Commit graph

  • 52b4766949 Start some integration tests with an OpenAI client Ben Browning 2025-04-09 13:55:34 -04:00
  • a1e9cff37c Update spec with latest changes as well Ben Browning 2025-04-09 10:08:10 -04:00
  • fcdeb3d7bf OpenAI completion prompt can also include tokens Ben Browning 2025-04-09 10:05:50 -04:00
  • a6cf8fa12b OpenAI completion prompt can also be an array Ben Browning 2025-04-09 09:28:50 -04:00
  • 24cfa1ef1a Mark inline vllm as OpenAI unsupported inference Ben Browning 2025-04-09 08:36:01 -04:00
  • de01b1455b Passthrough inference support for OpenAI-compatible APIs Ben Browning 2025-04-09 08:35:36 -04:00
  • 15d37fde19 Add unsupported OpenAI mixin to all remaining inference providers Ben Browning 2025-04-08 12:50:23 -04:00
  • 00c4493bda OpenAI-compatible completions and chats for litellm and together Ben Browning 2025-04-08 12:35:16 -04:00
  • 1dbdff1496 ollama OpenAI-compatible completions and chat completions Ben Browning 2025-04-08 09:29:49 -04:00
  • 5bc5fed6df Clean up some more usage of direct OpenAI types Ben Browning 2025-04-08 09:10:52 -04:00
  • 92fdf6d0c9 Use our own pydantic models for OpenAI Server APIs Ben Browning 2025-04-08 09:01:35 -04:00
  • a193c9fc3f Add OpenAI-Compatible models, completions, chat/completions endpoints Ben Browning 2025-04-07 21:27:06 -04:00
  • 662483f360 moved the existing quickstart page to detailed tutorial and made an even shorter quickstart to highlight value in as few lines of code as possible Francisco Javier Arceo 2025-04-09 14:52:28 -04:00
  • 1871cb9a71 Added coverage for the case where a vector DB was provided but no chunks were retrieved. ilya-kolchinsky 2025-04-09 19:53:59 +02:00
  • b4d216c3a2
    docs: Avoid bash script syntax highlighting for dark mode Yuan Tang 2025-04-09 13:49:54 -04:00
  • 2c034ab2ad fix: Mirror llama4 rope scaling fixes Ashwin Bharambe 2025-04-09 10:25:49 -07:00
  • fba633648c change model Francisco Javier Arceo 2025-04-09 13:14:09 -04:00
  • 026ce73ef8 adding some js to detect current browser theme Francisco Javier Arceo 2025-04-09 11:59:39 -04:00
  • 8353414487
    Merge pull request #1 from meta-llama/main Vaishnavi Hire 2025-04-09 11:25:24 -04:00
  • 19b5656083 setting default to light mode Francisco Javier Arceo 2025-04-09 11:04:02 -04:00
  • 3f0605a5c5 chore: Setting default screen setting to auto Francisco Javier Arceo 2025-04-09 10:44:32 -04:00
  • 72cc19a2c1 making <h3> font lighter for better visibility and moving some copy Francisco Javier Arceo 2025-04-09 10:32:30 -04:00
  • 127b62dee0 Raise an error when no vector DB IDs are provided to the query() method of the RAG (knowledge search) tool. ilya-kolchinsky 2025-04-09 16:07:20 +02:00
  • 3366937765
    Merge branch 'main' into docs-4 Francisco Arceo 2025-04-09 07:48:55 -06:00
  • c583bee415 handle feedback from mark Francisco Javier Arceo 2025-04-09 09:41:36 -04:00
  • 17b62c373a add tavily_search option to playground api Michael Clifford 2025-04-09 09:29:24 -04:00
  • 1bbb4f3dbd add tools demo page to playground Michael Clifford 2025-04-01 15:41:17 -04:00
  • ba76111db2 docs: add AMD ROCm of remote-vllm distro Alex He 2025-04-09 19:17:21 +08:00
  • a15ebfa46d Introducing a trailing message in the knowledge search tool reply that repeats the original query. ilya-kolchinsky 2025-04-09 12:28:10 +02:00
  • 513da16225
