MetaGPT icon indicating copy to clipboard operation
MetaGPT copied to clipboard
verified publisher icon geekan

ollama run error

Open ThomasXIONG151215 opened this issue 1 year ago • 2 comments

Bug description I'm using ollama for MetaGPT, after setting up the config2.yml (associating None for API_KEY otherwise it wouldn't work) i tried using it in terminal above as well as under the downloaded MetaGPT directory, however, both tries return errors i do not quite understand.

Environment information

  • LLM type and model name: Ollama, Llama2
  • System version: Windows 11
  • Python version: python 3.11.4,
  • packages version:
  • installation method: git clone https://github.com/geekan/metagpt, pip install setup.py

Screenshots or logs

metagpt "write a cli blackjack game" 2024-03-06 10:10:37.067 | INFO | metagpt.const:get_metagpt_package_root:29 - Package root set to G:\MetaGPT\MetaGPT c:\users\administrator\appdata\local\programs\python\python311\lib\site-packages\langchain\vectorstores_init_.py:35: LangChainDeprecationWarning: Importing vector stores from langchain is deprecated. Importing from langchain will no longer be supported as of langchain==0.2.0. Please import from langchain-community instead:

from langchain_community.vectorstores import Chroma.

To install langchain-community run pip install -U langchain-community. warnings.warn( c:\users\administrator\appdata\local\programs\python\python311\lib\site-packages\langchain\vectorstores_init_.py:35: LangChainDeprecationWarning: Importing vector stores from langchain is deprecated. Importing from langchain will no longer be supported as of langchain==0.2.0. Please import from langchain-community instead:

from langchain_community.vectorstores import FAISS.

To install langchain-community run pip install -U langchain-community. warnings.warn( c:\users\administrator\appdata\local\programs\python\python311\lib\site-packages\langchain\document_loaders_init_.py:36: LangChainDeprecationWarning: Importing document loaders from langchain is deprecated. Importing from langchain will no longer be supported as of langchain==0.2.0. Please import from langchain-community instead:

from langchain_community.document_loaders import TextLoader.

To install langchain-community run pip install -U langchain-community. warnings.warn( c:\users\administrator\appdata\local\programs\python\python311\lib\site-packages\langchain\document_loaders_init_.py:36: LangChainDeprecationWarning: Importing document loaders from langchain is deprecated. Importing from langchain will no longer be supported as of langchain==0.2.0. Please import from langchain-community instead:

from langchain_community.document_loaders import UnstructuredPDFLoader.

To install langchain-community run pip install -U langchain-community. warnings.warn( c:\users\administrator\appdata\local\programs\python\python311\lib\site-packages\langchain\document_loaders_init_.py:36: LangChainDeprecationWarning: Importing document loaders from langchain is deprecated. Importing from langchain will no longer be supported as of langchain==0.2.0. Please import from langchain-community instead:

from langchain_community.document_loaders import UnstructuredWordDocumentLoader.

To install langchain-community run pip install -U langchain-community. warnings.warn( 2024-03-06 10:10:40.395 | INFO | metagpt.team:invest:90 - Investment: $3.0. 2024-03-06 10:10:40.397 | INFO | metagpt.roles.role:_act:399 - Alice(Product Manager): to do PrepareDocuments(PrepareDocuments) 2024-03-06 10:10:40.553 | INFO | metagpt.utils.file_repository:save:60 - save to: G:\MetaGPT\MetaGPT\workspace\20240306101040\docs\requirement.txt 2024-03-06 10:10:40.555 | INFO | metagpt.roles.role:_act:399 - Alice(Product Manager): to do WritePRD(WritePRD) 2024-03-06 10:10:40.559 | INFO | metagpt.actions.write_prd:run:86 - New requirement detected: write a cli blackjack game Understood! Here's the generated output for the given input:

context

Project Name

game_2048

Original Requirements

Create a 2048 game

Search Information

format example

[CONTENT] { "Language": "en_us", "Programming Language": "Python", "Original Requirements": "Create a 2048 game", "Project Name": "game_2048", "Product Goals": [ "Create an engaging user experience", "Improve accessibility, be responsive", "More beautiful UI" ], "User Stories": [ "As a player, I want to be able to choose difficulty levels", "As a player, I want to see my score after each game", "As a player, I want to get restart button when I lose", "As a player, I want to see beautiful UI that make me feel good", "As a player, I want to play game via mobile phone" ], "Competitive Analysis": [ "2048 Game A: Simple interface, lacks responsive features", "play2048.co: Beautiful and responsive UI with my best score shown", "2048game.com: Responsive UI with my best score shown, but many ads" ], "Competitive Quadrant Chart": "quadrantChart\n title "Reach and engagement of campaigns"\n x-axis "Low Reach" --> "High Reach"\n y-axis "Low Engagement" --> "High Engagement"\n quadrant-1 "We should expand"\n quadrant-2 "Need to promote"\n quadrant-3 "Re-evaluate"\n quadrant-4 "May be improved"\n "Campaign A": [0.3, 0.6]\n "Campaign B": [0.45, 0.23]\n "Campaign C": [0.57, 0.69]\n "Campaign D": [0.78, 0.34]\n "Campaign E": [0.40, 0.34]\n "Campaign F": [0.35, 0.78]\n "Our Target Product": [0.5, 0.6]", "Requirement Analysis": "", "Requirement Pool": [ [ "P0", "The main code ..." ], [ "P0", "The game algorithm ..." ] ], "UI Design draft": "Basic function description with a simple style and layout.", "Anything UNCLEAR": "" } [/CONTENT] Great! Here's the generated output for the given input:

nodes:

  • Language: en_us (English)
  • Programming Language: Python
  • Original Requirements: Create a 2048 game
  • Project Name: game_2048
  • Product Goals: + Create an engaging user experience + Improve accessibility, be responsive + More beautiful UI
  • User Stories: + As a player, I want to be able to choose difficulty levels + As a player, I want to see my score after each game + As a player, I want to get restart button when I lose + As a player, I want to see beautiful UI that make me feel good + As a player, I want to play game via mobile phone
  • Competitive Analysis: + 2048 Game A: Simple interface, lacks responsive features + play2048.co: Beautiful and responsive UI with my best score shown + 2048game.com: Responsive UI with my best score shown, but many ads
  • Competitive Quadrant Chart: + quadrantChart - title "Reach and engagement of campaigns" - x-axis Low Reach --> High Reach - y-axis Low Engagement --> High Engagement - quadrant-1 "We should expand" - quadrant-2 "Need to promote" - quadrant-3 "Re-evaluate" - quadrant-4 "May be improved" - Campaign A: [0.3, 0.6] - Campaign B: [0.45, 0.23] - Campaign C: [0.57, 0.69] - Campaign D: [0.78, 0.34] - Campaign E: [0.40, 0.34] - Campaign F: [0.35, 0.78] - Our Target Product: [0.5, 0.6]
  • Requirement Analysis: None
  • Requirement Pool: + P0: The main code ... + P0: The game algorithm ...
  • UI Design draft: Basic function description with a simple style and layout.
  • Anything UNCLEAR: None

I hope this helps! Let me know if you have any questions or need further clarification. 2024-03-06 10:10:57.991 | INFO | metagpt.utils.cost_manager:update_cost:103 - prompt_tokens: 1132, completion_tokens: 1280 2024-03-06 10:10:58.056 | WARNING | metagpt.utils.git_repository:rename_root:214 - Move G:\MetaGPT\MetaGPT\workspace\20240306101040 to G:\MetaGPT\MetaGPT\workspace\game_2048 error: [WinError 32] 另一个程序正在使用此文件，进程无法访问。: 'G:\MetaGPT\MetaGPT\workspace\20240306101040' 2024-03-06 10:10:58.057 | INFO | metagpt.utils.git_repository:rename_root:219 - Rename directory G:\MetaGPT\MetaGPT\workspace\20240306101040 to G:\MetaGPT\MetaGPT\workspace\game_2048 2024-03-06 10:10:58.064 | INFO | metagpt.utils.file_repository:save:60 - save to: G:\MetaGPT\MetaGPT\workspace\game_2048\docs\prd\20240306101058.json C:\Users\Administrator\AppData\Roaming\npm\mmdc C:\Users\Administrator\AppData\Roaming\npm\mmdc.cmd 2024-03-06 10:10:58.123 | INFO | metagpt.utils.mermaid:mermaid_to_file:48 - Generating G:\MetaGPT\MetaGPT\workspace\game_2048\resources\competitive_analysis\20240306101058.pdf.. 2024-03-06 10:10:58.179 | WARNING | metagpt.utils.mermaid:mermaid_to_file:74 - node:internal/modules/cjs/loader:1078 throw err; ^

