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

  • dc94433072
         feat(pre-commit): enhance pre-commit hooks with additional checks (#2014) Sébastien Han 2025-04-30 20:35:49 +02:00
  • d897313e0b
         feat: add additional logging to llama stack build (#1689) Nathan Weinberg 2025-04-30 14:06:24 -04:00
  • 2c7aba4158
         fix: enforce stricter ASCII rules lint rules in Ruff (#2062) Sébastien Han 2025-04-30 18:05:27 +02:00
  • eab550f7d2
         fix: Fix messages format in NVIDIA safety check request body (#2063) Jash Gulabrai 2025-04-30 12:01:28 -04:00
  • 4412694018
         chore: Remove zero-width space characters from OTEL service name env var defaults (#2060) Sébastien Han 2025-04-30 17:56:46 +02:00
  • 653e8526ec
         chore(ci): misc Ollama improvements (#2052) Sébastien Han 2025-04-30 16:05:28 +02:00
  • 78ef6a6099
         chore: Increase unit test coverage of routing_tables.py (#2057) Derek Higgins 2025-04-30 15:00:43 +01:00
  • 17b5302543
         fix: Fix precommit-hook (#2059) Derek Higgins 2025-04-30 11:03:19 +01:00
  • afd7e750d9
         ci: add UBI 9 container-build gate (#2039) Alexey Rybak 2025-04-30 00:52:57 -07:00
  • 5a2bfd6ad5
         refactor: Replace SQLITE_DB_PATH by SQLITE_STORE_DIR env in templates (#2055) Roland Huß 2025-04-30 00:28:10 +02:00
  • 7532f4cdb2
         chore(github-deps): bump astral-sh/setup-uv from 5 to 6 (#2051) Yuan Tang 2025-04-29 14:41:41 -04:00
  • 799286fe52 fix: Bump version to 0.2.4 Ashwin Bharambe 2025-04-29 10:34:17 -07:00
  • 5c0680cd3f build: Bump version to 0.2.4 v0.2.4 release-0.2.4 github-actions[bot] 2025-04-29 17:23:26 +00:00
  • 302b3050c2 Release candidate 0.2.4rc1 v0.2.4rc1 github-actions[bot] 2025-04-29 17:18:17 +00:00
  • 4d0bfbf984
         feat: add api.llama provider, llama-guard-4 model (#2058) Ashwin Bharambe 2025-04-29 10:07:41 -07:00
  • 934446ddb4
         fix: ollama still using tools with tool_choice="none" (#2047) Ben Browning 2025-04-29 04:45:28 -04:00
  • 2aca7265b3
         fix: add todo for schema validation (#1991) Kevin Postlethwait 2025-04-29 03:59:35 -04:00
  • fe9b5ef08b
         fix: tools page on playground resets agent after every interaction (#2044) Michael Clifford 2025-04-28 17:13:27 -04:00
  • 7807a86358
         ci: simplify external provider integration test (#2050) Sébastien Han 2025-04-28 23:10:27 +02:00
  • 8dfce2f596
         feat: OpenAI Responses API (#1989) Ben Browning 2025-04-28 17:06:00 -04:00
  • 79851d93aa
         feat: Add Kubernetes authentication (#1778) Sébastien Han 2025-04-28 22:24:58 +02:00
  • e6bbf8d20b
         feat: Add NVIDIA NeMo datastore (#1852) Rashmi Pawar 2025-04-28 22:11:59 +05:30
  • c149cf2e0f
         chore(github-deps): bump actions/setup-python from 5.5.0 to 5.6.0 (#2038) dependabot[bot] 2025-04-28 11:46:29 +02:00
  • 1050837622
         feat: Llama Stack Meta Reference installation script (#1383) Alexey Rybak 2025-04-28 02:25:59 -07:00
  • 921ce36480
         docs: Add changelog for v0.2.2 and v0.2.3 (#2040) Yuan Tang 2025-04-27 14:46:13 -04:00
  • 28687b0e85
