Commit graph

  • e233284577
    chore: removed unused class Sébastien Han 2025-05-26 15:43:14 +02:00
  • f52b97843b
    chore: allow to pass CA cert to remote vllm Sébastien Han 2025-05-26 11:50:44 +02:00
  • a00d2dbfdc fix Ashwin Bharambe 2025-05-25 13:49:10 -07:00
  • c10a3a5936 fix: match mcp headers in provider data to Responses API shape Ashwin Bharambe 2025-05-25 13:47:11 -07:00
  • cddc1f3524 several fixes Ashwin Bharambe 2025-05-25 10:35:48 -07:00
  • bf8a73e09a fix(tools): do not index tools, only index toolgroups Ashwin Bharambe 2025-05-25 00:20:36 -07:00
  • d876aa1eb4
    Merge branch 'main' into cprint raghotham 2025-05-24 23:26:56 -07:00
  • ddddaeae74
    Update conf.py raghotham 2025-05-24 23:23:07 -07:00
  • 917ff05e82 chore: split routing_tables into individual files Ashwin Bharambe 2025-05-24 23:03:16 -07:00
  • ee36a54a42 fix Ashwin Bharambe 2025-05-24 22:39:47 -07:00
  • f1e1ab7dfc chore: split routers into individual files (inference, tool, vector_io, eval_scoring) Ashwin Bharambe 2025-05-24 22:14:54 -07:00
  • 9ff501f88e [𝘀𝗽𝗿] initial version Ashwin Bharambe 2025-05-24 22:31:30 -07:00
  • 0a636629a0 [𝘀𝗽𝗿] changes to main this commit is based on Ashwin Bharambe 2025-05-24 22:31:29 -07:00
  • 855000a4cc [𝘀𝗽𝗿] initial version Ashwin Bharambe 2025-05-24 22:31:25 -07:00
  • 9f20e5cdca [𝘀𝗽𝗿] changes to main this commit is based on Ashwin Bharambe 2025-05-24 22:31:25 -07:00
  • 4a1643c78a [𝘀𝗽𝗿] initial version Ashwin Bharambe 2025-05-24 22:31:21 -07:00
  • 36e03b9c31 [𝘀𝗽𝗿] changes to main this commit is based on Ashwin Bharambe 2025-05-24 22:31:21 -07:00
  • 1319fe1b98 [𝘀𝗽𝗿] initial version Ashwin Bharambe 2025-05-24 22:31:17 -07:00
  • d6eac9f219 [𝘀𝗽𝗿] changes to main this commit is based on Ashwin Bharambe 2025-05-24 22:31:17 -07:00
  • 2527b78179 [𝘀𝗽𝗿] initial version Ashwin Bharambe 2025-05-24 22:31:12 -07:00
  • 625cecbf81 [𝘀𝗽𝗿] changes to main this commit is based on Ashwin Bharambe 2025-05-24 22:31:12 -07:00
  • 2c3746ed90 [𝘀𝗽𝗿] initial version Ashwin Bharambe 2025-05-24 22:31:08 -07:00
  • 43564050ad [𝘀𝗽𝗿] changes to main this commit is based on Ashwin Bharambe 2025-05-24 22:31:08 -07:00
  • 146fe19253 [𝘀𝗽𝗿] initial version Ashwin Bharambe 2025-05-24 22:31:04 -07:00
  • ab998a5fef chore: split routers into individual files (datasets) Ashwin Bharambe 2025-05-24 15:03:08 -07:00
  • 8658109454 fix: make cprint write to stderr Raghotham Murthy 2025-05-24 21:46:40 -07:00
  • af87945427 [𝘀𝗽𝗿] initial version Ashwin Bharambe 2025-05-24 17:03:40 -07:00
  • 48865ad150 [𝘀𝗽𝗿] initial version Ashwin Bharambe 2025-05-24 16:41:01 -07:00
  • 8ba43cbcd6 [𝘀𝗽𝗿] initial version Ashwin Bharambe 2025-05-24 15:23:52 -07:00
  • 45a7f9a145 better fix Ashwin Bharambe 2025-05-24 14:39:12 -07:00
  • 83d02df028 fix(telemetry): get rid of annoying sqlite span export error Ashwin Bharambe 2025-05-24 14:30:31 -07:00
  • a5132b4857 more test fixes Ashwin Bharambe 2025-05-24 12:02:28 -07:00
  • cc6662db7b add output to pytest logs to see wtf is happening Ashwin Bharambe 2025-05-24 08:17:33 -07:00
  • 41b84cbe66 disable test_inference_store_tool_calls also Ashwin Bharambe 2025-05-24 07:58:33 -07:00
