Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Error while running video_understanding demo #200

Open
ruspaul013 opened this issue Jan 23, 2025 · 4 comments
Open

Error while running video_understanding demo #200

ruspaul013 opened this issue Jan 23, 2025 · 4 comments
Assignees
@XeonHis

Comments

@ruspaul013
Copy link

Hello!

While trying to run the video_understanding demo, I got this error:

Please input the video path:(Waiting for input. Your input can only be text or image path each time, you can press Enter once to input multiple times. Press Enter twice to finish the entire
 input.):
>>>/root/test.mov
>>>what is inside?
>>>
INFO | 2025-01-23 15:12:21,107 | /root/github/OmAgent/examples/video_understanding/run_cli.py:79 | <module> | User input lines: ['/root/test.mov', 'what is inside?']
INFO | 2025-01-23 15:12:21,457 | /root/github/OmAgent/omagent-core/src/omagent_core/clients/devices/app/input.py:79 | read_input | Received message: {'payload': '{"agent_id": "57921ba3-b050-4138-bac7-0cfd4b885553", "messages": [{"role": "user", "content": [{"type": "image_url", "data": "/root/test.mov"}, {"type": "text", "data": "what is inside?"}]}], "kwargs": {}}'}
  Detected: 0 | Progress:   0%|                                                                                                                                  | 0/582 [00:00<?, ?frames/s]2025-01-23 15:12:21,555 pyscenedetect INFO     Detecting scenes...
  Detected: 0 | Progress: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊| 581/582 [00:01<00:00, 567.87frames/s]2025-01-23 15:12:22,714 [3113034] omagent_core.engine.worker.base ERROR    Error executing task VideoPreprocessor with id de26c1ab-748a-40c6-a641-c4147b1c6b6c.  error = Traceback (most recent call last):
  File "/root/github/OmAgent/omagent-core/src/omagent_core/engine/worker/base.py", line 141, in execute
    task_output = self._run(**task_input)
                  ^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/github/OmAgent/examples/video_understanding/agent/video_preprocessor/video_preprocess.py", line 182, in _run
    video = VideoScenes.load(
            ^^^^^^^^^^^^^^^^^
  File "/root/github/OmAgent/examples/video_understanding/agent/misc/scene.py", line 98, in load
    audio = AudioSegment.from_file(video_path)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/omagent/lib64/python3.11/site-packages/pydub/audio_segment.py", line 728, in from_file
    info = mediainfo_json(orig_file, read_ahead_limit=read_ahead_limit)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/omagent/lib64/python3.11/site-packages/pydub/utils.py", line 279, in mediainfo_json
    info = json.loads(output)
           ^^^^^^^^^^^^^^^^^^
  File "/usr/lib64/python3.11/json/__init__.py", line 346, in loads
    return _default_decoder.decode(s)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib64/python3.11/json/decoder.py", line 337, in decode
    obj, end = self.raw_decode(s, idx=_w(s, 0).end())
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib64/python3.11/json/decoder.py", line 353, in raw_decode
    obj, end = self.scan_once(s, idx)
               ^^^^^^^^^^^^^^^^^^^^^^
json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 2 column 1 (char 2)

I am using local models and for STT and Embedding I followed the example from #197 .

Version: v0.2.2

If you need more details, please let me know.
@XeonHis
Copy link
Collaborator

XeonHis commented Jan 24, 2025

It seems there are some audio issues in the video file.
Could you provide the related video file /root/test.mov so we can find out the reason further? In the meantime, you can try using other video files to test the video_understanding process again.

@XeonHis XeonHis self-assigned this Jan 24, 2025
@ruspaul013
Copy link
Author

ruspaul013 commented Jan 24, 2025 •
edited
Loading

Sorry but I can't give you the test.mov file, but I found another one with the same problem.