Error: Cannot find module 'C:\Users\Administrator\AppData\Roaming\npm\node_modules@mermaid-js\mermaid-cli\src\cli.js' at Module._resolveFilename (node:internal/modules/cjs/loader:1075:15) at Module._load (node:internal/modules/cjs/loader:920:27) at Function.executeUserEntryPoint [as runMain] (node:internal/modules/run_main:81:12) at node:internal/main/run_main_module:23:47 { code: 'MODULE_NOT_FOUND', requireStack: [] }

Node.js v18.16.0

2024-03-06 10:10:58.180 | INFO | metagpt.utils.mermaid:mermaid_to_file:48 - Generating G:\MetaGPT\MetaGPT\workspace\game_2048\resources\competitive_analysis\20240306101058.svg.. 2024-03-06 10:10:58.510 | WARNING | metagpt.utils.mermaid:mermaid_to_file:74 - node:internal/modules/cjs/loader:1078 throw err; ^

Error: Cannot find module 'C:\Users\Administrator\AppData\Roaming\npm\node_modules@mermaid-js\mermaid-cli\src\cli.js' at Module._resolveFilename (node:internal/modules/cjs/loader:1075:15) at Module._load (node:internal/modules/cjs/loader:920:27) at Function.executeUserEntryPoint [as runMain] (node:internal/modules/run_main:81:12) at node:internal/main/run_main_module:23:47 { code: 'MODULE_NOT_FOUND', requireStack: [] }

Node.js v18.16.0

2024-03-06 10:10:58.511 | INFO | metagpt.utils.mermaid:mermaid_to_file:48 - Generating G:\MetaGPT\MetaGPT\workspace\game_2048\resources\competitive_analysis\20240306101058.png.. 2024-03-06 10:10:58.922 | WARNING | metagpt.utils.mermaid:mermaid_to_file:74 - node:internal/modules/cjs/loader:1078 throw err; ^

Error: Cannot find module 'C:\Users\Administrator\AppData\Roaming\npm\node_modules@mermaid-js\mermaid-cli\src\cli.js' at Module._resolveFilename (node:internal/modules/cjs/loader:1075:15) at Module._load (node:internal/modules/cjs/loader:920:27) at Function.executeUserEntryPoint [as runMain] (node:internal/modules/run_main:81:12) at node:internal/main/run_main_module:23:47 { code: 'MODULE_NOT_FOUND', requireStack: [] }