  • 6294f31226 skip mcp test for http client Ashwin Bharambe 2025-05-24 07:56:14 -07:00
  • 3d0509687e fix: disable test_responses_store Ashwin Bharambe 2025-05-24 07:40:36 -07:00
  • d92e69b9ee add mcp dep Ashwin Bharambe 2025-05-24 07:38:45 -07:00
  • bc7901e3bd fixes and enable tool_runtime tests Ashwin Bharambe 2025-05-24 07:27:53 -07:00
  • 9f7ed4be43 fixes, add auth test Ashwin Bharambe 2025-05-23 16:57:46 -07:00
  • 5937d94da5 feat: enable MCP execution in Response implementation Ashwin Bharambe 2025-05-22 20:21:47 -07:00
  • fc88c7cb3c keep post-training test Raghotham Murthy 2025-05-24 07:07:01 -07:00
  • 80b202817b fix precommit error Raghotham Murthy 2025-05-24 06:39:10 -07:00
  • 5ee1b71408 fix: skip failing tests Raghotham Murthy 2025-05-24 06:28:44 -07:00
  • 0f70e7003c
    Merge branch 'main' into update-setuptools Francisco Arceo 2025-05-23 22:22:37 -06:00
  • 092baab0ca
    fix(security): Upgrade setuptools to v80.8.0. Fixes CVE-2025-47273 Yuan Tang 2025-05-23 22:57:32 -04:00
  • 497b93e6dc
    lint Yuan Tang 2025-05-23 22:46:49 -04:00
  • 496d95825a
    docs: Update CHANGELOG.md Yuan Tang 2025-05-23 22:45:53 -04:00
  • de47dc4d8b feat: add responses input items api Eric Huang 2025-05-23 18:37:10 -07:00
  • f39d1732ea list responses Eric Huang 2025-05-23 13:00:58 -07:00
  • 98320d4eb2 feat: allow using llama-stack-library-client from verifications Ashwin Bharambe 2025-05-22 20:21:47 -07:00
  • 4e8e2104c0 run ui Eric Huang 2025-05-23 11:10:32 -07:00
  • 61a9c14ea7 fix: signature change to match OpenAI SDK Ashwin Bharambe 2025-05-23 10:52:14 -07:00
  • fb5cf1f353 chore: add sqlalchemy to test dependencies Eric Huang 2025-05-23 10:30:13 -07:00
  • 9352d9b42c add test for streaming, test against server Ashwin Bharambe 2025-05-22 16:13:07 -07:00
  • 0d67e17a91 feat: accept MCP authorization headers for MCP toolgroups Ashwin Bharambe 2025-05-22 14:39:59 -07:00
  • ecd8f2113a chat completion, testing Eric Huang 2025-05-22 21:44:14 -07:00
  • c5c495da20 feat: add MCP tool signature to Responses API Ashwin Bharambe 2025-05-22 16:28:48 -07:00
  • f1f179d8ca fix: openai provider model id Eric Huang 2025-05-22 12:10:04 -07:00
  • a1b356a2a2 impl Eric Huang 2025-05-21 21:59:34 -07:00
  • 5322c45116
    fix: use proper service account for kube auth Sébastien Han 2025-05-21 23:23:29 +02:00
  • 3166efdf56
    fix: only print routes that match the runtime config Sébastien Han 2025-05-21 23:06:58 +02:00
  • 6a2a0836c5 Feature: Configuring search modes for RAG - Address review Varsha Prasad Narsing 2025-05-21 10:57:37 -07:00
  • 2060fdba7f fix: sqlite_vec keyword implementation Varsha Prasad Narsing 2025-05-07 16:05:25 -07:00
  • e2a7022d3c feat (RAG): Implement configurable search mode in RAGQueryConfig Varsha Prasad Narsing 2025-04-14 16:53:17 -07:00
  • e12df4293b
    Merge branch 'main' into feat/sambanova-safety Jorge Piedrahita Ortiz 2025-05-21 11:32:42 -05:00
  • 6b14199233
    docs: misc cleanup Sébastien Han 2025-05-21 14:05:06 +02:00
  • c32db30281
    chore: clarify cache_ttl to be key_recheck_period Sébastien Han 2025-05-21 09:35:34 +02:00
  • 2fa63742d2
    chore: refactor workflow writting Sébastien Han 2025-05-21 14:26:37 +02:00
