Commits

Commit history

1. Commits on Jan 10, 2024

   • Logan/together ai (#9962)

     logan-markewich

     authored
     fddb29dView commit details

     Copy full SHA for fddb29d

     View code at this pointBrowse repository at this point
2. Commits on Jan 9, 2024

   • Support for Nvidia TensorRT-LLM Inference (#9842)

     jdye64

     authored
     87a0adaView commit details

     Copy full SHA for 87a0ada

     View code at this pointBrowse repository at this point

   • add streaming support to QueryPipeline (#9919)

     jerryjliu

     authored
     7ab3f50View commit details

     Copy full SHA for 7ab3f50

     View code at this pointBrowse repository at this point
3. Commits on Jan 8, 2024

   • add query pipeline (#9908)

     jerryjliu

     authored
     06ed8a3View commit details

     Copy full SHA for 06ed8a3

     View code at this pointBrowse repository at this point

   • Fix 9219: OpenAIAgent using AzureOpenAI not working with stream_chat and astream_chat (#9890)

     BryceAmackerLE

     authored
     d9954d8View commit details

     Copy full SHA for d9954d8

     View code at this pointBrowse repository at this point
4. Commits on Jan 7, 2024

   • Feature: Azure Multi Modal (fixes: #9471) (#9843)

     Show description for a696d84
     

     joelbarmettlerUZH

     and

     hatianzhang

     authored
     a696d84View commit details

     Copy full SHA for a696d84

     View code at this pointBrowse repository at this point
5. Commits on Jan 6, 2024

   • move more classes to core (#9871)

     jerryjliu

     authored
     6c261c5View commit details

     Copy full SHA for 6c261c5

     View code at this pointBrowse repository at this point
6. Commits on Jan 4, 2024

   • Add prompt formatting to langchain llm (#9844)

     logan-markewich

     authored
     e3c1263View commit details

     Copy full SHA for e3c1263

     View code at this pointBrowse repository at this point

   • Support for Nvidia Triton LLM (#9488)

     jdye64

     authored
     44848c3View commit details

     Copy full SHA for 44848c3

     View code at this pointBrowse repository at this point
7. Commits on Jan 2, 2024

   • Fixing `description` error management in Issue #9777 (#9790)

     FaresKi

     authored
     8279ecfView commit details

     Copy full SHA for 8279ecf

     View code at this pointBrowse repository at this point
8. Commits on Jan 1, 2024

   • add missing azure openai model context sizes (#9782)

     fcakyon

     authored
     2b43fbeView commit details

     Copy full SHA for 2b43fbe

     View code at this pointBrowse repository at this point
9. Commits on Dec 31, 2023

   • Actually use provided HTTP client when using Azure OpenAI (#9772)

     andrewisplinghoff

     authored
     dacd6f5View commit details

     Copy full SHA for dacd6f5

     View code at this pointBrowse repository at this point
10. Commits on Dec 29, 2023

    • fix beam search for vllm: add missing parameter (#9741)

      Show description for a19504a
      Sombressoul

      authored
      a19504aView commit details

      Copy full SHA for a19504a

      View code at this pointBrowse repository at this point
11. Commits on Dec 26, 2023

    • refactor(ollama): use httpx for Ollama API (#9689)

      sandangel

      authored
      0d9c9dcView commit details

      Copy full SHA for 0d9c9dc

      View code at this pointBrowse repository at this point
12. Commits on Dec 25, 2023

    • refactor(ollama): use chat API (#9685)

      sandangel

      authored
      2ab4c30View commit details

      Copy full SHA for 2ab4c30

      View code at this pointBrowse repository at this point
13. Commits on Dec 22, 2023

    • some bedrock nits and fixes (#9646)

      jerryjliu

      authored
      b8e565fView commit details

      Copy full SHA for b8e565f

      View code at this pointBrowse repository at this point
14. Commits on Dec 20, 2023

    • Add support for Google Gemini models via VertexAI (#9624)

      Show description for a31b127
      nicoloboschi

      authored
      a31b127View commit details

      Copy full SHA for a31b127

      View code at this pointBrowse repository at this point

    • fix(vllm): make Vllm's 'complete' method behave the same as other LLM class (#9634)

      xuguodong1999

      authored
      009907cView commit details

      Copy full SHA for 009907c

      View code at this pointBrowse repository at this point
15. Commits on Dec 19, 2023