Please input the video path:(Waiting for input. Your input can only be text or image path each time, you can press Enter once to input multiple times. Press Enter twice to finish the entire
 input.):
>>>/nfs/exports/file_example_AVI_640_800kB.avi
>>>what is in this video?
>>>
INFO | 2025-01-24 09:39:47,393 | /root/github/OmAgent/examples/video_understanding/run_cli.py:79 | <module> | User input lines: ['/nfs/exports/file_example_AVI_640_800kB.avi', 'what is in t
his video?']
INFO | 2025-01-24 09:39:47,977 | /root/github/OmAgent/omagent-core/src/omagent_core/clients/devices/app/input.py:79 | read_input | Received message: {'payload': '{"agent_id": "e77f4dd4-0d11
-495c-9df0-a64148a71090", "messages": [{"role": "user", "content": [{"type": "image_url", "data": "/nfs/exports/file_example_AVI_640_800kB.avi"}, {"type": "text", "data": "what is in this v
ideo?"}]}], "kwargs": {}}'}
  Detected: 0 | Progress:   0%|                                                                                                                                  | 0/901 [00:00<?, ?frames/s]
2025-01-24 09:39:48,033 pyscenedetect INFO     Detecting scenes...
  Detected: 0 | Progress: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 901/901 [00:00<00:00, 1397.57frames/s]
2025-01-24 09:39:48,826 [3404590] omagent_core.engine.worker.base ERROR    Error executing task VideoPreprocessor with id 25ace73f-c30f-4cff-acc4-23114e16ed18.  error = Traceback (most rece
nt call last):
  File "/root/github/OmAgent/omagent-core/src/omagent_core/engine/worker/base.py", line 141, in execute
    task_output = self._run(**task_input)
                  ^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/github/OmAgent/examples/video_understanding/agent/video_preprocessor/video_preprocess.py", line 182, in _run
    video = VideoScenes.load(
            ^^^^^^^^^^^^^^^^^
  File "/root/github/OmAgent/examples/video_understanding/agent/misc/scene.py", line 98, in load
    audio = AudioSegment.from_file(video_path)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/omagent/lib64/python3.11/site-packages/pydub/audio_segment.py", line 728, in from_file
    info = mediainfo_json(orig_file, read_ahead_limit=read_ahead_limit)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/omagent/lib64/python3.11/site-packages/pydub/utils.py", line 279, in mediainfo_json
    info = json.loads(output)
           ^^^^^^^^^^^^^^^^^^
  File "/usr/lib64/python3.11/json/__init__.py", line 346, in loads
    return _default_decoder.decode(s)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib64/python3.11/json/decoder.py", line 337, in decode
    obj, end = self.raw_decode(s, idx=_w(s, 0).end())
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib64/python3.11/json/decoder.py", line 353, in raw_decode
    obj, end = self.scan_once(s, idx)
               ^^^^^^^^^^^^^^^^^^^^^^
json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 2 column 1 (char 2)

file: https://file-examples.com/index.php/sample-video-files/sample-avi-files-download/ - the second file ( I could not attach the avi file )

@ruspaul013
Copy link
Author

ruspaul013 commented Jan 24, 2025 •
edited
Loading

I tried with a wmv file, but I get this error

Please input the video path:(Waiting for input. Your input can only be text or image path each time, you can press Enter once to input multiple times. Press Enter twice to finish the entire
 input.):
>>>/nfs/exports/file_example_WMV_640_1_6MB.wmv
>>>what is in this video?
>>>
INFO | 2025-01-24 09:41:29,675 | /root/github/OmAgent/examples/video_understanding/run_cli.py:79 | <module> | User input lines: ['/nfs/exports/file_example_WMV_640_1_6MB.wmv', 'what is in t
his video?']
INFO | 2025-01-24 09:41:30,128 | /root/github/OmAgent/omagent-core/src/omagent_core/clients/devices/app/input.py:79 | read_input | Received message: {'payload': '{"agent_id": "e77f4dd4-0d11
-495c-9df0-a64148a71090", "messages": [{"role": "user", "content": [{"type": "image_url", "data": "/nfs/exports/file_example_WMV_640_1_6MB.wmv"}, {"type": "text", "data": "what is in this v
ideo?"}]}], "kwargs": {}}'}
  Detected: 0 | Progress:   0%|                                                                                                                                  | 0/918 [00:00<?, ?frames/s]
2025-01-24 09:41:30,166 pyscenedetect INFO     Detecting scenes...
  Detected: 0 | Progress:  98%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊  | 901/918 [00:00<00:00, 1535.27frames/s]
Processing scene 0 / 1...
2025-01-24 09:41:31,454 httpx        INFO     HTTP Request: POST http://10.150.92.131:8081/audio/transcriptions "HTTP/1.1 404 Not Found"
2025-01-24 09:41:31,465 [3404590] omagent_core.engine.worker.base ERROR    Error executing task VideoPreprocessor with id 974e0af5-39a8-4d36-a762-8deb4c7282e8.  error = Traceback (most rece
nt call last):
  File "/root/github/OmAgent/omagent-core/src/omagent_core/engine/worker/base.py", line 141, in execute
    task_output = self._run(**task_input)
                  ^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/github/OmAgent/examples/video_understanding/agent/video_preprocessor/video_preprocess.py", line 198, in _run
    scene.stt_res = self.stt.infer(audio_clip)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/github/OmAgent/omagent-core/src/omagent_core/models/asr/stt.py", line 38, in infer
    trans = self.client.audio.transcriptions.create(
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/omagent/lib64/python3.11/site-packages/openai/resources/audio/transcriptions.py", line 188, in create
    return self._post(  # type: ignore[return-value]
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/omagent/lib64/python3.11/site-packages/openai/_base_client.py", line 1283, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/omagent/lib64/python3.11/site-packages/openai/_base_client.py", line 960, in request
    return self._request(
           ^^^^^^^^^^^^^^
  File "/root/omagent/lib64/python3.11/site-packages/openai/_base_client.py", line 1064, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.NotFoundError: Error code: 404 - {'error': {'code': 404, 'message': 'Resource not found', 'type': ''}}