         fix: Bump h11 to 0.16.0 to fix cve-2025-43859 (#2041) Yuan Tang 2025-04-27 14:45:35 -04:00
  • 6cf6791de1
         fix: updated watsonx inference chat apis with new repo changes (#2033) Sajikumar JS 2025-04-26 22:47:52 +05:30
  • 0266b20535
         docs: update prompt_format.md for llama4 (#2035) ehhuang 2025-04-25 15:52:15 -07:00
  • 1e8fce126f build: Bump version to 0.2.3 v0.2.3 release-0.2.3 Ashwin Bharambe 2025-04-25 15:38:49 -07:00
  • bb1a85c9a0 fix: make sure test works equally well against llama stack as a server Ashwin Bharambe 2025-04-25 15:23:53 -07:00
  • 3ca284a52b Release candidate 0.2.3rc5 v0.2.3rc5 github-actions[bot] 2025-04-25 22:07:01 +00:00
  • 8713d67ce3
         fix: Correctly parse algorithm_config when launching NVIDIA customization job; fix internal request handler (#2025) Jash Gulabrai 2025-04-25 16:21:50 -04:00
  • b5d8e44e81 fix: only sleep for tests when they pass or fail Ashwin Bharambe 2025-04-25 13:15:52 -07:00
  • 1b2e116a2a
         fix: tool call encoded twice (#2034) ehhuang 2025-04-25 13:16:16 -07:00
  • 4fb583b407
         fix: check that llama stack client plain can be used as a subst for OpenAI client (#2032) Ashwin Bharambe 2025-04-25 12:23:33 -07:00
  • 0e4307de0f
         docs: Fix missing --gpu all flag in Docker run commands (#2026) Derek Higgins 2025-04-25 20:17:31 +01:00
  • 1deab94ea0
         chore: exclude test, provider, and template directories from coverage (#2028) Sébastien Han 2025-04-25 21:16:57 +02:00
  • 1bb1d9b2ba
         feat: Add watsonx inference adapter (#1895) Sajikumar JS 2025-04-25 23:59:21 +05:30
  • 29072f40ab
         feat: new system prompt for llama4 (#2031) ehhuang 2025-04-25 11:29:08 -07:00
  • 4bbd0c0693 fix: add endpoint route debugs Ashwin Bharambe 2025-04-25 10:39:30 -07:00
  • f5dae0517c
         feat: Support ReAct Agent on Tools Playground (#2012) Andy Xie 2025-04-25 11:01:51 -04:00
  • 121c73c2f5
         feat(cli): add interactive tab completion for image type selection (#2027) Roland Huß 2025-04-25 16:57:42 +02:00
  • 59b7593609
         feat: Enhance tool display in Tools sidebar by simplifying tool identifiers (#2024) Surya Prakash Pathak 2025-04-25 01:22:22 -07:00
  • d9e00fca66
         fix: specify nbformat version in nb (#2023) Kevin Postlethwait 2025-04-25 04:10:37 -04:00
  • ace82836c1
         feat: NVIDIA allow non-llama model registration (#1859) Rashmi Pawar 2025-04-25 05:43:33 +05:30
  • cc77f79f55
         feat: Add NVIDIA Eval integration (#1890) Jash Gulabrai 2025-04-24 20:12:42 -04:00
  • 0b6cd45950
         fix: Additional streaming error handling (#2007) Ben Browning 2025-04-24 20:01:45 -04:00
  • c8797f1125
         fix: Including tool call in chat (#1931) Derek Higgins 2025-04-25 00:59:10 +01:00
  • 7ed137e963
         fix: meta ref inference (#2022) ehhuang 2025-04-24 13:03:35 -07:00
  • a5d6ab16b2 fix: meta-reference parallel utils bug, use isinstance not equality Ashwin Bharambe 2025-04-24 11:27:49 -07:00
  • 70488abe9c
         chore: Remove distributions/** from integration, external provider, and unit tests (#2018) Francisco Arceo 2025-04-24 09:39:31 -06:00
  • dc0d4763a0
         chore: Update External Providers CI to not run on changes to docs, rfcs, and scripts (#2009) Francisco Arceo 2025-04-24 09:24:07 -06:00
  • e664ba91d8
         fix: prevent the knowledge search tool from confusing the model with long content (#1908) Ilya Kolchinsky 2025-04-24 16:38:38 +02:00
  • 14e60e3c02
         feat: include run.yaml in the container image (#2005) Sébastien Han 2025-04-24 11:29:53 +02:00
  • a673697858
         chore: rename ramalama provider (#2008) Charlie Doern 2025-04-24 03:34:15 -04:00
  • fa5dfee07b
         fix: Return HTTP 400 for OpenAI API validation errors (#2002) Ben Browning 2025-04-23 11:48:32 -04:00
  • 6a44e7ba20
         docs: add API to external providers table (#2006) Nathan Weinberg 2025-04-23 09:58:10 -04:00
  • 64f747fe09
         feat: add tool name to chat output in playground (#1996) Michael Clifford 2025-04-23 09:57:54 -04:00
  • dc46725f56
         fix: properly handle streaming client disconnects (#2000) Ben Browning 2025-04-23 09:44:28 -04:00
  • e0fa67c81c
         docs: add examples for how to define RAG docs (#1981) Kevin Postlethwait 2025-04-23 09:39:18 -04:00
  • deee355952
         fix: Added lazy initialization of the remote vLLM client to avoid issues with expired asyncio event loop (#1969) Ilya Kolchinsky 2025-04-23 15:33:19 +02:00
  • d39462d073
         feat: Hide tool output under an expander in Playground UI (#2003) Ilya Kolchinsky 2025-04-23 15:32:12 +02:00
  • d6e88e0bc6
         docs: add RamaLama to list of known external providers (#2004) Nathan Weinberg 2025-04-23 03:44:18 -04:00
  • 825ce39879
         fix: Together provider shutdown and default to non-streaming (#2001) Ben Browning 2025-04-22 11:47:53 -04:00
  • e4d001c4e4
         feat: cleanup sidebar formatting on tools playground (#1998) Michael Clifford 2025-04-22 04:40:37 -04:00
  • 3110ad1e7c
         fix: update ref to raw_errors due to new version of pydantic (#1995) Kevin Postlethwait 2025-04-21 14:50:12 -04:00
  • 602e949a46
         fix: OpenAI Completions API and Fireworks (#1997) Ben Browning 2025-04-21 14:49:12 -04:00
  • 0d06c654d0
         feat: Update NVIDIA to GA docs; remove notebook reference until ready (#1999) Jash Gulabrai 2025-04-18 19:13:18 -04:00
  • 94f83382eb
         feat: allow building distro with external providers (#1967) Sébastien Han 2025-04-18 17:18:28 +02:00
  • c4570bcb48
         docs: Add tips for debugging remote vLLM provider (#1992) Yuan Tang 2025-04-18 08:47:47 -04:00
  • 9845631d51
         feat: update nvidia inference provider to use model_store (#1988) Matthew Farrellee 2025-04-18 04:16:43 -04:00
  • e72b1076ca
         fix(build): add UBI 9 compiler tool‑chain (#1983) Alexey Rybak 2025-04-18 00:49:10 -07:00
  • 4c6b7005fa
         fix: Fix docs lint issues (#1993) Yuan Tang 2025-04-18 02:33:13 -04:00
  • dd62a2388c
         docs: add notes to websearch tool and two extra example scripts (#1354) AN YU (安宇) 2025-04-18 01:20:52 +01:00
  • 0ed41aafbf
         test: add multi_image test (#1972) ehhuang 2025-04-17 12:51:42 -07:00
  • 2976b5d992
