Chih-Yu Yeh
Chih-Yu Yeh
@taoistwar hi, thanks for reaching out. could you help add this data source recommendation here? https://github.com/Canner/WrenAI/discussions/327
@skumarlabs @santosarns would you like to contribute on this? regarding to the implementation, I have some thoughts about this. given the [litellm docs](https://docs.litellm.ai/docs/guides/security_settings), I suggest we do several things basically...
> FYI my colleague and I believe we might have a workaround to simply set SSL_VERIFY=False in the environment, but it required a patch to the litellm codebase, which we...
@bpafoshizle @santosarns @skumarlabs I think you may try custom llm over https now, please follow several steps: 1. please make sure you are using this docker-compose.yaml(which is not released yet):...
@wxp2023 you could setup langfuse through this doc first: https://docs.getwren.ai/oss/ai_service/guide/langfuse_setup in simple words, the error message means that your llm generates malformed json output. After you setup langfuse, you could...
> ----------------------------------------error message > 2025-02-13 17:01:49 ERROR: Traceback (most recent call last): > 2025-02-13 17:01:49 File "/app/.venv/lib/python3.12/site-packages/starlette/routing.py", line 693, in lifespan > 2025-02-13 17:01:49 async with self.lifespan_context(app) as maybe_state: >...
> 我的env改成OPENAI_API_KEY=xxx，config.yaml也加了openai/，还是提示连接被拒绝，我觉得应该不是这个原因 我修改为openai的api试试 > > ``` > type: llm > provider: litellm_llm > models: > # put DEEPSEEK_API_KEY= in ~/.wrenai/.env > - api_base: https://api.deepseek.com/v1 > model: openai/deepseek/deepseek-chat > timeout: 120...
> > 我说说我遇到的几个坑吧。 一、首先遇到 > > 2025-02-13 17:01:49 File "/src/globals.py", line 240, in create_service_container > > 2025-02-13 17:01:49 **pipe_components["sql_pairs_deletion"], > > 2025-02-13 17:01:49 ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^ > > 2025-02-13 17:01:49 KeyError: 'sql_pairs_deletion'...
> > ## [@cyyeh](https://github.com/cyyeh) 感谢，感觉之前还是格式搞错了，不过我现在又遇到了 > > ` > > b'{"status":{"error":"Wrong input: Vector dimension error: expected dim: 3072, got 1024"},"time":0.011742224}' > > Oh no an error! Need help with Hamilton?...
> However, when my question is "How many...", the row count reported by the LLM is correct. > > WrenAI Version: 0.22.2 > LLM Model: Official DeepSeek @xpfxzxc Would u...