and in local-ai I get

9:41AM WRN Client error ip=10.150.92.131 latency="361.705µs" method=POST status=404 url=/audio/transcriptions

I restarted the local-ai server and I get this now

Please input the video path:(Waiting for input. Your input can only be text or image path each time, you can press Enter once to input multiple times. Press Enter twice to finish the entire
 input.):
>>>/nfs/exports/file_example_WMV_640_1_6MB.wmv
>>>what is inside?
>>>
INFO | 2025-01-24 09:50:24,749 | /root/github/OmAgent/examples/video_understanding/run_cli.py:79 | <module> | User input lines: ['/nfs/exports/file_example_WMV_640_1_6MB.wmv', 'what is insi
de?']
INFO | 2025-01-24 09:50:25,253 | /root/github/OmAgent/omagent-core/src/omagent_core/clients/devices/app/input.py:79 | read_input | Received message: {'payload': '{"agent_id": "e77f4dd4-0d1$
-495c-9df0-a64148a71090", "messages": [{"role": "user", "content": [{"type": "image_url", "data": "/nfs/exports/file_example_WMV_640_1_6MB.wmv"}, {"type": "text", "data": "what is inside?"}
]}], "kwargs": {}}'}
2025-01-24 09:50:25,302 [3404590] omagent_core.engine.worker.base ERROR    Error executing task VideoPreprocessor with id b9b49f5d-ed3d-443e-86ac-fe85244efbd3.  error = Traceback (most rece
nt call last):
  File "/root/github/OmAgent/omagent-core/src/omagent_core/engine/worker/base.py", line 141, in execute
    task_output = self._run(**task_input)
                  ^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/github/OmAgent/examples/video_understanding/agent/video_preprocessor/video_preprocess.py", line 251, in _run
    pickle.dump(video.scenes, f)
                ^^^^^
UnboundLocalError: cannot access local variable 'video' where it is not associated with a value

2025-01-24 09:50:29,813 [3404590] omagent_core.engine.automator.task_handler INFO     Stopped worker processes...

or

Please input the video path:(Waiting for input. Your input can only be text or image path each time, you can press Enter once to input multiple times. Press Enter twice to finish the entire input.):
>>>/nfs/exports/file_example_WMV_640_1_6MB.wmv
>>>what is inside this video?
>>>
INFO | 2025-01-24 09:55:54,651 | /root/github/OmAgent/examples/video_understanding/run_cli.py:79 | <module> | User input lines: ['/nfs/exports/file_example_WMV_640_1_6MB.wmv', 'what is inside this video?']
INFO | 2025-01-24 09:55:54,838 | /root/github/OmAgent/omagent-core/src/omagent_core/clients/devices/app/input.py:79 | read_input | Received message: {'payload': '{"agent_id": "3f77d919-c6a2-4fd5-924f-4b3f0a1abec9", "messages": [{"role": "user", "content": [{"type": "image_url", "data": "/nfs/exports/file_example_WMV_640_1_6MB.wmv"}, {"type": "text", "data": "what is inside this video?"}]}], "kwargs": {}}'}
2025-01-24 09:55:54,859 [3411265] omagent_core.engine.worker.base ERROR    Error executing task VideoPreprocessor with id e4cc7763-e4bf-443d-b344-a8be6e5bca7b.  error = Traceback (most recent call last):
  File "/root/github/OmAgent/omagent-core/src/omagent_core/engine/worker/base.py", line 141, in execute
    task_output = self._run(**task_input)
                  ^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/github/OmAgent/examples/video_understanding/agent/video_preprocessor/video_preprocess.py", line 100, in _run
    loaded_scene = pickle.load(f)
                   ^^^^^^^^^^^^^^
EOFError: Ran out of input

file: https://file-examples.com/index.php/sample-video-files/sample-wmv-files-download/ - the second one

