autogpt/llm_utils.py 137行代码可以考虑优化一下
zky001 opened this issue · comments
return openai.Embedding.create(
input=[text], model="text-embedding-ada-002"
)["data"][0]["embedding"]
可能导致
File "/media/Data/data/bone_seg/Auto-GPT-ZH-0.2.1/autogpt/memory/local.py", line 75, in add
embedding = create_embedding_with_ada(text)
File "/media/Data/data/bone_seg/Auto-GPT-ZH-0.2.1/autogpt/llm_utils.py", line 137, in create_embedding_with_ada
return openai.Embedding.create(
File "/home/anaconda3/lib/python3.9/site-packages/openai/api_resources/embedding.py", line 33, in create
response = super().create(*args, **kwargs)
File "/home/anaconda3/lib/python3.9/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create
response, _, api_key = requestor.request(
File "/home/anaconda3/lib/python3.9/site-packages/openai/api_requestor.py", line 226, in request
resp, got_stream = self._interpret_response(result, stream)
File "/home/anaconda3/lib/python3.9/site-packages/openai/api_requestor.py", line 619, in _interpret_response
self._interpret_response_line(
File "/home/anaconda3/lib/python3.9/site-packages/openai/api_requestor.py", line 682, in _interpret_response_line
raise self.handle_error_response(
openai.error.InvalidRequestError: This model's maximum context length is 8191 tokens, however you requested 11300 tokens (11300 in your prompt; 0 for the completion). Please reduce your prompt; or completion length.
解决思路：
1.限制此处text的长度，做个长度限制
2.直接把这块报错给expect掉
还有一个错误
可以考虑，我看了下原项目也有这个问题，如果明天他们不修复的话，我再修复
响应是对方返回东西，存在情况比较多，可能是没网，可能对方网站异常，暂时不处理