    chore: simplify running the demo UI Sébastien Han 2025-04-09 11:25:23 +02:00
  • 438b1168d1
    feat: ability to execute external providers Sébastien Han 2025-03-20 14:19:17 +01:00
  • 60282cd72b feat: adds test suite to verify provider's OAI compat endpoints Eric Huang 2025-04-08 21:06:45 -07:00
  • aff9e18f9f
    Merge branch 'meta-llama:main' into feat/litellm_sambanova_usage Jorge Piedrahita Ortiz 2025-04-08 16:02:58 -05:00
  • 8e6b622923 add llama4 maverick to sambanova inference models jhpiedrahitao 2025-04-08 16:02:08 -05:00
  • c04ab0133d In-progress: e2e notebook with partial Eval integration Jash Gulabrai 2025-04-08 14:08:01 -04:00
  • eab145eddb chore: fix hash for thollander/actions-comment-pull-request Ihar Hrachyshka 2025-04-08 13:57:02 -04:00
  • 524505d82e handle case where 'data' is not an attribute in unregister_toolgroup Paolo Dettori 2025-04-08 10:31:11 -04:00
  • 0c3f9f46f5 update test_register_and_unregister_toolgroup Paolo Dettori 2025-04-07 21:48:01 -04:00
  • da44d78b99 add integration testing for toolgroup registration Paolo Dettori 2025-03-14 21:12:51 -04:00
  • a1e6133523 fix unregister_toolgroup error Paolo Dettori 2025-03-13 10:33:53 -04:00
  • 582c785e65
    fix link Yuan Tang 2025-04-08 12:51:06 -04:00
  • 3b253be7da
    docs: Add recent release notes Yuan Tang 2025-04-08 12:50:48 -04:00
  • e27bfba4c2
    chore: remove unused tempdir in agent Sébastien Han 2025-04-08 10:58:52 +02:00
  • 28bcc48854 fix: type Eric Huang 2025-04-08 08:57:49 -07:00
  • 8cd10c1d05 feat: Add unit tests for NVIDIA safety Jash Gulabrai 2025-04-08 10:12:34 -04:00
  • ecf84a3b2f fix typo un sambanova llama4 scout model name jhpiedrahitao 2025-04-08 08:06:38 -05:00
  • 49bf4211da
    Merge branch 'main' into feat/litellm_sambanova_usage Jorge Piedrahita Ortiz 2025-04-08 07:40:56 -05:00
  • 12b0d2b485 updated code Sajikumar JS 2025-04-08 14:04:00 +05:30
  • 077dd51e0f Merge branch 'main' into add-watsonx-inference-adapter Sajikumar JS 2025-04-08 14:01:20 +05:30
  • 25374865a0 test fireworks Eric Huang 2025-04-07 21:58:42 -07:00
  • a23e5046ee adjusted based on latest feedback Francisco Javier Arceo 2025-04-07 23:40:40 -04:00
  • 35aac86997 update generate prompt format Ashwin Bharambe 2025-04-07 14:54:43 -07:00
  • e273a68567 fix: Fix NVIDIAEvalConfig config class path Jash Gulabrai 2025-04-07 17:27:21 -04:00
  • 76004eacb4 rename quant types to use _mixed naming Ashwin Bharambe 2025-04-07 12:57:58 -07:00
  • b239c57c54 fix Ashwin Bharambe 2025-04-07 11:57:20 -07:00
  • 84fd317783 updated playground rag page to use session id for persistent conversation Michael Clifford 2025-04-03 15:51:31 -04:00
  • 6ef46296f3
    refactor: move missing tests to test directory Sébastien Han 2025-04-07 21:13:32 +02:00
  • 63cf5dda50 allow changing model parallel size Ashwin Bharambe 2025-04-07 11:34:28 -07:00
  • 53f29eb8b9 appease the lint gods Suraj Subramanian 2025-04-07 11:31:02 -07:00
  • ff6c47d4e5 fold in meta-reference-quantized Ashwin Bharambe 2025-04-07 11:15:27 -07:00
  • f436348124 regen markdown Suraj Subramanian 2025-04-07 11:29:03 -07:00
  • 18c68c4950 clarifying wording on tool & ipython Suraj Subramanian 2025-04-07 11:26:34 -07:00
  • d05a4a8734 clarify tool v/s ipython role Suraj Subramanian 2025-04-07 11:08:10 -07:00
  • 7cf289ca03 regenerate markdown with eom tags and tool role Suraj Subramanian 2025-04-07 11:04:34 -07:00
