mem0ai/mem0

feat(ts-sdk): add FastEmbed embedding provider

Open

#5,770 创建于 2026年6月23日

在 GitHub 查看
 (2 评论) (0 反应) (0 负责人)Python (6,343 fork)batch import
enhancementgood first issuehelp wantedsdk-typescriptsize:M

仓库指标

Star
 (55,741 star)
PR 合并指标
 (平均合并 6天 11小时) (30 天内合并 208 个 PR)

描述

Summary

The Python SDK supports FastEmbed as an embedding provider, but the TypeScript OSS SDK (mem0ai/oss) does not. Add it to bring the TS SDK to parity.

Python reference mem0/embeddings/fastembed.py
Registered in (Python) mem0/utils/factory.py (EmbedderFactory)
Target file (TypeScript) mem0-ts/src/oss/src/embeddings/fastembed.ts
Suggested implementation Use the fastembed npm package (ONNX local embeddings).

Requirements

  • Implement FastEmbedEmbedder in mem0-ts/src/oss/src/embeddings/fastembed.ts, extending Embedder (mem0-ts/src/oss/src/embeddings/base.ts) and mirroring the Python provider's behavior (embed / embedBatch).
  • Register the "fastembed" provider in mem0-ts/src/oss/src/utils/factory.ts (EmbedderFactory).
  • Add config typing in mem0-ts/src/oss/src/types/.
  • Add a unit test under mem0-ts/src/oss/src/tests/.
  • Add fastembed to mem0-ts/package.json (optional/peer dependency, lazy-imported like other providers).
  • Update docs under docs/ if this provider is user-facing.

Reference pattern

Mirror an existing TS provider: embeddings/openai.ts.

Notes

fastembed (v2.x) is the JS port of Qdrant's FastEmbed — local/offline embeddings. Mirror the default model in mem0/embeddings/fastembed.py.


Part of the TypeScript ↔ Python SDK provider-parity effort. One provider per issue (atomic).

贡献者指南