         fix: OAI compat endpoint for meta reference inference provider (#1962) ehhuang 2025-04-17 11:16:04 -07:00
  • 8bd6665775
         chore(verification): update README and reorganize generate_report.py (#1978) ehhuang 2025-04-17 10:41:22 -07:00
  • cb874287a4
         fix: resync api spec (#1987) Sébastien Han 2025-04-17 17:36:04 +02:00
  • 326cbba579
         feat(agents): add agent naming functionality (#1922) Alexey Rybak 2025-04-17 07:02:47 -07:00
  • 5b8e75b392
         fix: OpenAI spec cleanup for assistant requests (#1963) Ben Browning 2025-04-17 09:56:10 -04:00
  • 4205376653
         chore: add meta/llama-3.3-70b-instruct as supported nvidia inference provider model (#1985) Matthew Farrellee 2025-04-17 09:50:40 -04:00
  • 2ae1d7f4e6
         docs: Add NVIDIA platform distro docs (#1971) Jash Gulabrai 2025-04-17 08:54:30 -04:00
  • 45e08ff417
         fix: Handle case when Customizer Job status is unknown (#1965) Jash Gulabrai 2025-04-17 04:27:07 -04:00
  • 6f97f9a593
         chore: Use hashes to pull actions for build-single-provider job (#1977) Ihar Hrachyshka 2025-04-17 04:26:08 -04:00
  • 8f57b08f2c
         fix(build): always pass path when no template/config provided (#1982) Alexey Rybak 2025-04-17 01:20:43 -07:00
  • 6ed92e03bc
         fix: print traceback on build failure (#1966) Sébastien Han 2025-04-17 09:45:21 +02:00
  • f12011794b
         fix: Updated tools playground to allow vdb selection (#1960) Michael Clifford 2025-04-17 03:29:40 -04:00
  • b44f84ce18
         test: disable flaky dataset (#1979) ehhuang 2025-04-16 15:33:37 -07:00
  • 30fc66923b
         fix: Add llama-3.2-1b-instruct to NVIDIA fine-tuned model list (#1975) Jash Gulabrai 2025-04-16 18:02:08 -04:00
  • 00b232c282
         chore: Fix to persist the theme preference across page navigation. (#1974) Francisco Arceo 2025-04-16 14:58:25 -06:00
  • b5a9ef4c6d
         fix: Do not send an empty 'tools' list to remote vllm (#1957) Daniel Alvarez Sanchez 2025-04-16 02:31:12 +02:00
  • fb8ff77ff2
         docs: 0.2.2 doc updates (#1961) Chirag Modi 2025-04-15 13:26:17 -07:00
  • 093881071a
         fix: add max_tokens slider to playground tools page (#1958) Michael Clifford 2025-04-15 12:11:08 -04:00
  • 71ed47ea76
         docs: add example for intel gpu in vllm remote (#1952) Dmitry Rogozhkin 2025-04-15 07:56:23 -07:00
  • 83b5523e2d
         feat: add --providers to llama stack build (#1718) Charlie Doern 2025-04-15 08:17:03 -04:00
  • 32e3da7392
         test(verification): more tests, multiturn tool use tests (#1954) ehhuang 2025-04-14 18:45:22 -07:00
  • 86c6f1f112
         fix: FastAPI built-in paths bypass custom routing (Docs) and update r… (#1841) Peter Double 2025-04-14 13:28:25 -04:00
  • cf158f2cb9
         feat: allow ollama to use 'latest' if available but not specified (#1903) Nathan Weinberg 2025-04-14 12:03:54 -04:00
  • 3ed4316ed5
         feat: Implement async job execution for torchtune training (#1437) Ihar Hrachyshka 2025-04-14 11:59:11 -04:00
  • 7641a5cd0b
         fix: 100% OpenAI API verification for together and fireworks (#1946) Ben Browning 2025-04-14 11:56:29 -04:00