bge-micro is a small BAAI embedding model; none of the candidate products names it directly. The closest matches are Replicate, which hosts open-source embedding models behind a cloud API 1, and Hugging Face, which hosts models and offers sentence-transformers training 7, with Sbert/SentenceTransformers as the Python library for running and training embedding models 9. The request does not say whether you want a hosted API or a local library, so the best route depends on that.
A question back: Do you want to run bge-micro locally in Python, or call it through a hosted API?
- 1
SentenceTransformers (Sbert)sbert.netverified and signed
Python module for computing embeddings from text with state-of-the-art embedding models, usable to load a small BGE model locally 9.
official:SDK · sentence-transformers+24 community tools built for it
for agents: embedding · BERT · deep
- 2
Hugging Facehuggingface.coverified and signed
Model hub and huggingface-hub SDK for downloading and hosting open embedding models, plus sentence-transformers training support 7.
official:MCP server · @huggingface/mcp-clientSDK · huggingface-hubCLI · text-embeddings-inferencerepository · pwc-cliskill · hf-cli+23 community tools built for it
for agents: train-sentence-transformers · models · model-hub
- 3
Replicatereplicate.comverified and signed
Cloud API for running open-source machine learning models, including embedding models, via a single run call 1.
+14 community tools built for it
for agents: ifaas-uk/bge-m3 · center-for-curriculum-redesign/bge_1-5_query_embeddings · mark3labs/embeddings-gte-base
Sources
- 1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 7Hugging Face – The AI community building the future.huggingface.co · read 2026-10-29
- 9SentenceTransformers Documentation — Sentence Transformers documentationsbert.net · read 2026-10-29
For agents: the 10 actions behind this answer
ifaas-uk/bge-m3 · ifaas-uk/bge-m3 verified and signed
Multilingual BGE-M3 embedding model for dense and sparse hybrid retrieval.
embedding-generation · NV-CLIP verified and signed
Task: embedding generation
zerodb_generate_embeddings · AINative ZeroDB MCP Server found in code, not yet checked
Generate embeddings using specified model (384/768/1024 dimensions). Supports BAAI/bge-small-en-v1.5 (384-dim, default), BAAI/bge-base-en-v1.5 (768-dim), BAAI/bge-large-en-v1.5 (1024-dim). Use when you need raw embedding vectors without storing them. Does not persist data — for embed + store in one
createEmbedding · OpenAI API verified and signed
Creates an embedding vector representing the input text.
model-recommendation · model-recommendation verified and signed
Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiency
graph_sage_predict · neo4j-gds found in code, not yet checked
Generates node embeddings using a previously trained GraphSAGE model from the model catalog (see graph_sage_train).
train-sentence-transformers · train-sentence-transformers verified and signed
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification
codec · ebcdic verified and signed
embedding · sentence-transformers verified and signed
workers-ai-search-model · Cloudflare API verified and signed
Model Search
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.