@yileld
Copy link
Contributor

yileld commented Jan 25, 2025 •
edited
Loading

I tried with a wmv file, but I get this error

Please input the video path:(Waiting for input. Your input can only be text or image path each time, you can press Enter once to input multiple times. Press Enter twice to finish the entire
 input.):
>>>/nfs/exports/file_example_WMV_640_1_6MB.wmv
>>>what is in this video?
>>>
INFO | 2025-01-24 09:41:29,675 | /root/github/OmAgent/examples/video_understanding/run_cli.py:79 | <module> | User input lines: ['/nfs/exports/file_example_WMV_640_1_6MB.wmv', 'what is in t
his video?']
INFO | 2025-01-24 09:41:30,128 | /root/github/OmAgent/omagent-core/src/omagent_core/clients/devices/app/input.py:79 | read_input | Received message: {'payload': '{"agent_id": "e77f4dd4-0d11
-495c-9df0-a64148a71090", "messages": [{"role": "user", "content": [{"type": "image_url", "data": "/nfs/exports/file_example_WMV_640_1_6MB.wmv"}, {"type": "text", "data": "what is in this v
ideo?"}]}], "kwargs": {}}'}
  Detected: 0 | Progress:   0%|                                                                                                                                  | 0/918 [00:00<?, ?frames/s]
2025-01-24 09:41:30,166 pyscenedetect INFO     Detecting scenes...
  Detected: 0 | Progress:  98%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊  | 901/918 [00:00<00:00, 1535.27frames/s]
Processing scene 0 / 1...
2025-01-24 09:41:31,454 httpx        INFO     HTTP Request: POST http://10.150.92.131:8081/audio/transcriptions "HTTP/1.1 404 Not Found"
2025-01-24 09:41:31,465 [3404590] omagent_core.engine.worker.base ERROR    Error executing task VideoPreprocessor with id 974e0af5-39a8-4d36-a762-8deb4c7282e8.  error = Traceback (most rece
nt call last):
  File "/root/github/OmAgent/omagent-core/src/omagent_core/engine/worker/base.py", line 141, in execute
    task_output = self._run(**task_input)
                  ^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/github/OmAgent/examples/video_understanding/agent/video_preprocessor/video_preprocess.py", line 198, in _run
    scene.stt_res = self.stt.infer(audio_clip)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/github/OmAgent/omagent-core/src/omagent_core/models/asr/stt.py", line 38, in infer
    trans = self.client.audio.transcriptions.create(
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/omagent/lib64/python3.11/site-packages/openai/resources/audio/transcriptions.py", line 188, in create
    return self._post(  # type: ignore[return-value]
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/omagent/lib64/python3.11/site-packages/openai/_base_client.py", line 1283, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/omagent/lib64/python3.11/site-packages/openai/_base_client.py", line 960, in request
    return self._request(
           ^^^^^^^^^^^^^^
  File "/root/omagent/lib64/python3.11/site-packages/openai/_base_client.py", line 1064, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.NotFoundError: Error code: 404 - {'error': {'code': 404, 'message': 'Resource not found', 'type': ''}}

and in local-ai I get

9:41AM WRN Client error ip=10.150.92.131 latency="361.705µs" method=POST status=404 url=/audio/transcriptions

