deer-flow
deer-flow copied to clipboard
Published
3 weeks ago
•
bytedance
bytedance
planner可以正常出结果，但是_execute_agent_step中报错400
感谢开源，报错信息如下：
================================== Ai Message ==================================
Name: planner
{
"locale": "zh-CN",
"has_enough_context": false,
"thought": "用户想要了解大模型时代的技术发展情况，需从多个方面进行研究，以呈现全面且深入的技术发展态势。",
"title": "大模型时代技术发展的研究计划",
"steps": [
{
"need_web_search": true,
"title": "大模型时代技术发展的历史与现状研究",
"description": "收集大模型从起步到当前阶段的关键时间节点及标志性技术突破；各阶段代表性大模型的参数规模、训练数据量、应用领域等数据；当前主流大模型在自然语言处理、计算机视觉等主要领域的性能指标与应用成果。",
"step_type": "research"
},
{
"need_web_search": true,
"title": "大模型技术发展的未来预测与利益相关者研究",
"description": "收集各大研究机构与专家对大模型未来3 - 5年在技术能力、应用拓展等方面的预测报告；分析大模型技术发展涉及的主要利益相关者，如科技企业、科研机构、政府部门等的态度、投入与期望。",
"step_type": "research"
},
{
"need_web_search": true,
"title": "大模型技术发展的风险与挑战研究",
"description": "梳理大模型在数据隐私、伦理道德、计算资源消耗等方面面临的问题与挑战；收集已有的应对措施、政策法规及行业规范等相关资料。",
"step_type": "research"
}
]
}
2025-05-15 10:09:34,822 - src.graph.nodes - INFO - Research team is collaborating on tasks.
2025-05-15 10:09:34,823 - src.graph.nodes - INFO - Researcher node is researching.
2025-05-15 10:09:42,765 - src.graph.nodes - INFO - Executing step: 大模型时代技术发展的历史与现状研究
2025-05-15 10:09:42,985 - httpx - INFO - HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions "HTTP/1.1 400 Bad Request"
Traceback (most recent call last):
File "/Users/ritian/work/deer-flow/main.py", line 146, in <module>
ask(
File "/Users/ritian/work/deer-flow/main.py", line 33, in ask
asyncio.run(
File "/Users/ritian/.local/share/uv/python/cpython-3.12.10-macos-aarch64-none/lib/python3.12/asyncio/runners.py", line 195, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/Users/ritian/.local/share/uv/python/cpython-3.12.10-macos-aarch64-none/lib/python3.12/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/ritian/.local/share/uv/python/cpython-3.12.10-macos-aarch64-none/lib/python3.12/asyncio/base_events.py", line 691, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/Users/ritian/work/deer-flow/src/workflow.py", line 78, in run_agent_workflow_async
async for s in graph.astream(
File "/Users/ritian/work/deer-flow/.venv/lib/python3.12/site-packages/langgraph/pregel/__init__.py", line 2305, in astream
async for _ in runner.atick(
File "/Users/ritian/work/deer-flow/.venv/lib/python3.12/site-packages/langgraph/pregel/runner.py", line 444, in atick
await arun_with_retry(
File "/Users/ritian/work/deer-flow/.venv/lib/python3.12/site-packages/langgraph/pregel/retry.py", line 128, in arun_with_retry
return await task.proc.ainvoke(task.input, config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/ritian/work/deer-flow/.venv/lib/python3.12/site-packages/langgraph/utils/runnable.py", line 583, in ainvoke
input = await step.ainvoke(input, config, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/ritian/work/deer-flow/.venv/lib/python3.12/site-packages/langgraph/utils/runnable.py", line 371, in ainvoke
ret = await asyncio.create_task(coro, context=context)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/ritian/work/deer-flow/src/graph/nodes.py", line 427, in researcher_node
return await _setup_and_execute_agent_step(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/ritian/work/deer-flow/src/graph/nodes.py", line 416, in _setup_and_execute_agent_step
return await _execute_agent_step(state, agent, agent_type)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/ritian/work/deer-flow/src/graph/nodes.py", line 338, in _execute_agent_step
result = await agent.ainvoke(input=agent_input)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
...
...
openai.BadRequestError: Error code: 400 - {'error': {'code': 'InvalidParameter', 'message': "Invalid function format: 'type' Request id: 021747274983045b74caa216dfc0d2d7ac74b9263441db7c0e3e3", 'param': '', 'type': 'BadRequest'}}
During task with name 'agent' and id '099f2da0-c98f-e4b7-3312-1d910690fb67'
During task with name 'researcher' and id '6730d661-f5d6-2e0d-3764-2d6431ba0fad'
Could you provide which model you are using?
AGENT_LLM_MAP: dict[str, LLMType] = {
"coordinator": "basic",
"planner": "reasoning",
"researcher": "reasoning",
"coder": "basic",
"reporter": "reasoning",
"podcast_script_writer": "basic",
"ppt_composer": "basic",
"prose_writer": "basic",
}
BASIC_MODEL:
base_url: https://ark.cn-beijing.volces.com/api/v3
model: "deepseek-v3-250324"
# model: "doubao-1-5-pro-32k-250115"
max_tokens: 8192
REASONING_MODEL:
base_url: https://ark.cn-beijing.volces.com/api/v3
model: "doubao-1-5-thinking-vision-pro-250428"
max_tokens: 8192
VISION_MODEL:
base_url: https://ark.cn-beijing.volces.com/api/v3
model: "doubao-1-5-thinking-vision-pro-250428"
max_tokens: 8192
Could you provide which model you are using?
AGENT_LLM_MAP: dict[str, LLMType] = {
"coordinator": "basic",
"planner": "basic",
"researcher": "basic",
"coder": "basic",
"reporter": "basic",
"podcast_script_writer": "basic",
"ppt_composer": "basic",
"prose_writer": "basic",
}
BASIC_MODEL:
base_url: https://ark.cn-beijing.volces.com/api/v3
model: "doubao-1-5-pro-32k-250115"
+1
openai.BadRequestError: Error code: 400 - {'error': {'message': "This model's maximum context length is 131072 tokens. However, you requested 170799 tokens (170799 in the messages, 0 in the completion). Please reduce the length of the messages or completion.", 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_request_error'}} During task with name 'agent' and id '544dd79f-df3b-291e-b26d-b11f850ccdc7' During task with name 'researcher' and id '0c0c2341-b9bd-9784-a0cf-1ddcd9fe5a02'
