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

  • 52977e56a8
         docs: update Agent documentation (#1333) ehhuang 2025-03-01 22:34:52 -08:00
  • 46b0a404e8
         chore: remove straggler references to llama-models (#1345) Ashwin Bharambe 2025-03-01 14:26:03 -08:00
  • 8bbd52bb9f
         chore: remove dependency on llama_models completely (#1344) Ashwin Bharambe 2025-03-01 12:48:08 -08:00
  • 7131d5ddeb
         chore: remove start_venv.sh (#1341) Reid 2025-03-02 03:22:06 +08:00
  • 6609d4ada4
         feat: allow conditionally enabling providers in run.yaml (#1321) Ashwin Bharambe 2025-03-01 11:19:14 -08:00
  • 81c6ef5c1c
         fix: don't update tool_config inplace (#1338) ehhuang 2025-03-01 10:40:00 -08:00
  • 327b17e5f0
         chore: add container cmd check in start_stack.sh (#1340) Reid 2025-03-02 02:39:32 +08:00
  • 7cff9f504f
         fix: raise error when request param failed to convert (#1339) ehhuang 2025-03-01 10:39:05 -08:00
  • dc069025f5
         chore: fix typo (#1343) Reid 2025-03-02 02:36:04 +08:00
  • 21ec67356c
         fix: RAG with documents (#1337) ehhuang 2025-02-28 16:51:00 -08:00
  • 7854af8b52
         docs: update user prompt example (#1329) ehhuang 2025-02-28 16:42:29 -08:00
  • ba3bedc7e9
         test: remove old test (#1334) ehhuang 2025-02-28 16:42:13 -08:00
  • 2faee24873
         chore: better raise (#1335) ehhuang 2025-02-28 16:41:20 -08:00
  • 7ad7e3b970 fix: only install llama-stack package, deps are now correctly incorporated Ashwin Bharambe 2025-02-28 16:12:05 -08:00
  • 5e24409189 Bump version to 0.1.5.1 v0.1.5.1 release-0.1.5.1 github-actions[bot] 2025-02-28 22:13:25 +00:00
  • 040f1f04f7 Release candidate 0.1.5.1rc1 v0.1.5.1rc1 github-actions[bot] 2025-02-28 22:13:25 +00:00
  • 9b6a2577b1
         docs: Update llama-stack version in README.md (#1330) Surya Prakash Pathak 2025-02-28 21:37:03 +00:00
  • 82fa0803fa
         chore: refactor client tool in test (#1331) Xi Yan 2025-02-28 12:29:50 -08:00
  • 75cda30df7 fix: replace eval with json decoding for format_adapter (#1328) Xi Yan 2025-02-28 11:25:23 -08:00
  • 31c9c6c62f fix: replace eval with json decoding (#1327) Xi Yan 2025-02-28 11:10:45 -08:00
  • 15f69e75ff
         fix: replace eval with json decoding for format_adapter (#1328) Xi Yan 2025-02-28 11:25:23 -08:00
  • 5547ef953c
         feat: enhance OpenAPI spec to include Error types (#1320) Ashwin Bharambe 2025-02-28 11:16:12 -08:00
  • 6520baebed
         fix: replace eval with json decoding (#1327) Xi Yan 2025-02-28 11:10:45 -08:00
  • 66cd128ab5
         docs: update the downloaded list doc (#1266) Reid 2025-03-01 02:10:12 +08:00
  • 14c442f177
         chore: update cmd check (#1293) Reid 2025-03-01 02:08:05 +08:00
  • ea4f13cc20
         chore: add container cmd check (#1306) Reid 2025-03-01 02:07:24 +08:00
  • 5366dab31e
         docs: update build doc (#1262) Reid 2025-03-01 02:03:45 +08:00
  • 83dc8fbdff
         test: cleanup embedding model test suite (#1322) Matthew Farrellee 2025-02-28 12:02:36 -06:00
  • c91548fe07
         build(container): misc improvements (#1291) Sébastien Han 2025-02-28 19:01:52 +01:00
  • 18ab1985da
         fix: Make remote::vllm compatible with vLLM <= v0.6.3 (#1325) Yuan Tang 2025-02-28 12:48:49 -05:00
  • 6fa257b475
         chore(lint): update Ruff ignores for project conventions and maintainability (#1184) Sébastien Han 2025-02-28 18:36:49 +01:00
  • 3b57d8ee88
         feat: add prompt-format list (#1222) Reid 2025-03-01 01:27:22 +08:00
  • 234408f411
         docs: Add link to distributions guide in quick start guide (#1326) Yuan Tang 2025-02-28 12:18:02 -05:00
  • 9ac7f1c8da Bump version to 0.1.5 v0.1.5 github-actions[bot] 2025-02-28 08:14:18 +00:00
  • 56798fbdda Release candidate 0.1.5rc3 v0.1.5rc3 github-actions[bot] 2025-02-28 08:14:18 +00:00
  • 7f9b767277
         fix: check conda env name using basepath in exec.py (#1301) Dinesh Yeduguru 2025-02-27 23:07:23 -08:00
  • 8efa53daf1
