kartik-mem0
493a62cb03
fix(embeddings): size Vertex AI batches by model family
...
gemini-embedding-* accepts one input text per predict request, but
embed_batch() chunked at 250 for every model while defaulting to
gemini-embedding-001. Derive the chunk size from the model instead.
2026-07-09 21:30:39 +05:30
Alok Tripathi and GitHub
3e2ae734e7
feat(embeddings): add native embed_batch to 5 embedders (LMStudio, Together, HuggingFace, VertexAI, GoogleGenAI) ( #5609 )
2026-06-18 16:46:31 +05:30
Kartik and GitHub
cd2dd7cc54
refactor: update default Gemini and Vertex AI embedder model to gemini-embedding-001 ( #4571 )
2026-03-28 20:39:27 +05:30
Dev Khant and GitHub
d85fcda037
Formatting ( #2750 )
2025-05-22 01:17:29 +05:30
Wonbin Kim and GitHub
6acb00731d
Add config option for vertex embedding tasks ( #2266 )
2025-02-28 15:20:05 +05:30
Dev Khant and GitHub
605558da9d
Code formatting ( #1986 )
2024-10-29 11:32:07 +05:30
Divyanshu Prasad and GitHub
d107b639b3
(bug-fix) : fix VertexAI missing configurations ( #1926 )
2024-10-03 21:34:14 +05:30
dbcontributions and GitHub
61dd5a5ea4
Add vertexai test cases ( #1907 )
2024-09-26 21:33:55 +05:30
kartik-mem0