microsoft / graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system
https://microsoft.github.io/graphrag/
MIT License
20.06k stars 1.96k forks source link

[Issue]: ERROR Error executing verb "derive" in create_final_entities: derive() missing 3 required positional arguments: 'column1', 'column2', and 'operator' #643

Closed Ikaros-521 closed 4 months ago

Ikaros-521 commented 4 months ago

Describe the issue

create_final_entities error

Steps to reproduce

python -m graphrag.index --root ./ragtest --verbose --reporter rich --emit parquet

GraphRAG Config Used

async_mode: threaded
cache:
  base_dir: cache
  type: file
chunks:
  group_by_columns:
  - id
  overlap: 64
  size: 512
claim_extraction:
  enabled: true
  description: Any claims or facts that could be relevant to information discovery.
  max_gleanings: 0
  prompt: prompts/claim_extraction.txt
cluster_graph:
  max_cluster_size: 10
community_report:
  max_input_length: 8000
  max_length: 2000
  prompt: prompts/community_report.txt
embed_graph:
  enabled: false
embeddings:
  async_mode: threaded
  llm:
    api_base: http://127.0.0.1:11434/api
    api_key: ${GRAPHRAG_API_KEY}
    model: nomic-embed-text:latest
    provider: ollama
    type: openai_embedding
encoding_model: cl100k_base
entity_extraction:
  entity_types:
  - organization
  - person
  - geo
  - event
  max_gleanings: 0
  prompt: prompts/entity_extraction.txt
global_search:
  concurrency: 32
input:
  base_dir: input
  file_encoding: utf-8
  file_pattern: .*\.txt$
  file_type: text
  type: file
llm:
  api_base: http://127.0.0.1:11434/v1
  api_key: ${GRAPHRAG_API_KEY}
  max_tokens: 1024
  model: mistral:latest
  model_supports_json: true
  provider: ollama
  temperature: 0.5
  type: openai_chat
local_search: null
parallelization:
  num_threads: 50
  stagger: 0.3
reporting:
  base_dir: output/${timestamp}/reports
  type: file
skip_workflows: []
snapshots:
  graphml: true
  raw_entities: true
  top_level_nodes: true
storage:
  base_dir: output/${timestamp}/artifacts
  type: file
summarize_descriptions:
  max_length: 500
  prompt: prompts/summarize_descriptions.txt
umap:
  enabled: false

Logs and screenshots

00:45:31,525 graphrag.index.run INFO Workflow create_base_entity_graph completed with 1 rows in 0.01 seconds
00:45:31,525 graphrag.index.emit.parquet_table_emitter INFO emitting parquet table create_base_entity_graph.parquet
00:45:31,646 graphrag.index.run INFO Running workflow: create_final_entities...
00:45:31,646 graphrag.index.run INFO dependencies for create_final_entities: ['create_base_entity_graph']
00:45:31,647 graphrag.index.run INFO read table from storage: create_base_entity_graph.parquet
00:45:31,651 datashaper.workflow.workflow INFO executing verb derive
00:45:31,651 datashaper.workflow.workflow ERROR Error executing verb "derive" in create_final_entities: derive() missing 3 required positional arguments: 'column1', 'column2', and 'operator'
Traceback (most recent call last):
  File "f:\GraphRAG-Ollama-UI\Miniconda3\lib\site-packages\datashaper\workflow\workflow.py", line 410, in _execute_verb
    result = node.verb.func(**verb_args)
TypeError: derive() missing 3 required positional arguments: 'column1', 'column2', and 'operator'
00:45:31,652 graphrag.index.reporting.file_workflow_callbacks INFO Error executing verb "derive" in create_final_entities: derive() missing 3 required positional arguments: 'column1', 'column2', and 'operator' details=None
00:45:31,652 graphrag.index.run ERROR error running workflow create_final_entities
Traceback (most recent call last):
  File "F:\GraphRAG-Ollama-UI\graphrag\index\run.py", line 357, in run_pipeline
    result = await workflow.run(context, callbacks)
  File "f:\GraphRAG-Ollama-UI\Miniconda3\lib\site-packages\datashaper\workflow\workflow.py", line 369, in run
    timing = await self._execute_verb(node, context, callbacks)
  File "f:\GraphRAG-Ollama-UI\Miniconda3\lib\site-packages\datashaper\workflow\workflow.py", line 410, in _execute_verb
    result = node.verb.func(**verb_args)
TypeError: derive() missing 3 required positional arguments: 'column1', 'column2', and 'operator'
00:45:31,652 graphrag.index.reporting.file_workflow_callbacks INFO Error running pipeline! details=None

Additional Information

natoverse commented 4 months ago

It's difficult for us to tell if this is a bug in the GraphRAG code or an issue with unexpected response format from the model. Routing to consolidated alternate model providers issue #657.