         fix: Agent telemetry inputs/outputs should be structured (#1302) Hardik Shah 2025-02-27 23:06:37 -08:00
  • caffafd101
         feat: update the default system prompt for 3.2/3.3 models (#1310) ehhuang 2025-02-27 23:05:42 -08:00
  • ece354eedd test: dont hardcode faiss as provider in the tests please Ashwin Bharambe 2025-02-27 22:54:34 -08:00
  • 4c8a0fa8dc fix: ensure ollama embedding model is registered properly in the template Ashwin Bharambe 2025-02-27 22:49:06 -08:00
  • 834d117077 Release candidate 0.1.5rc2 v0.1.5rc2 github-actions[bot] 2025-02-28 05:04:13 +00:00
  • 999195fe5b
         fix: [Litellm]Do not swallow first token (#1316) Hardik Shah 2025-02-27 20:53:47 -08:00
  • 7780fc92d5
         fix: update getting_started notebook to pass nbeval (#1318) Xi Yan 2025-02-27 20:13:00 -08:00
  • 52ed2a7c35 Release candidate 0.1.5rc1 v0.1.5rc1 github-actions[bot] 2025-02-28 03:38:04 +00:00
  • 6824d23dc9
         test: Only run embedding tests for remote::nvidia (#1317) Yuan Tang 2025-02-27 22:35:52 -05:00
  • a9f5c5bfca
         fix: Incorrect import path for print_subcommand_description() (#1315) Yuan Tang 2025-02-27 21:50:41 -05:00
  • f4df3a76d9
         fix: Incorrect import path for print_subcommand_description() (#1314) Yuan Tang 2025-02-27 21:35:49 -05:00
  • 3567274183
         fix: Incorrect import path for print_subcommand_description() (#1313) Yuan Tang 2025-02-27 21:24:01 -05:00
  • 076d2f349d
         fix: litellm tool call parsing event type to in_progress (#1312) Xi Yan 2025-02-27 18:00:27 -08:00
  • 2f7683bc5f
         fix: Structured outputs for recursive models (#1311) Hardik Shah 2025-02-27 17:31:53 -08:00
  • 94e2186bb8
         chore: add subcommands description in help (#1219) Reid 2025-02-28 09:00:27 +08:00
  • e28cedd833
         feat: add nvidia embedding implementation for new signature, task_type, output_dimention, text_truncation (#1213) Matthew Farrellee 2025-02-27 18:58:11 -06:00
  • 73c6f6126f
         fix: Avoid unexpected keyword argument for sentence_transformers (#1269) Luis Tomas Bolivar 2025-02-28 01:47:26 +01:00
  • c2d2a80b0a
         docs: update the output of llama-stack-client models list (#1271) Reid 2025-02-28 08:46:38 +08:00
  • 264c2c46db
         build: Add dotenv file for running tests with uv (#1251) Yuan Tang 2025-02-27 19:42:55 -05:00
  • 04de2f84e9
         fix: register provider model name and HF alias in run.yaml (#1304) Ashwin Bharambe 2025-02-27 16:39:23 -08:00
  • c54164556a
         fix: update notebooks to avoid using the nutsy --image-name __system__ thing (#1308) Ashwin Bharambe 2025-02-27 16:39:04 -08:00
  • a34f3aafcf
         fix: don't include tool args not in the function definition (#1307) ehhuang 2025-02-27 16:25:30 -08:00
  • 663c6b0537
         fix: duplicate ToolResponseMessage in Turn message history (#1305) Xi Yan 2025-02-27 15:06:47 -08:00
  • 6e8dfa727d fix: precommits ugh why wont they run correctly because they dont have the right dependencies Ashwin Bharambe 2025-02-27 15:02:04 -08:00
  • 4780223544 fix: groq now depends on litellm Ashwin Bharambe 2025-02-27 14:07:12 -08:00
  • 928a39d17b
         feat(providers): Groq now uses LiteLLM openai-compat (#1303) Ashwin Bharambe 2025-02-27 13:16:50 -08:00
  • 564f0e5f93
         fix: Revert "chore: remove vector_db_id from AgentSessionInfo" (#1299) Xi Yan 2025-02-27 10:37:15 -08:00
  • 200ef29233
         chore: remove vector_db_id from AgentSessionInfo (#1296) Xi Yan 2025-02-27 10:13:10 -08:00
  • 981fc3c93c
         fix(test): no need to specify tool prompt format explicitly in tests (#1295) Ashwin Bharambe 2025-02-27 10:09:57 -08:00
  • fc5aff3ccf
         feat: ability to retrieve agents session, turn, step by ids (#1286) Xi Yan 2025-02-27 09:45:14 -08:00
  • 0762c61402
         feat: don't silently ignore incorrect toolgroup (#1285) ehhuang 2025-02-27 05:11:09 -08:00
  • 99b6925ad8
         feat: add nemo retriever text embedding models to nvidia inference provider (#1218) Matthew Farrellee 2025-02-26 23:18:34 -06:00
