we1s3

可以自定义提示词然后强制必须输入租户ID去生成sql吗

> Looks like what you’re hitting isn’t just an MSSQL driver issue, it maps to ProblemMap No.6 (logic collapse in retrieval layer). The stack trace shows query context breaking outside...

> > > [@xiatiandegaga](https://github.com/xiatiandegaga) since you declared `qwen3-fast` as alias in your llm config, you should put `litellm_llm.qwen3-fast` in pipe definitions instead of using `litellm_llm.default`. Also I think maybe you...

> > > > > [@xiatiandegaga](https://github.com/xiatiandegaga) since you declared `qwen3-fast` as alias in your llm config, you should put `litellm_llm.qwen3-fast` in pipe definitions instead of using `litellm_llm.default`. Also I think...

> [@we1s3](https://github.com/we1s3) could you attache complete wren-ai-service container log file? thanks Thank you for your reply. Perhaps this error is related to a mismatched vector model? 2025-08-20 17:39:41.575 | 2025-08-20...

> Looks like what you’re running into is very close to Problem [#7](https://github.com/Canner/WrenAI/issues/7) (provider / embedding mismatch in config.yaml). Basically when the embedding model (like qwen text-embedding-v3) and the LLM...

> Looks like what you’re running into is very close to Problem [#7](https://github.com/Canner/WrenAI/issues/7) (provider / embedding mismatch in config.yaml). Basically when the embedding model (like qwen text-embedding-v3) and the LLM...