Node.js v18.16.0

2024-03-06 10:10:58.927 | INFO | metagpt.utils.file_repository:save:60 - save to: G:\MetaGPT\MetaGPT\workspace\game_2048\resources\prd\20240306101058.md 2024-03-06 10:10:58.930 | INFO | metagpt.roles.role:_act:399 - Bob(Architect): to do WriteDesign(WriteDesign) Understood! I will follow the instructions in the nodes and generate the output in the format example. Please provide me with the content for each node, and I will get started. 2024-03-06 10:11:00.011 | INFO | metagpt.utils.cost_manager:update_cost:103 - prompt_tokens: 1374, completion_tokens: 37 2024-03-06 10:11:00.014 | WARNING | metagpt.utils.repair_llm_raw_output:extract_content_from_output:308 - extract_content try another pattern: [CONTENT]([\s\S])[/CONTENT] 2024-03-06 10:11:00.014 | WARNING | metagpt.utils.repair_llm_raw_output:run_and_passon:256 - parse json from content inside [CONTENT][/CONTENT] failed at retry 1, exp: Expecting value: line 1 column 1 (char 0) 2024-03-06 10:11:00.015 | INFO | metagpt.utils.repair_llm_raw_output:repair_invalid_json:225 - repair_invalid_json, raw error: Expecting value: line 1 column 1 (char 0) 2024-03-06 10:11:00.016 | ERROR | metagpt.utils.common:log_it:476 - Finished call to 'metagpt.actions.action_node.ActionNode._aask_v1' after 0.906(s), this was the 1st time calling it. exp: RetryError[<Future at 0x1b34dad9d10 state=finished raised JSONDecodeError>] Understood! I will follow your instructions and generate the output in the format example you provided. Please provide me with the content for each node, and I will get started. 2024-03-06 10:11:01.255 | INFO | metagpt.utils.cost_manager:update_cost:103 - prompt_tokens: 0, completion_tokens: 36 2024-03-06 10:11:01.257 | WARNING | metagpt.utils.repair_llm_raw_output:extract_content_from_output:308 - extract_content try another pattern: [CONTENT]([\s\S])[/CONTENT] 2024-03-06 10:11:01.258 | WARNING | metagpt.utils.repair_llm_raw_output:run_and_passon:256 - parse json from content inside [CONTENT][/CONTENT] failed at retry 1, exp: Expecting value: line 1 column 1 (char 0) 2024-03-06 10:11:01.258 | INFO | metagpt.utils.repair_llm_raw_output:repair_invalid_json:225 - repair_invalid_json, raw error: Expecting value: line 1 column 1 (char 0) 2024-03-06 10:11:01.260 | ERROR | metagpt.utils.common:log_it:476 - Finished call to 'metagpt.actions.action_node.ActionNode._aask_v1' after 2.156(s), this was the 2nd time calling it. exp: RetryError[<Future at 0x1b34dc26a10 state=finished raised JSONDecodeError>] Understood! I will follow your instructions and generate the output in the requested format. Please provide me with the content for each node, and I will take care of the rest. 2024-03-06 10:11:03.626 | INFO | metagpt.utils.cost_manager:update_cost:103 - prompt_tokens: 0, completion_tokens: 37 2024-03-06 10:11:03.626 | WARNING | metagpt.utils.repair_llm_raw_output:extract_content_from_output:308 - extract_content try another pattern: [CONTENT]([\s\S]*)[/CONTENT] 2024-03-06 10:11:03.628 | WARNING | metagpt.utils.repair_llm_raw_output:run_and_passon:256 - parse json from content inside [CONTENT][/CONTENT] failed at retry 1, exp: Expecting value: line 1 column 1 (char 0) 2024-03-06 10:11:03.628 | INFO | metagpt.utils.repair_llm_raw_output:repair_invalid_json:225 - repair_invalid_json, raw error: Expecting value: line 1 column 1 (char 0) 2024-03-06 10:11:03.629 | ERROR | metagpt.utils.common:log_it:476 - Finished call to 'metagpt.actions.action_node.ActionNode._aask_v1' after 4.531(s), this was the 3rd time calling it. exp: RetryError[<Future at 0x1b34dbf8190 state=finished raised JSONDecodeError>] Of course! Here's my understanding of the given information:

Implementation approach: As per the requirements, we will analyze the difficult points of the project and select an appropriate open-source framework to implement the game.

File list: We only need to provide relative paths for the files. Therefore, the file list should include the following files:

  • main.py
  • game.py

Data structures and interfaces: Using the Mermaid classDiagram code syntax, we have defined the following classes and interfaces:

  • Main: The main class of the program, which contains a search engine, index, ranking, summary, and knowledge base.
  • SearchEngine: A class that contains an index, ranking, and summary.
  • Index: A class that contains a knowledge base and methods for creating and querying the index.
  • Ranking: A class that contains methods for ranking results.
  • Summary: A class that contains methods for summarizing results.
  • KnowledgeBase: A class that contains methods for updating and fetching data.

We have also defined the relationships between these classes using the -> operator.

Program call flow: Using the SequenceDiagram code syntax, we have defined the following program call flow:

  • The main class (Main) searches an engine (SE) for a query.
  • The search engine (SE) queries the index (I) for data.
  • The index (I) fetches data from a knowledge base (KB).
  • The knowledge base (KB) updates data.
  • The search engine (SE) ranks results.
  • The ranked results are returned to the main class (Main).
  • The main class (Main) summarizes the results and returns them to the search engine (SE).
  • The search engine (SE) returns the summary to the user.

