trafficstars
起始日期 | Start Date
No response
实现PR | Implementation PR
No response
相关Issues | Reference Issues
No response
摘要 | Summary
希望能支持autogen直接调用api-for-open-llm的api接口。
基本示例 | Basic Example
希望能支持autogen
缺陷 | Drawbacks
无
未解决问题 | Unresolved questions
No response
API-FOR-OPEN-LLM当前支持autogen单个agent使用，但是多个agent调用时报错。
报错信息如下：
user_proxy (to chat_manager):
find a lastest paper about gpt-4 on arxiv and find its potential applications in software.
Traceback (most recent call last):
File "/tools/codes/test-autogen02/react_demo4.py", line 697, in
test_autogen15()
File "/tools/codes/test-autogen02/react_demo4.py", line 690, in test_autogen15
user_proxy.initiate_chat(
File "/root/anaconda3/envs/test-autogen02/lib/python3.10/site-packages/autogen/agentchat/conversable_agent.py", line 550, in initiate_chat
self.send(self.generate_init_message(**context), recipient, silent=silent)
File "/root/anaconda3/envs/test-autogen02/lib/python3.10/site-packages/autogen/agentchat/conversable_agent.py", line 348, in send
recipient.receive(message, self, request_reply, silent)
File "/root/anaconda3/envs/test-autogen02/lib/python3.10/site-packages/autogen/agentchat/conversable_agent.py", line 481, in receive
reply = self.generate_reply(messages=self.chat_messages[sender], sender=sender)
File "/root/anaconda3/envs/test-autogen02/lib/python3.10/site-packages/autogen/agentchat/conversable_agent.py", line 906, in generate_reply
final, reply = reply_func(self, messages=messages, sender=sender, config=reply_func_tuple["config"])
File "/root/anaconda3/envs/test-autogen02/lib/python3.10/site-packages/autogen/agentchat/groupchat.py", line 269, in run_chat
speaker = groupchat.select_speaker(speaker, self)
File "/root/anaconda3/envs/test-autogen02/lib/python3.10/site-packages/autogen/agentchat/groupchat.py", line 158, in select_speaker
final, name = selector.generate_oai_reply(
File "/root/anaconda3/envs/test-autogen02/lib/python3.10/site-packages/autogen/agentchat/conversable_agent.py", line 625, in generate_oai_reply
response = client.create(
File "/root/anaconda3/envs/test-autogen02/lib/python3.10/site-packages/autogen/oai/client.py", line 247, in create
response = self._completions_create(client, params)
File "/root/anaconda3/envs/test-autogen02/lib/python3.10/site-packages/autogen/oai/client.py", line 327, in _completions_create
response = completions.create(**params)
File "/root/anaconda3/envs/test-autogen02/lib/python3.10/site-packages/openai/_utils/_utils.py", line 299, in wrapper
return func(*args, **kwargs)
File "/root/anaconda3/envs/test-autogen02/lib/python3.10/site-packages/openai/resources/chat/completions.py", line 598, in create
return self._post(
File "/root/anaconda3/envs/test-autogen02/lib/python3.10/site-packages/openai/_base_client.py", line 1063, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
File "/root/anaconda3/envs/test-autogen02/lib/python3.10/site-packages/openai/_base_client.py", line 842, in request
return self._request(
File "/root/anaconda3/envs/test-autogen02/lib/python3.10/site-packages/openai/_base_client.py", line 885, in _request
raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'detail': 'Invalid request: Incorrect role system.'}
Process finished with exit code 1
这是调用模型时的请求：
2023-12-01 09:05:37.232 | DEBUG | api.routes.chat:create_chat_completion:46 - ==== request ====
{'model': 'Qwen-14B-Chat', 'frequency_penalty': 0.0, 'function_call': None, 'functions': None, 'logit_bias': None, 'max_tokens': 1024, 'n': 1, 'presence_penalty': 0.0, 'response_format': None, 'seed': None, 'stop': ['<|endoftext|>', '<|im_end|>'], 'temperature': 0.0, 'tool_choice': None, 'tools': None, 'top_p': 1.0, 'user': None, 'stream': False, 'prompt_or_messages': [{'content': 'You are in a role play game. The following roles are available:\nuser_proxy: a human admin.\ncoder: You are a helpful AI assistant.\nSolve tasks using your coding and language skills.\nIn the following cases, suggest python code (in a python coding block) or shell script (in a sh coding block) for the user to execute.\n 1. When you need to collect info, use the code to output the info you need, for example, browse or search the web, download/read a file, print the content of a webpage or a file, get the current date/time, check the operating system. After sufficient info is printed and the task is ready to be solved based on your language skill, you can solve the task by yourself.\n 2. When you need to perform some task with code, use the code to perform the task and output the result. Finish the task smartly.\nSolve the task step by step if you need to. If a plan is not provided, explain your plan first. Be clear which step uses code, and which step uses your language skill.\nWhen using code, you must indicate the script type in the code block. The user cannot provide any other feedback or perform any other action beyond executing the code you suggest. The user can't modify your code. So do not suggest incomplete code which requires users to modify. Don't use a code block if it's not intended to be executed by the user.\nIf you want the user to save the code in a file before executing it, put # filename: inside the code block as the first line. Don't include multiple code blocks in one response. Do not ask users to copy and paste the result. Instead, use 'print' function for the output when relevant. Check the execution result returned by the user.\nIf the result indicates there is an error, fix the error and output the code again. Suggest the full code instead of partial code or code changes. If the error can't be fixed or if the task is not solved even after the code is executed successfully, analyze the problem, revisit your assumption, collect additional info you need, and think of a different approach to try.\nWhen you find an answer, verify the answer carefully. Include verifiable evidence in your response if possible.\nReply "TERMINATE" in the end when everything is done.\n \npm: creative in software product ideas..\n\nRead the following conversation.\nThen select the next role from ['user_proxy', 'coder', 'pm'] to play. Only return the role.', 'role': 'system'}, {'content': 'find a lastest paper about gpt-4 on arxiv and find its potential applications in software.', 'role': 'user'}, {'content': "Read the above conversation. Then select the next role from ['user_proxy', 'coder', 'pm'] to play. Only return the role.", 'role': 'system'}], 'echo': False, 'stop_token_ids': [151643, 151644, 151645]}
INFO: 10.249.250.190:60878 - "POST /v1/chat/completions HTTP/1.1" 400 Bad Request
api-for-open-llm copied to clipboard
xusenlinzy
