294a01c4b
         [2/n][torchtune integration] implement job management and return training artifacts (#593) Botao Chen 2024-12-13 15:00:04 -08:00
  • 5764a95912
         Add missing environments field for vLLM provider (#623) Yuan Tang 2024-12-13 17:06:27 -05:00
  • 516e1a3e59
         add embedding model by default to distribution templates (#617) Dinesh Yeduguru 2024-12-13 12:48:00 -08:00
  • e893b22868 export LibraryClient Ashwin Bharambe 2024-12-13 12:07:42 -08:00
  • 6de92a6c33
         Reformat distributions table (#608) Yuan Tang 2024-12-13 14:45:17 -05:00
  • 4800247b5c minor Ashwin Bharambe 2024-12-13 11:44:08 -08:00
  • aeb76390fc
         [1/n] torchtune <> llama-stack integration skeleton (#540) Botao Chen 2024-12-13 11:05:35 -08:00
  • 53b3a1e345
         Update kotlin docs to 0.0.58 (#614) Riandy 2024-12-13 05:09:13 +08:00
  • 2a9b13dd52
         add test for completion logprobs (#532) Matthew Farrellee 2024-12-12 15:19:48 -05:00
  • 96e158eaac
         Make embedding generation go through inference (#606) Dinesh Yeduguru 2024-12-12 11:47:50 -08:00
  • a14785af46
         [docs] add playground ui docs (#592) Xi Yan 2024-12-12 10:40:38 -08:00
  • 8b45d147df
         [/datasetio] drop columns not specified by dataset schema for huggingface provider (#611) Xi Yan 2024-12-12 10:23:09 -08:00
  • b7cb06f004
         Allow using an "inline" version of Chroma using PersistentClient (#567) Ashwin Bharambe 2024-12-11 16:02:04 -08:00
  • 41487e6ed1
         refactor scoring/eval pytests (#607) Xi Yan 2024-12-11 10:47:37 -08:00
  • 47b2dc8ae3
         Revert "add model type to APIs" (#605) Dinesh Yeduguru 2024-12-11 10:17:54 -08:00
  • 8e33db6015
         add model type to APIs (#588) Dinesh Yeduguru 2024-12-11 10:16:53 -08:00
  • 7e1d628864
         Fix some typos in distributions/providers docs (#603) Yuan Tang 2024-12-11 13:10:52 -05:00
  • b52df5fe5b
         add completion api support to nvidia inference provider (#533) Matthew Farrellee 2024-12-11 13:08:38 -05:00
  • 07c72c4256
         Add vLLM to API providers and distributions tables (#604) Yuan Tang 2024-12-11 13:05:47 -05:00
  • a4bcfb8bba
         [/scoring] add ability to define aggregation functions for scoring functions & refactors (#597) Xi Yan 2024-12-11 10:03:42 -08:00
  • e128f2547a
         add tracing back to the lib cli (#595) Dinesh Yeduguru 2024-12-11 08:44:20 -08:00
  • 1c03ba239e
         [#342] RAG - fix PDF format in vector database (#551) Aidan Do 2024-12-11 16:33:27 +11:00
  • f5c36c47ed
         Added support for llama 3.3 model (#601) varunfb 2024-12-10 20:03:31 -08:00
  • 76eb558bde
         doc: llama-stack build --config help text references old directory (#596) Aidan Do 2024-12-11 12:42:02 +11:00
  • e0d5be41fe
         add nvidia nim inference provider to docs (#534) Matthew Farrellee 2024-12-10 16:23:56 -05:00
  • e2054d53e4
         Fix issue 586 (#594) v0.0.61 Xi Yan 2024-12-10 10:22:04 -08:00
  • 02b43be9d7 Bump version to 0.0.61 Ashwin Bharambe 2024-12-10 10:18:44 -08:00
  • fa68ded07c Remove the unnecessary message after llama stack build Ashwin Bharambe 2024-12-10 09:46:37 -08:00
  • 885bb0900b memory retrival to print only the bytes injected Dinesh Yeduguru 2024-12-10 09:32:18 -08:00
  • 2e3d3a62a5 Revert "add tracing to library client (#591)" Dinesh Yeduguru 2024-12-10 08:50:20 -08:00
  • 16d103842a Revert "await end_trace in libcli" Dinesh Yeduguru 2024-12-10 08:47:32 -08:00
  • f969b561ea Revert "Disable telemetry in library client for now" Dinesh Yeduguru 2024-12-10 08:47:18 -08:00
  • 686f8d5b8d remove info logging in agent instance Dinesh Yeduguru 2024-12-10 08:40:42 -08:00
  • 1ad691bb04 Bump version to 0.0.60 Ashwin Bharambe 2024-12-09 22:19:51 -08:00
  • 176ebddf47 Disable telemetry in library client for now Ashwin Bharambe 2024-12-09 22:17:25 -08:00
  • baae4f7b51 Bump version to 0.0.59 Ashwin Bharambe 2024-12-09 21:22:20 -08:00
  • a4d8a6009a
         Fixes for library client (#587) Ashwin Bharambe 2024-12-09 17:14:37 -08:00
  • 7615da78b8 await end_trace in libcli Dinesh Yeduguru 2024-12-09 15:54:42 -08:00
  • bc1fddf1df
         add tracing to library client (#591) Dinesh Yeduguru 2024-12-09 15:46:26 -08:00
  • ab7145a04f minor refactor Xi Yan 2024-12-09 15:43:12 -08:00
  • cd40a5fdbf
         update template run.yaml to include openai api key for braintrust (#590) Xi Yan 2024-12-09 15:40:59 -08:00