  • 3f9af163e8
    chore: remove k8s auth in favor of k8s jwks endpoint Sébastien Han 2025-05-20 11:45:26 +02:00
  • f6fb4a5865 add context to distinguish multiple credentials for the same (user, provider) Ashwin Bharambe 2025-05-20 19:41:43 -07:00
  • e6ddf5dac7 add basic integration test Ashwin Bharambe 2025-05-20 18:20:16 -07:00
  • 6e57929ede feat: basic implementation and usage of Credentials API for MCP Ashwin Bharambe 2025-05-19 16:51:03 -07:00
  • f28dfc73d5 Add SambaNova safety addaptor jhpiedrahitao 2025-05-20 16:38:05 -05:00
  • b43cdaaed5 updates Ashwin Bharambe 2025-05-20 13:51:28 -07:00
  • c4d32600f2 fixes Ashwin Bharambe 2025-05-19 12:15:37 -07:00
  • e4a7f482de add expires_at Ashwin Bharambe 2025-05-18 18:01:00 -07:00
  • 9a017ba605 fix Ashwin Bharambe 2025-05-18 12:31:52 -07:00
  • ba0fcdef06 naming Ashwin Bharambe 2025-05-18 11:42:01 -07:00
  • 226dc60775 feat: introduce a /credentials API for specifying ephemeral provider-specific keys Ashwin Bharambe 2025-05-18 11:35:45 -07:00
  • 7ee1ae0a3d feat: Extend the oauth_token provider to allow for token introspection Gordon Sim 2025-05-19 18:09:41 +01:00
  • 01fdae0adb XXX Ihar Hrachyshka 2025-05-20 13:06:35 -04:00
  • 9607140e24 ci: Clean up disk when testing post-training Ihar Hrachyshka 2025-05-20 12:46:44 -04:00
  • 55d88ac194 chore: Updated readme Francisco Javier Arceo 2025-05-20 10:40:38 -04:00
  • 189b6deb89 fix: unit tests Jash Gulabrai 2025-05-20 09:58:07 -04:00
  • 1d94f3617a fix: Pass model param as configuration name to NeMo Customizer Jash Gulabrai 2025-05-20 09:43:51 -04:00
  • dacd522f57 feat(quota): support per‑client and anonymous server‑side request quotas Wen Liang 2025-05-02 16:58:20 -04:00
  • 602e4a90c1
    chore: collapse all local hook under the same repo Sébastien Han 2025-05-20 14:58:43 +02:00
  • b1ab9dce81 fix: synchronize concurrent coroutines checking key set Gordon Sim 2025-05-20 13:02:31 +01:00
  • c482dfb5f7 feat: add llama stack rm and llama stack list commands Abhishek koserwal 2025-05-13 13:41:33 +05:30
  • f0a142f5a8
    Merge branch 'main' into patch-metadata Francisco Arceo 2025-05-20 03:08:53 -06:00
  • 9d28b731e3
    ci: enable ruff output format for github Sébastien Han 2025-05-20 10:53:20 +02:00
  • 490e77bffa feat: allow access attributes for resources to be configured Gordon Sim 2025-05-06 18:54:58 +01:00
  • 9c8167edd5 feat: Add "instructions" support to responses API Derek Higgins 2025-05-19 17:21:47 +01:00
  • 51b68b4be6 Merge branch 'main' into nvidia-e2e-notebook Jash Gulabrai 2025-05-19 09:23:07 -04:00
  • e9bcb0e827
    feat: export distribution container build artifacts Sébastien Han 2025-05-16 11:37:56 +02:00
  • 856e27c6df Update BuildConfig.external_providers_dir datatype plus fallout. Michael Anstis 2025-05-19 09:42:01 +01:00
  • de8105e7bf
    fix: remove wrong deprecated warning Sébastien Han 2025-05-19 10:34:02 +02:00
  • e89e1d0cc2 Pass external_config_dir to BuildConfig Michael Anstis 2025-05-16 14:07:09 +01:00
  • 3bc175320b apis, alt Eric Huang 2025-05-18 21:20:00 -07:00
  • 5a807da6af
    Merge branch 'main' into patch-metadata Francisco Arceo 2025-05-18 19:34:14 -06:00