Commit graph

  • 099a95b614 slight upgrade to CLI Ashwin Bharambe 2024-10-06 18:02:47 -07:00
  • 1550187cd8 cleanup Ashwin Bharambe 2024-10-06 17:20:33 -07:00
  • 91e0063593 Introduce model_store, shield_store, memory_bank_store Ashwin Bharambe 2024-10-06 16:29:33 -07:00
  • e45a417543 more fixes, plug shutdown handlers Ashwin Bharambe 2024-10-05 23:48:18 -07:00
  • 60dead6196 apis_to_serve -> apis Ashwin Bharambe 2024-10-05 23:16:11 -07:00
  • 59302a86df inference registry updates Ashwin Bharambe 2024-10-05 22:25:48 -07:00
  • 4215cc9331 Push registration methods onto the backing providers Ashwin Bharambe 2024-10-05 22:17:06 -07:00
  • 5a7b01d292 Significantly upgrade the interactive configuration experience Ashwin Bharambe 2024-10-05 11:12:46 -07:00
  • 8d157a8197 rename Ashwin Bharambe 2024-10-05 09:04:50 -07:00
  • f3923e3f0b Redo the { models, shields, memory_banks } typeset Ashwin Bharambe 2024-10-05 08:41:36 -07:00
  • b87bdd0176 registry refactor Xi Yan 2024-10-08 15:44:02 -07:00
  • 6b094b72d3
    Update cli_reference.md Xi Yan 2024-10-08 15:32:06 -07:00
  • ce70d21f65
    Add files via upload Xi Yan 2024-10-08 15:29:19 -07:00
  • a7b17fe58b add clarifai inference provider sanjaychelliah 2024-10-09 03:35:31 +05:30
  • 6b7569da59
    docs: Updated README.md Anush 2024-10-09 01:57:27 +05:30
  • d9531d17de
    Merge remote-tracking branch 'upstream/main' into qdrant Anush008 2024-10-09 01:37:29 +05:30
  • a0c888c071
    feat: Qdrant Vector index support Anush008 2024-10-09 01:28:06 +05:30
  • 2d4f7d8acf
    Create SECURITY.md Dalton Flanagan 2024-10-08 13:30:40 -04:00
  • 48d0d2001e
    Add classifiers in setup.py (#217) Yuan Tang 2024-10-08 09:55:16 -04:00
  • a56ea48d71 excel dataset Xi Yan 2024-10-07 21:56:13 -07:00
  • b527a95c58
    Update setup.py Yuan Tang 2024-10-07 22:57:17 -04:00
  • 6e7868c18c
    Update setup.py Yuan Tang 2024-10-07 22:54:08 -04:00
  • 4d5f7459aa
    [bugfix] Fix logprobs on meta-reference impl (#213) Xi Yan 2024-10-07 19:42:39 -07:00
  • e4ae09d090
    Add .idea to .gitignore (#216) Yuan Tang 2024-10-07 22:38:43 -04:00
  • 0d5b1b192a
    Add classifiers in setup.py Yuan Tang 2024-10-07 22:10:25 -04:00
  • 5096f422e3 bugfix Xi Yan 2024-10-07 17:43:46 -07:00
  • f1d31fe9b5 error handling Xi Yan 2024-10-07 17:40:43 -07:00
  • 8a67e7a2bd add back LogProbsConfig Xi Yan 2024-10-07 17:36:39 -07:00
  • 5b7d24b1c3 wip Xi Yan 2024-10-07 17:27:06 -07:00
  • 20e78ff241 fix log probs Xi Yan 2024-10-07 16:45:06 -07:00
  • 4764762dd4 tasks registry Xi Yan 2024-10-07 15:57:39 -07:00
  • 30274b3fac
    Remove unused imports Yuan Tang 2024-10-07 17:57:21 -04:00
  • f3a8a3a5e8
    Move to utils Yuan Tang 2024-10-07 17:20:49 -04:00
  • 16ba0fa06f
    Update README.md Xi Yan 2024-10-07 11:24:27 -07:00
  • 996efa9b42
    README.md: Add vLLM to providers table (#207) Russell Bryant 2024-10-07 13:26:52 -04:00
  • 3e3b096071
    Fix issue #183 Ezreal 2024-10-08 01:21:31 +08:00
  • 2366e18873
    refactor docs (#209) Xi Yan 2024-10-07 10:21:26 -07:00
  • c221c23492 refactor docs Xi Yan 2024-10-07 10:19:59 -07:00
  • de80f66470
    Fix issue #183 Ezreal 2024-10-08 01:15:28 +08:00
  • 4de3c198c8 README.md: Add vLLM to providers table Russell Bryant 2024-10-07 12:02:50 -04:00
  • 53d440e952
    Fix ValueError in case chunks are empty (#206) Mindaugas 2024-10-07 18:55:06 +03:00
  • a4e775c465
    download: improve help text (#204) Russell Bryant 2024-10-07 11:40:04 -04:00
  • fa1fb0f4d6 Fix ValueError in case chunks are empty Minutis 2024-10-07 18:35:12 +03:00
  • 5ae082df7f Refactor KVStore range function Minutis 2024-10-06 13:36:57 +03:00
  • 6a8e80c015 download: improve help text Russell Bryant 2024-10-07 10:35:35 -04:00
  • 4263764493 Fix adapter_id -> adapter_type for Weaviate Ashwin Bharambe 2024-10-07 06:46:32 -07:00
  • f4f7618120
    add Weaviate memory adapter (#95) Zain Hasan 2024-10-07 01:21:50 -04:00
  • fce14735c6
    Add .idea to .gitignore Yuan Tang 2024-10-06 15:31:30 -04:00
  • 27587f32bc fix db path Xi Yan 2024-10-06 11:46:08 -07:00
  • cfe3ad33b3 fix db path Xi Yan 2024-10-06 11:45:35 -07:00
  • d8c4e7da4b
    Remove testing code Yuan Tang 2024-10-06 10:00:55 -04:00
  • a8a860ea1f
    Fix async case Yuan Tang 2024-10-06 09:44:20 -04:00
  • 4f7a01c022
    WIP: Add generic OpenAI compatible inference provider Yuan Tang 2024-10-05 23:34:20 -04:00
  • 969a11fb8a Ensure models are downloaded before serving in Ollama inference Frieda (Jingying) Huang 2024-10-06 12:09:22 -04:00
  • 0edf24b227 Fixed model name; use routing_key to get model Frieda (Jingying) Huang 2024-10-04 21:53:54 -04:00
  • 8ed548b18e (#183) Ensure models are downloaded before serving in Ollama inference Frieda (Jingying) Huang 2024-10-04 14:46:33 -04:00
  • 7abab7604b
    add databricks provider (#83) Prithu Dasgupta 2024-10-05 23:35:54 -07:00
  • 399b136187
    Merge branch 'main' into add-databricks-inference-provider Ashwin Bharambe 2024-10-05 23:35:38 -07:00
  • f73e247ba1
    Inline vLLM inference provider (#181) Russell Bryant 2024-10-06 02:34:16 -04:00
  • 29138a5167
    Update getting_started.md Xi Yan 2024-10-05 12:28:02 -07:00
  • 6d4013ac99
    Update getting_started.md Xi Yan 2024-10-05 12:14:59 -07:00
  • 041634192a move folder Xi Yan 2024-10-05 11:57:21 -07:00
  • 9d16129603
    Add 'url' property to Redis KV config (#192) Mindaugas 2024-10-05 21:26:26 +03:00
  • a569da8be3 Add 'url' property to Redis KV config Minutis 2024-10-05 17:06:43 +03:00
  • 5626e79731 Implement (chat_)completion for vllm provider Russell Bryant 2024-10-01 13:12:11 +00:00
  • 08da5d003a Add a local-vllm template Russell Bryant 2024-09-28 19:10:04 +00:00
  • 608e827d36 update provider and test prithu-dasgupta 2024-10-04 15:53:18 -07:00
  • 6234dd97d5 eleuther eval provider Xi Yan 2024-10-04 13:45:52 -07:00
  • bfb0e92034 Bump version to 0.0.40 Ashwin Bharambe 2024-10-04 09:33:43 -07:00
  • dc75aab547 Add setuptools dependency Ashwin Bharambe 2024-10-04 09:30:54 -07:00
  • 441052b0fd avoid jq since non-standard on macOS Dalton Flanagan 2024-10-04 10:11:43 -04:00
  • 9bf2e354ae CLI now requires jq Dalton Flanagan 2024-10-04 10:05:59 -04:00
  • 2441e66d14 evals api mvp Xi Yan 2024-10-04 00:50:03 -07:00
  • 3cbe3a72e8 mvp Xi Yan 2024-10-04 00:25:57 -07:00
  • 00ed9a410b
    Update getting_started.md raghotham 2024-10-03 23:28:43 -07:00
  • 734f59d3b8
    Check that the model is found before use. (#182) AshleyT3 2024-10-03 23:24:47 -07:00
  • d3b689ceab Check that the model is found before use. Ashley R. Thomas 2024-10-03 21:04:14 -07:00
  • 4f07aca309 get task Xi Yan 2024-10-03 17:31:46 -07:00
  • f913b57397 fix fp8 imports Ashwin Bharambe 2024-10-03 14:40:21 -07:00
  • 31a0c51dea Add vllm to the inference registry Russell Bryant 2024-09-28 19:06:53 +00:00
  • a08fd8f331 Add boilerplate for vllm inference provider Russell Bryant 2024-09-28 18:46:35 +00:00
  • 8339b2cef3 wip api Xi Yan 2024-10-03 13:47:15 -07:00
  • 0515d5f348 ci: Only run pre-commit on diff instead of all files Russell Bryant 2024-10-03 19:10:27 +00:00
  • f85b055027 flake8: Update exclude formatting for docs Russell Bryant 2024-10-03 14:17:54 +00:00
  • e8c894fece flake8: Fix config formatting error Russell Bryant 2024-10-03 14:00:20 +00:00
  • b06b8e9c7d ci: Run pre-commit checks in CI Russell Bryant 2024-10-03 13:52:24 +00:00
  • 7143ecfc0d wip Xi Yan 2024-10-03 11:36:18 -07:00
  • 8d41e6caa9 Bump version to 0.0.39 Ashwin Bharambe 2024-10-03 11:31:03 -07:00
  • 7f49315822 Kill a derpy import Ashwin Bharambe 2024-10-03 11:25:58 -07:00
  • 62d266f018
    [CLI] avoid configure twice (#171) Xi Yan 2024-10-03 11:20:54 -07:00
  • 8a8cc7951d script update Xi Yan 2024-10-03 11:20:25 -07:00
  • b07be298e1 update msg Xi Yan 2024-10-03 11:19:07 -07:00
  • 06db9213b1
    inference: Add model option to client (#170) Russell Bryant 2024-10-03 14:18:57 -04:00
  • 5e9301de90 wip Xi Yan 2024-10-03 11:18:23 -07:00
  • 210b71b0ba
    fix prompt guard (#177) Ashwin Bharambe 2024-10-03 11:07:53 -07:00
  • a93e493fcc Several more fixes Ashwin Bharambe 2024-10-03 11:01:41 -07:00
  • b9b1e8b08b
    [bugfix] conda path lookup (#179) Xi Yan 2024-10-03 10:45:16 -07:00
  • a086c0b16c comments Xi Yan 2024-10-03 10:43:41 -07:00
  • fbce62ba26 address comment Xi Yan 2024-10-03 10:41:50 -07:00
  • a7250a1e33
    Merge branch 'main' into fix_configure Xi Yan 2024-10-03 10:38:20 -07:00