langgenius / dify

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
https://dify.ai
Other
45.99k stars 6.48k forks source link

jina-embeddings-v2-base-zh model load balancing failed to save #8591

Open 18075717849 opened 2 hours ago

18075717849 commented 2 hours ago

Self Checks

Dify version

0.8.2

Cloud or Self Hosted

Cloud

Steps to reproduce

lQLPJw4eLgqYaxPNAvrNBL-wHWJ8Q79M7dQG1UigdNsnAA_1215_762 jina-embeddings-v2-base-zh model load balancing failed to save, prompting me that the parameter base_url is missing, all jina model load balancing failed, but openai can be saved, all jina model load balancing failed, prompting that base_url is missing

✔️ Expected Behavior

I hope to know how to modify it to make jina load balancing save successfully.

❌ Actual Behavior

jina-embeddings-v2-base-zh model load balancing failed to save, prompting me that the parameter base_url is missing, all jina model load balancing failed, but openai can be saved, all jina model load balancing failed, prompting that base_url is missing

dosubot[bot] commented 2 hours ago

I found a similar open issue regarding the base_url parameter missing when using the Jina model for load balancing. The issue is still open and was last updated on September 20, 2024. The suggested solution is to ensure that the base_url parameter is included in the credentials dictionary when configuring load balancing for the Jina model. If base_url is not included, the code defaults to using self.api_base, which is set to "https://api.jina.ai/v1".

Here's the relevant code snippet:

base_url = credentials.get("base_url", self.api_base)
base_url = base_url.removesuffix("/")

To resolve this issue, make sure to include the base_url parameter in the credentials dictionary when setting up the Jina model load balancing [1].

For more detailed steps on configuring model load balancing, you can refer to the documentation titled "zh_CN/guides/model-configuration/load-balancing.md" [2].

To continue talking to Dosu, mention @dosu.