Sebastian.W

建议用qwen2.5-VL-7b.

Hey, this is a must have fix for text with mixed Chinese and English words. When can this PR be merged? It seems there is not code conflicts.

@fireblade2534 is there any barrier block this PR? If not, could you please merge this PR? It's very important for scenario with mixed Chinese and English words.

I am getting the exact same error. It's raised from ``` wrenai-wren-ai-service-1 | File "/src/pipelines/indexing/db_schema.py", line 346, in __init__ wrenai-wren-ai-service-1 | "embedder": embedder_provider.get_document_embedder(), ``` and my WrenAI info as below:...

I am still getting the same error. My ai-service configuration as below: ``` type: embedder provider: openai_embedder timeout: 120 models: - model: openai/bce-embedding-base dimension: 768 url: http://bce-embedding.localai:8080/v1 --- type: pipeline...

> please use api_base for openai_embedder instead of url, thanks The error remains the same. I am going to provide the whole log: ``` Waiting for qdrant to start... qdrant...

@cyyeh The config.yaml file as below: ```yaml type: llm provider: litellm_llm timeout: 120 models: - model: openai/qwen2.5-72b-instruct api_base: https://llm.localai/v1 api_key_name: LLM_OPENAI_API_KEY kwargs: temperature: 0 n: 1 # for better consistency...