  • cfaf9e0e8b revert some unintentional changes by copying source of truth to llama-models Ashwin Bharambe 2025-04-07 11:00:48 -07:00
  • 8a76fb32f3 Add info about eom and tool role Suraj Subramanian 2025-04-07 10:55:44 -07:00
  • a2734d24e7 fix: add tool-calling example with tool response Suraj Subramanian 2025-04-07 10:48:10 -07:00
  • 53a8086e37 several fixes Ashwin Bharambe 2025-04-07 10:31:20 -07:00
  • 5a7572706a Some small copy changes Francisco Javier Arceo 2025-04-07 11:35:51 -04:00
  • caf30f68be chore: Minor cleanup Jash Gulabrai 2025-04-07 11:06:29 -04:00
  • de5fc92803 fix: Remove print statements Jash Gulabrai 2025-04-07 10:53:13 -04:00
  • f939117dbf fix: Update NVIDIA Eval README Jash Gulabrai 2025-04-07 10:30:08 -04:00
  • 4317a0ddcc feat: Add NVIDIA Eval integration Jash Gulabrai 2025-04-07 10:24:42 -04:00
  • edf8610448
    tested with v0.2.1 Yu An 2025-04-07 15:02:46 +01:00
  • ec73b3d066
    Merge branch 'main' into feat/litellm_sambanova_usage Jorge Piedrahita Ortiz 2025-04-07 08:52:51 -05:00
  • f3f6e58688
    ci: introduce Mergify bot to notify on PR conflicts Sébastien Han 2025-03-17 15:53:53 +01:00
  • b0ed1381e6 some more minor changes Francisco Javier Arceo 2025-04-07 09:02:26 -04:00
  • 2bf0ca67cb Merge branch 'main' into add-watsonx-inference-adapter Sajikumar JS 2025-04-07 16:07:43 +05:30
  • 8a3e20068b
    Merge branch 'meta-llama:main' into preprocessors-api Ilya Kolchinsky 2025-04-07 12:23:33 +02:00
  • 7c1836bbbf
    Merge branch 'main' into update-getting-started-ollama-pull Matthew Farrellee 2025-04-07 06:04:13 -04:00
  • 3941d083ea
    Merge branch 'meta-llama:main' into preprocessors Ilya Kolchinsky 2025-04-07 12:03:11 +02:00
  • e2e2820c9a refactor: move all llama code to models/llama out of meta reference Ashwin Bharambe 2025-04-06 16:08:48 -07:00
  • aab91cd52d updated readme for watsonx inference Sajikumar JS 2025-04-07 10:49:08 +05:30
  • 5366c423ae Merge branch 'main' into add-watsonx-inference-adapter Sajikumar JS 2025-04-07 10:42:30 +05:30
  • 11b53acfb8 merged latest changes Francisco Javier Arceo 2025-04-06 23:20:56 -04:00
  • f822c583ee updated providers index page and some copy on getting started Francisco Javier Arceo 2025-04-04 21:57:06 -04:00
  • 1639fd8b75 rebased Francisco Javier Arceo 2025-04-06 22:54:40 -04:00
  • 415c555767 update prompt slightly Hardik Shah 2025-04-06 19:13:39 -07:00
  • f2b0c282ed make click more obvious Francisco Javier Arceo 2025-04-04 15:36:50 -04:00
  • d3ebc18559 final fixes Hardik Shah 2025-04-06 18:01:43 -07:00
  • 971566fd74 xfail for non-llama4 Hardik Shah 2025-04-06 17:38:17 -07:00
  • 541d0c6f1a minor fix Hardik Shah 2025-04-06 17:36:42 -07:00
  • 31453f3f79 update sys prompt Hardik Shah 2025-04-06 15:52:42 -07:00
  • d86ee6f386 tool calls and responses end with <|emo|> Hardik Shah 2025-04-06 15:38:13 -07:00
  • 9334338928 add 3 more test cases Hardik Shah 2025-04-06 12:59:18 -07:00
  • cd618e9ad0 update test to try multi-turn scenarios Hardik Shah 2025-04-06 12:13:59 -07:00
  • 8cf8bd35f8 Merge branch 'main' into add-watsonx-inference-adapter Sajikumar JS 2025-04-06 16:28:39 +05:30
  • eafbde4e17 multi-turn tool call test Hardik Shah 2025-04-05 20:26:22 -07:00
  • f47f7f1105 precommit Xi Yan 2025-04-05 20:01:47 -07:00
  • f9e45e6edf test inference Xi Yan 2025-04-05 19:59:10 -07:00