    • Fix Gemini Chat Mode (#9599)

      Show description for 647a0e4
      hatianzhang

      authored
      647a0e4View commit details

      Copy full SHA for 647a0e4

      View code at this pointBrowse repository at this point

    • fix(azure_openai.py): add missing return to subclass override (#9598)

      Show description for 01bd4de
      

      zimmermannJakob

      and

      Jakob Zimmermann

      authored
      01bd4deView commit details

      Copy full SHA for 01bd4de

      View code at this pointBrowse repository at this point
16. Commits on Dec 18, 2023

    • fix mix up b/w 'formatted' and 'format' params for ollama api call (#9594)

      Show description for d68c3bb
      

      3 peopleauthored
      d68c3bbView commit details

      Copy full SHA for d68c3bb

      View code at this pointBrowse repository at this point

    • Update ollama.py (#9591)

      tobi

      authored
      c46c8e0View commit details

      Copy full SHA for c46c8e0

      View code at this pointBrowse repository at this point

    • Fix pickle again, add unit test (#9588)

      logan-markewich

      authored
      5b9d2c7View commit details

      Copy full SHA for 5b9d2c7

      View code at this pointBrowse repository at this point

    • Add OpenRouter, with Mixtral demo (#9464)

      alexanderatallah

      authored
      cf1fe0aView commit details

      Copy full SHA for cf1fe0a

      View code at this pointBrowse repository at this point

    • Integrations: Gradient[Embeddings,LLM] - sdk-upgrade (#9528)

      Show description for 92f82f8
      michaelfeil

      authored
      92f82f8View commit details

      Copy full SHA for 92f82f8

      View code at this pointBrowse repository at this point

    • Add mixtral 8x7b model to anyscale available models (#9573)

      Show description for 3deae08
      rc19

      authored
      3deae08View commit details

      Copy full SHA for 3deae08

      View code at this pointBrowse repository at this point
17. Commits on Dec 16, 2023

    • Update Ollama API for ollama v0.1.16 (#9558)

      Show description for 4561b5a
      cyberkaida

      authored
      4561b5aView commit details

      Copy full SHA for 4561b5a

      View code at this pointBrowse repository at this point

    • ollama: strip invalid `formatted` option (#9555)

      Show description for d2aa3d5
      idoru

      authored
      d2aa3d5View commit details

      Copy full SHA for d2aa3d5

      View code at this pointBrowse repository at this point
18. Commits on Dec 15, 2023

    • Logan/hf fix 3 (#9539)

      logan-markewich

      authored
      3b892b3View commit details

      Copy full SHA for 3b892b3

      View code at this pointBrowse repository at this point
19. Commits on Dec 14, 2023

    • Fix Bedrock LLMs (#9473)

      cbornet

      authored
      42ba571View commit details

      Copy full SHA for 42ba571

      View code at this pointBrowse repository at this point

    • Allowing `LOCALAI_DEFAULTS` to work with `__ror__` (#9502)

      jamesbraza

      authored
      5fdf7f5View commit details

      Copy full SHA for 5fdf7f5

      View code at this pointBrowse repository at this point

    • Added missing `default=None` to `LLM.system_prompt` (#9504)

      Show description for 9d4528d
      jamesbraza

      authored
      9d4528dView commit details

      Copy full SHA for 9d4528d

      View code at this pointBrowse repository at this point
20. Commits on Dec 13, 2023

    • Merge Gemini Same Role Chat Message (#9498)

      Show description for f83af27
      hatianzhang

      authored
      f83af27View commit details

      Copy full SHA for f83af27

      View code at this pointBrowse repository at this point

    • Add a Gemini models for text and multi-modal. (#9452)

      Show description for de3a99e
      

      markmcd

      and

      hatianzhang

      authored
      de3a99eView commit details

      Copy full SHA for de3a99e

      View code at this pointBrowse repository at this point

    • Make ollama support additional_kwargs correctly (#9455)

      Show description for fadef5f
      samx81

      authored
      fadef5fView commit details

      Copy full SHA for fadef5f

      View code at this pointBrowse repository at this point