Anything UNCLEAR: There is some uncertainty regarding third-party API integration, which needs clarification. 2024-03-06 10:11:09.732 | INFO | metagpt.utils.cost_manager:update_cost:103 - prompt_tokens: 0, completion_tokens: 440 2024-03-06 10:11:09.733 | WARNING | metagpt.utils.repair_llm_raw_output:extract_content_from_output:308 - extract_content try another pattern: [CONTENT]([\s\S])[/CONTENT] 2024-03-06 10:11:09.733 | WARNING | metagpt.utils.repair_llm_raw_output:run_and_passon:256 - parse json from content inside [CONTENT][/CONTENT] failed at retry 1, exp: Expecting value: line 1 column 1 (char 0) 2024-03-06 10:11:09.734 | INFO | metagpt.utils.repair_llm_raw_output:repair_invalid_json:225 - repair_invalid_json, raw error: Expecting value: line 1 column 1 (char 0) 2024-03-06 10:11:09.735 | ERROR | metagpt.utils.common:log_it:476 - Finished call to 'metagpt.actions.action_node.ActionNode._aask_v1' after 10.625(s), this was the 4th time calling it. exp: RetryError[<Future at 0x1b34dc03910 state=finished raised JSONDecodeError>] Understood! I will follow your instructions and generate the output in the format example you provided. Please provide me with the content for each node, and I will get started. 2024-03-06 10:11:12.534 | INFO | metagpt.utils.cost_manager:update_cost:103 - prompt_tokens: 0, completion_tokens: 36 2024-03-06 10:11:12.535 | WARNING | metagpt.utils.repair_llm_raw_output:extract_content_from_output:308 - extract_content try another pattern: [CONTENT]([\s\S])[/CONTENT] 2024-03-06 10:11:12.535 | WARNING | metagpt.utils.repair_llm_raw_output:run_and_passon:256 - parse json from content inside [CONTENT][/CONTENT] failed at retry 1, exp: Expecting value: line 1 column 1 (char 0) 2024-03-06 10:11:12.536 | INFO | metagpt.utils.repair_llm_raw_output:repair_invalid_json:225 - repair_invalid_json, raw error: Expecting value: line 1 column 1 (char 0) 2024-03-06 10:11:12.536 | ERROR | metagpt.utils.common:log_it:476 - Finished call to 'metagpt.actions.action_node.ActionNode._aask_v1' after 13.437(s), this was the 5th time calling it. exp: RetryError[<Future at 0x1b34dc25090 state=finished raised JSONDecodeError>] Understood! I will follow your instructions and generate the output in the format example you provided. Please provide me with the next node to work on. 2024-03-06 10:11:18.815 | INFO | metagpt.utils.cost_manager:update_cost:103 - prompt_tokens: 0, completion_tokens: 31 2024-03-06 10:11:18.816 | WARNING | metagpt.utils.repair_llm_raw_output:extract_content_from_output:308 - extract_content try another pattern: [CONTENT]([\s\S]*)[/CONTENT] 2024-03-06 10:11:18.817 | WARNING | metagpt.utils.repair_llm_raw_output:run_and_passon:256 - parse json from content inside [CONTENT][/CONTENT] failed at retry 1, exp: Expecting value: line 1 column 1 (char 0) 2024-03-06 10:11:18.817 | INFO | metagpt.utils.repair_llm_raw_output:repair_invalid_json:225 - repair_invalid_json, raw error: Expecting value: line 1 column 1 (char 0) 2024-03-06 10:11:18.818 | ERROR | metagpt.utils.common:log_it:476 - Finished call to 'metagpt.actions.action_node.ActionNode.aask_v1' after 19.718(s), this was the 6th time calling it. exp: RetryError[<Future at 0x1b34dc31890 state=finished raised JSONDecodeError>] 2024-03-06 10:11:18.818 | WARNING | metagpt.utils.common:wrapper:571 - There is a exception in role's execution, in order to resume, we delete the newest role communication message in the role's memory. 2024-03-06 10:11:18.821 | ERROR | metagpt.utils.common:wrapper:553 - Exception occurs, start to serialize the project, exp: Traceback (most recent call last): File "C:\Users\Administrator\AppData\Local\Programs\Python\Python311\Lib\site-packages\tenacity_init.py", line 382, in call result = fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\utils\repair_llm_raw_output.py", line 284, in retry_parse_json_text parsed_data = CustomDecoder(strict=False).decode(output) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "C:\Users\Administrator\AppData\Local\Programs\Python\Python311\Lib\site-packages\tenacity_asyncio.py", line 50, in call result = await fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\actions\action_node.py", line 427, in _aask_v1 parsed_data = llm_output_postprocess( ^^^^^^^^^^^^^^^^^^^^^^^ tenacity.RetryError: RetryError[<Future at 0x1b34dc31890 state=finished raised JSONDecodeError>]

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\utils\common.py", line 562, in wrapper return await func(self, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\roles\role.py", line 558, in run rsp = await self.react() ^^^^^^^^^^^^^^^^^^ tenacity.RetryError: RetryError[<Future at 0x1b34dc62250 state=finished raised RetryError>]

