Skip to content

解析qtbase-opensource-src 仓库,报错tokens数量太大 #470

@Bob2019-li

Description

@Bob2019-li

ERROR - api.simple_chat - simple_chat.py:501 - Error with Openai API: Error code: 413 - {'error': {'message': '输入Tokens数量(1176440)超过系统限制(1000000) (request id: 2026020123301026091426VGEK0SGk)', 'type': 'new_api_error', 'param': '', 'code': 'local:invalid_request'}}

是下面这段代码报的错:
elif request.provider == "openai":
try:
# Get the response and handle it properly using the previously created api_kwargs
logger.info("Making Openai API call")
response = await model.acall(api_kwargs=api_kwargs, model_type=ModelType.LLM)
# Handle streaming response from Openai
async for chunk in response:
choices = getattr(chunk, "choices", [])
if len(choices) > 0:
delta = getattr(choices[0], "delta", None)
if delta is not None:
text = getattr(delta, "content", None)
if text is not None:
yield text
except Exception as e_openai:
logger.error(f"Error with Openai API: {str(e_openai)}")
yield f"\nError with Openai API: {str(e_openai)}\n\nPlease check that you have set the OPENAI_API_KEY environment variable with a valid API key."

我使用的embedder.json配置内容,用的是openai api

{
  "embedder": {
    "client_class": "OpenAIClient",
    "initialize_kwargs": {
      "api_key": "${OPENAI_API_KEY}",
      "base_url": "${OPENAI_BASE_URL}"
    },
    "batch_size": 8,
    "model_kwargs": {
      "model": "text-embedding-3-large",
      "dimensions": 512,
      "encoding_format": "float"
    }
  },
  "embedder_ollama": {
    "client_class": "OllamaClient",
    "model_kwargs": {
      "model": "nomic-embed-text"
    }
  },
  "retriever": {
    "top_k": 10
  },
  "text_splitter": {
    "split_by": "token",
    "chunk_size": 300,
    "chunk_overlap": 60
  }
}

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions