AutoRAG TroubleShooting

1. API Connection Error

APIConnectionError: Connection error.

If you’ve encountered that error log, you’re probably using OPENAI but forgot to set OPENAI_API_KEY as an environment variable.

If so, you can set the API Key in one of two ways!

1. Setting the OPENAI_API_KEY environment variable with export

export OPENAI_API_KEY=sk-xxx(Your OPENAI API KEY)

2. Putting the api_key directly in the YAML file

- node_type: generator
  strategy:
    metrics: [bleu, meteor, rouge]
  modules:
    - module_type: llama_index_llm
      llm: openai
      model: gpt-3.5-turbo
      batch: 4
      api_key: your_api_key

2. LlamaIndex Import Error

ImportError: cannot import name 'Document' from 'llama_index.core'

If you encountered the following llama_index ImportError, you need to check your LlamaIndex version.

If it is lower than 0.10.0, you need to use a version at least 0.10.0!

3. GPU-related Error

No available memory for the cache block

The error appears to be a VRAM out of memory error.

In this case, try lowering the batch (which can be set as a module parameter in YAML) as much as possible, If that doesn't work, we recommend using a quantized model (if available)!

4. UnicodeDecodeError

UnicodeDecodeError: 'cp949' codec can't decode
byte 0xeb in position 1371: illegal multibyte
sequence

Error reading a parquet file on Windows!

The workaround on Windows is to use engine=’pyarrow’, This is something that needs to be fixed inside AutoRAG.

We’ll try to fix it in the issue :)

For now, please use Mac or Linux (or WSL on Windows)!