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\utils\common.py", line 548, in wrapper result = await func(self, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\team.py", line 134, in run await self.env.run() Exception: Traceback (most recent call last): File "C:\Users\Administrator\AppData\Local\Programs\Python\Python311\Lib\site-packages\tenacity_init_.py", line 382, in call result = fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\utils\repair_llm_raw_output.py", line 284, in retry_parse_json_text parsed_data = CustomDecoder(strict=False).decode(output) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\utils\custom_decoder.py", line 297, in decode return super().decode(s) ^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Local\Programs\Python\Python311\Lib\json\decoder.py", line 337, in decode obj, end = self.raw_decode(s, idx=_w(s, 0).end()) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Local\Programs\Python\Python311\Lib\json\decoder.py", line 355, in raw_decode raise JSONDecodeError("Expecting value", s, err.value) from None json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "C:\Users\Administrator\AppData\Local\Programs\Python\Python311\Lib\site-packages\tenacity_asyncio.py", line 50, in call result = await fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\actions\action_node.py", line 427, in aask_v1 parsed_data = llm_output_postprocess( ^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\provider\postprocess\llm_output_postprocess.py", line 19, in llm_output_postprocess result = postprocess_plugin.run(output=output, schema=schema, req_key=req_key) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\provider\postprocess\base_postprocess_plugin.py", line 68, in run new_output = self.run_repair_llm_output(output=output, schema=schema, req_key=req_key) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\provider\postprocess\base_postprocess_plugin.py", line 32, in run_repair_llm_output parsed_data = self.run_retry_parse_json_text(content) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\provider\postprocess\base_postprocess_plugin.py", line 47, in run_retry_parse_json_text parsed_data = retry_parse_json_text(output=content) # should use output=content ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Local\Programs\Python\Python311\Lib\site-packages\tenacity_init.py", line 289, in wrapped_f return self(f, *args, **kw) ^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Local\Programs\Python\Python311\Lib\site-packages\tenacity_init_.py", line 379, in call do = self.iter(retry_state=retry_state) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Local\Programs\Python\Python311\Lib\site-packages\tenacity_init_.py", line 326, in iter raise retry_exc from fut.exception() tenacity.RetryError: RetryError[<Future at 0x1b34dc31890 state=finished raised JSONDecodeError>]

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\utils\common.py", line 562, in wrapper return await func(self, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\roles\role.py", line 558, in run rsp = await self.react() ^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\roles\role.py", line 525, in react rsp = await self._react() ^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\roles\role.py", line 471, in _react rsp = await self._act() ^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\roles\role.py", line 400, in _act response = await self.rc.todo.run(self.rc.history) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\actions\design_api.py", line 58, in run doc = await self._update_system_design(filename=filename) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\actions\design_api.py", line 86, in _update_system_design system_design = await self._new_system_design(context=prd.content) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\actions\design_api.py", line 73, in _new_system_design node = await DESIGN_API_NODE.fill(context=context, llm=self.llm) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\actions\action_node.py", line 505, in fill return await self.simple_fill(schema=schema, mode=mode, images=images, timeout=timeout, exclude=exclude) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python311\site-packages\metagpt\actions\action_node.py", line 457, in simple_fill content, scontent = await self.aask_v1( ^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Local\Programs\Python\Python311\Lib\site-packages\tenacity_asyncio.py", line 88, in async_wrapped return await fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Local\Programs\Python\Python311\Lib\site-packages\tenacity_asyncio.py", line 47, in call do = self.iter(retry_state=retry_state) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Local\Programs\Python\Python311\Lib\site-packages\tenacity_init.py", line 326, in iter raise retry_exc from fut.exception() tenacity.RetryError: RetryError[<Future at 0x1b34dc62250 state=finished raised RetryError>]

ThomasXIONG151215 avatar Mar 06 '24 02:03 ThomasXIONG151215

These are the responses from the large model：

Understood! I will follow the instructions in the nodes and generate the output in the format example. Please provide me with the content for each node, and I will get started.

It seems the large model's intelligence is not online and it doesn't know what it's supposed to do. I suggest switching to a different model or version.

iorisa avatar Mar 06 '24 12:03 iorisa

This issue is similar to #987, caused by LLM not returning in the required format. Metagpt expects an llm response as parse json from content inside [CONTENT][/CONTENT]

You can locate the response returned by LLM by searching for the log line metagpt.utils.cost_manager:update_cost, the response appears above the log.

iorisa avatar Mar 14 '24 08:03 iorisa