Repository navigation

Commits

Commits on Nov 15, 2024
- change available_models to return List[Model], previously List[str] (#16968)
  mattf
  authored
  a10af2c
Commits on Nov 8, 2024
- skip model validation for nvdev embedding models (#16883)
  mattf
  authored
  4d576a9
- skip model validation for nvdev llm models (#16882)
  mattf
  authored
  5848d7b
Commits on Oct 25, 2024
- add nvidia/llama-3.2-nv-embedqa-1b-v1 to set of supported models (#16694)
  mattf
  authored
  bf2d2f6
- add nvidia/llama-3.2-nv-rerankqa-1b-v1 to set of supported models (#16695)
  mattf
  authored
  c29117b
Commits on Sep 4, 2024
- enable async tests for structured output and tools (#15826)
  mattf
  authored
  b5d688e
- update openai base.py to use all_kwargs (#15815)
  mattf
  authored
  a796b68
Commits on Aug 28, 2024
- Update README.md (#15690)
  mattf
  authored
  7f402e1
Commits on Aug 26, 2024
- fix downloaded nim endpoint path (#15645)
  mattf
  authored
  1666712
- fix llama-index-postprocessor-nvidia-rerank tests (#15643)
  mattf
  authored
  0af2ec5
Commits on Aug 23, 2024
- update default embedding model to nvidia/nv-embedqa-e5-v5 (#15593)
  mattf
  authored
  72cbe0a
- upgrade to 0.2.0, remove deprecated mode switching (#15544)
  mattf
  authored
  0bfc824
Commits on Aug 21, 2024
- remove poetry.lock (#15551)
  mattf
  authored
  e6d1476
- update default model to nvidia/nv-rerankqa-mistral-4b-v3 (#15543)
  mattf
  authored
  c079fd1
- Update to 0.2.0 (#15533)
  mattf
  authored
  a63caa9
Commits on Aug 19, 2024
- add truncate support (#15490)
  mattf
  authored
  ff72eea
- fix handling of base_url, re-enable nvidia/nv-rerankqa-mistral-4b-v3 (#15485)
  mattf
  authored
  78f4bb8
Commits on Jul 19, 2024
- add support for nvidia/nv-rerankqa-mistral-4b-v3 (#14844)
  mattf
  authored
  93e630a
Commits on Jun 27, 2024
- add known context lengths for hosted models (#14436)
  mattf
  authored
  8d5ea16
Commits on Jun 17, 2024
- add support for nvidia/nv-embed-v1 (https://huggingface.co/nvidia/NV-Embed-v1) (#14194)
  mattf
  authored
  89a985a
Commits on May 18, 2024
- Deprecate mode() in favor of __init__(base_url=...) for NVIDIA, NVIDIAEmbedding, NVIDIARerank (#13572)
  mattf
  authored
  347f122
Commits on May 17, 2024
- add snowflake/arctic-embed-l support (#13555)
  mattf
  authored
  024c418
Commits on May 9, 2024
- add dynamic model listing support (#13398)
  mattf
  authored
  1a0e705
Commits on May 8, 2024
- set default max_tokens to 1024 (#13371)
  mattf
  authored
  7c65654
- fix truncate passing for aget_query_embedding and get_text_embedding_batch (#13367)
  mattf
  authored
  d089b78
Commits on May 7, 2024
- add nvidia nim llm support (#13176)
  mattf
  authored
  4431e99
Commits on May 3, 2024
- add nvidia nim embeddings support (#13177)
  mattf
  authored
  d3b4001
- add nvidia nim rerank support (#13178)
  mattf
  authored
  f79e186
Commits on Apr 30, 2024
- fix direct reranker use in bm25_retriever example (#13171)
  mattf
  authored
  61f4aeb

Branch selector

User selector

Datepicker

Commit history

Commits on Nov 15, 2024

Commits on Nov 8, 2024

Commits on Oct 25, 2024

Commits on Sep 4, 2024

Commits on Aug 28, 2024

Commits on Aug 26, 2024

Commits on Aug 23, 2024

Commits on Aug 21, 2024

Commits on Aug 19, 2024

Commits on Jul 19, 2024

Commits on Jun 27, 2024

Commits on Jun 17, 2024

Commits on May 18, 2024

Commits on May 17, 2024

Commits on May 9, 2024

Commits on May 8, 2024

Commits on May 7, 2024

Commits on May 3, 2024

Commits on Apr 30, 2024