Model Troubleshooting

(1) How to check model availability issues

1. For privately deployed models, first confirm whether the deployed model is normal.
2. Directly test whether the upstream model is running normally through CURL request (cloud model or private model are both tested).
3. Request OneAPI through CURL request to test whether the model is normal.
4. Use the model for testing in FastGPT.

Here are a few test CURL examples:

curl https://api.openai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }'

curl https://api.openai.com/v1/embeddings \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "The food was delicious and the waiter...",
    "model": "text-embedding-ada-002",
    "encoding_format": "float"
  }'

curl --location --request POST 'https://xxxx.com/api/v1/rerank' \
--header 'Authorization: Bearer {{ACCESS_TOKEN}}' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "bge-rerank-m3",
  "query": "Who is the director",
  "documents": [
    "Who are you?\nI am the assistant of the movie 'Suzume'"
  ]
}'

curl https://api.openai.com/v1/audio/speech \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "The quick brown fox jumped over the lazy dog.",
    "voice": "alloy"
  }' \
  --output speech.mp3

curl https://api.openai.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F file="@/path/to/file/audio.mp3" \
  -F model="whisper-1"

(2) Error - Model response is empty/Model error

This error is due to the fact that under stream mode, oneapi directly ended the stream request and did not return any content.

Version 4.8.10 added error logs. When an error occurs, the actual Body parameters sent will be printed in the log. You can copy the parameters and send a request test to oneapi through curl.

Since oneapi cannot correctly capture errors in stream mode, sometimes you can set stream=false to get the exact error.

Possible error issues:

1. Domestic models hit risk control.
2. Unsupported model parameters: only keep messages and necessary parameters for testing, delete other parameters for testing.

(3) "Current group upstream load is saturated, please try again later"

If you encounter this error (e.g. request id:xxx) in the logs or response, this is typically an OneAPI channel issue. Try switching to a different model or a different relay provider.

(4) "Connection Error" in logs when using the API

Most likely the API key is pointing to OpenAI's endpoint, but the server is deployed in mainland China and can't reach overseas endpoints. Use a relay service or reverse proxy to resolve the connectivity issue.

(5) Enable image indexing reports 400

You need to correctly configure the OCR model in Admin -> System Configuration.