  • 23b65b6cee
         fix(test): update client-sdk tests to handle tool format parametrization better (#1287) Ashwin Bharambe 2025-02-26 21:16:00 -08:00
  • 30ef1c3680
         feat: Add model context protocol tools with ollama provider (#1283) Shrey 2025-02-26 18:38:18 -05:00
  • 2250ab7274
         fix: don't attempt to clean gpu memory up when device is cpu (#1191) Ihar Hrachyshka 2025-02-26 18:12:11 -05:00
  • 21c547aa21
         chore: upgrade uv pre-commit version, uv-sync -> uv-lock (#1284) Ashwin Bharambe 2025-02-26 14:57:48 -08:00
  • 270d64007a
         fix: sqlite conn (#1282) ehhuang 2025-02-26 14:44:31 -08:00
  • c8a20b8ed0
         feat: allow specifying specific tool within toolgroup (#1239) ehhuang 2025-02-26 14:07:05 -08:00
  • 657efc67bc fix: bump up registry key version to clear off stale entries in dbs Ashwin Bharambe 2025-02-26 13:58:03 -08:00
  • 3f0b8c25aa fix: run uv-sync manually. locally pre-commit is not triggering Ashwin Bharambe 2025-02-26 13:53:57 -08:00
  • fca84db5b0
         fix: time logging format (#1281) ehhuang 2025-02-26 13:51:33 -08:00
  • 6b075e5075 feat: automatically update documentation version based on pyproject.toml source of truth Ashwin Bharambe 2025-02-26 13:41:54 -08:00
  • 9a3db9a290
         feat: update the post training notebook (#1280) Botao Chen 2025-02-26 13:39:16 -08:00
  • bb2690f176
         feat: remove special handling of builtin::rag tool (#1015) ehhuang 2025-02-26 13:04:52 -08:00
  • c64f0d5888
         fix: Get builtin tool calling working in remote-vllm (#1236) Ben Browning 2025-02-26 15:25:47 -05:00
  • 2ed2c0bd26
         fix(cli): Missing default for --image-type in stack run command (#1274) Yuan Tang 2025-02-26 15:23:44 -05:00
  • 4cf95475e5 fix: make vision and embedding tests pass with openai, anthropic and gemini Ashwin Bharambe 2025-02-26 10:52:33 -08:00
  • abfc4b3bce
         fix: the pre-commit new line issue (#1272) Reid 2025-02-26 17:25:41 +08:00
  • 123fb9eb24
         feat: [post training] support save hf safetensor format checkpoint (#845) Botao Chen 2025-02-25 23:29:08 -08:00
  • 63e6acd0c3
         feat: add (openai, anthropic, gemini) providers via litellm (#1267) Ashwin Bharambe 2025-02-25 22:07:33 -08:00
  • b0310af177
         refactor: move OpenAI compat utilities from nvidia to openai_compat (#1258) Ashwin Bharambe 2025-02-25 22:02:11 -08:00
  • 82799a55bb
         chore: removed executorch submodule (#1265) Jeff Tang 2025-02-25 21:57:21 -08:00
  • 3a002f6cf1
         chore: update download error message (#1217) Reid 2025-02-26 13:38:10 +08:00
  • 56c1a50b86
         fix: fix the describe table display issue (#1221) Reid 2025-02-26 13:34:53 +08:00
  • 929c5f0842
         refactor(server): replace print statements with logger (#1250) Sébastien Han 2025-02-26 06:31:37 +01:00
  • eb743a3b26
         build: Merge redundant "files" field for codegen check in .pre-commit-config.yaml (#1261) Yuan Tang 2025-02-25 23:56:22 -05:00
  • 55eb257459
         chore: update the zero_to_hero_guide doc link (#1220) Reid 2025-02-26 09:16:02 +08:00
  • c0c7622295
         fix: dont assume SentenceTransformer is imported Hardik Shah 2025-02-25 16:53:01 -08:00
  • 967cff4533
         feat: Add Groq distribution template (#1173) Vladislav Bronzov 2025-02-25 23:16:56 +01:00
  • 99c1d4c456
         docs: Remove $ from client CLI ref to add valid copy and paste ability (#1260) Kelly Brown 2025-02-25 16:50:00 -05:00
  • 0885f959f1
         fix: update index.md to include 0.1.4 (#1259) raghotham 2025-02-25 13:34:29 -08:00
  • 3a31611486
         feat: completing text /chat-completion and /completion tests (#1223) LESSuseLESS 2025-02-25 11:37:04 -08:00
  • 9b130f96a7
         fix: build_venv expects an extra argument (#1233) Charlie Doern 2025-02-25 14:08:50 -05:00
  • c223b1862b
         fix: resolve type hint issues and import dependencies (#1176) Sébastien Han 2025-02-25 20:06:47 +01:00