I restarted the local-ai server and I get this now

Please input the video path:(Waiting for input. Your input can only be text or image path each time, you can press Enter once to input multiple times. Press Enter twice to finish the entire
 input.):
>>>/nfs/exports/file_example_WMV_640_1_6MB.wmv
>>>what is inside?
>>>
INFO | 2025-01-24 09:50:24,749 | /root/github/OmAgent/examples/video_understanding/run_cli.py:79 | <module> | User input lines: ['/nfs/exports/file_example_WMV_640_1_6MB.wmv', 'what is insi
de?']
INFO | 2025-01-24 09:50:25,253 | /root/github/OmAgent/omagent-core/src/omagent_core/clients/devices/app/input.py:79 | read_input | Received message: {'payload': '{"agent_id": "e77f4dd4-0d1$
-495c-9df0-a64148a71090", "messages": [{"role": "user", "content": [{"type": "image_url", "data": "/nfs/exports/file_example_WMV_640_1_6MB.wmv"}, {"type": "text", "data": "what is inside?"}
]}], "kwargs": {}}'}
2025-01-24 09:50:25,302 [3404590] omagent_core.engine.worker.base ERROR    Error executing task VideoPreprocessor with id b9b49f5d-ed3d-443e-86ac-fe85244efbd3.  error = Traceback (most rece
nt call last):
  File "/root/github/OmAgent/omagent-core/src/omagent_core/engine/worker/base.py", line 141, in execute
    task_output = self._run(**task_input)
                  ^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/github/OmAgent/examples/video_understanding/agent/video_preprocessor/video_preprocess.py", line 251, in _run
    pickle.dump(video.scenes, f)
                ^^^^^
UnboundLocalError: cannot access local variable 'video' where it is not associated with a value

2025-01-24 09:50:29,813 [3404590] omagent_core.engine.automator.task_handler INFO     Stopped worker processes...

or

Please input the video path:(Waiting for input. Your input can only be text or image path each time, you can press Enter once to input multiple times. Press Enter twice to finish the entire input.):
>>>/nfs/exports/file_example_WMV_640_1_6MB.wmv
>>>what is inside this video?
>>>
INFO | 2025-01-24 09:55:54,651 | /root/github/OmAgent/examples/video_understanding/run_cli.py:79 | <module> | User input lines: ['/nfs/exports/file_example_WMV_640_1_6MB.wmv', 'what is inside this video?']
INFO | 2025-01-24 09:55:54,838 | /root/github/OmAgent/omagent-core/src/omagent_core/clients/devices/app/input.py:79 | read_input | Received message: {'payload': '{"agent_id": "3f77d919-c6a2-4fd5-924f-4b3f0a1abec9", "messages": [{"role": "user", "content": [{"type": "image_url", "data": "/nfs/exports/file_example_WMV_640_1_6MB.wmv"}, {"type": "text", "data": "what is inside this video?"}]}], "kwargs": {}}'}
2025-01-24 09:55:54,859 [3411265] omagent_core.engine.worker.base ERROR    Error executing task VideoPreprocessor with id e4cc7763-e4bf-443d-b344-a8be6e5bca7b.  error = Traceback (most recent call last):
  File "/root/github/OmAgent/omagent-core/src/omagent_core/engine/worker/base.py", line 141, in execute
    task_output = self._run(**task_input)
                  ^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/github/OmAgent/examples/video_understanding/agent/video_preprocessor/video_preprocess.py", line 100, in _run
    loaded_scene = pickle.load(f)
                   ^^^^^^^^^^^^^^
EOFError: Ran out of input

file: https://file-examples.com/index.php/sample-video-files/sample-wmv-files-download/ - the second one

I can run the avi file, and local-ai is

INF Success ip=127.0.0.1 latency=12.056258541s method=POST status=200 url=/v1/audio/transcriptions

My version of pydub is 0.25.1.
It seems you miss /v1 in video_preprocessor.yml

endpoint: http://localhost:8080/v1

And please update ./agent/conclude/conclude.py from other example /examples/general_dnc/agent/conclude/conclude.py about iterator judgement part. This fix isn't updated yet.

from collections.abc import Iterator
.
.
.
 if isinstance(chat_complete_res, Iterator):
     last_output = "Answer: "
     self.callback.send_incomplete(
         agent_id=self.workflow_instance_id, msg="Answer: "
     )
     for chunk in chat_complete_res:
         if len(chunk.choices) > 0:
             current_msg = chunk.choices[0].delta.content if chunk.choices[0].delta.content is not None else ''
             self.callback.send_incomplete(
                 agent_id=self.workflow_instance_id,
                 msg=f"{current_msg}",
             )
             last_output += current_msg
     self.callback.send_answer(agent_id=self.workflow_instance_id, msg="")
 else:
     last_output = chat_complete_res["choices"][0]["message"]["content"]
     self.callback.send_answer(
         agent_id=self.workflow_instance_id,
         msg=f'Answer: {chat_complete_res["choices"][0]["message"]["content"]}',
     )
 self.callback.send_answer(agent_id=self.workflow_instance_id, msg=f"Token usage: {self.token_usage}")
 self.stm(self.workflow_instance_id).clear()
 return {"last_output": last_output}

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@XeonHis XeonHis

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@yileld @XeonHis @ruspaul013