enhancementhelp wantedsdk-typescriptsize:M
Métricas do repositório
- Stars
- (55.741 estrelas)
- Métricas de merge de PR
- (Métricas PR pendentes)
Description
Summary
The Python SDK supports AWS Bedrock as an LLM provider, but the TypeScript OSS SDK (mem0ai/oss) does not. Add it to bring the TS SDK to parity.
| Python reference | mem0/llms/aws_bedrock.py |
| Registered in (Python) | mem0/utils/factory.py (LLMFactory) |
| Target file (TypeScript) | mem0-ts/src/oss/src/llms/aws_bedrock.ts |
| Suggested implementation | Use @aws-sdk/client-bedrock-runtime (BedrockRuntimeClient + InvokeModelCommand / ConverseCommand). |
Requirements
- Implement
AWSBedrockLLMinmem0-ts/src/oss/src/llms/aws_bedrock.ts, extendingLLM(mem0-ts/src/oss/src/llms/base.ts) and mirroring the Python provider's behavior (generateResponse / generateChat). - Register the
"aws_bedrock"provider inmem0-ts/src/oss/src/utils/factory.ts(LLMFactory). - Add config typing in
mem0-ts/src/oss/src/types/. - Add a unit test under
mem0-ts/src/oss/src/tests/. - Add
@aws-sdk/client-bedrock-runtimetomem0-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: llms/deepseek.ts (OpenAI-compatible) or llms/openai.ts.
Notes
Message formatting differs per model family (Anthropic, Titan, Llama, etc.) — mirror the per-model handling in mem0/llms/aws_bedrock.py. Auth via the standard AWS credential chain.
Part of the TypeScript ↔ Python SDK provider-parity effort. One provider per issue (atomic).