[Issue] Crashing at Entity Extraction using Ollama: KeyError: "['type', 'description'] not in index"

[hellocaio]

Do you need to file an issue?

• [ ] I have searched the existing issues and this bug is not already filed.
• [ ] My model is hosted on OpenAI or Azure. If not, please look at the "model providers" issue and don't file a new one here.
• [ ] I believe this is a legitimate bug, not just a question. If this is a question, please use the Discussions area.

Describe the issue

GraphRAG is crashing during entity extraction using llama 3 (via Ollama) with the following error:

KeyError: "['type', 'description'] not in index"

I've tried multiple file formats with different file sizes (csv, txt, pdf), but the issue persists. I suspect it could be running out of memory or hitting some kind of threshold.

Steps to reproduce

Follow the Get Started instructions from Microsoft's GraphRAG documentation.

GraphRAG Config Used

encoding_model: cl100k_base
skip_workflows: []
llm:
  api_key: ${GRAPHRAG_API_KEY}
  type: openai_chat # or azure_openai_chat
  model: mistral
  model_supports_json: true # recommended if this is available for your model.
  # max_tokens: 4000
  # request_timeout: 180.0
  api_base: http://localhost:11434/v1
  # api_version: 2024-02-15-preview
  # organization: <organization_id>
  # deployment_name: <azure_model_deployment_name>
  # tokens_per_minute: 150_000 # set a leaky bucket throttle
  # requests_per_minute: 10_000 # set a leaky bucket throttle
  # max_retries: 10
  # max_retry_wait: 10.0
  # sleep_on_rate_limit_recommendation: true # whether to sleep when azure suggests wait-times
  # concurrent_requests: 25 # the number of parallel inflight requests that may be made

parallelization:
  stagger: 0.3
  # num_threads: 50 # the number of threads to use for parallel processing

async_mode: threaded # or asyncio

embeddings:
  ## parallelization: override the global parallelization settings for embeddings
  async_mode: threaded # or asyncio
  llm:
    api_key: ${GRAPHRAG_API_KEY}
    type: openai_embedding # or azure_openai_embedding
    model: nomic_embed_text #text-embedding-3-large  #mxbai-embed-large #
    api_base: http://localhost:11434/api
    # api_version: 2024-02-15-preview
    # organization: <organization_id>
    # deployment_name: <azure_model_deployment_name>
    tokens_per_minute: 150000 # set a leaky bucket throttle
    requests_per_minute: 10000 # set a leaky bucket throttle
    # max_retries: 10
    # max_retry_wait: 10.0
    # sleep_on_rate_limit_recommendation: true # whether to sleep when azure suggests wait-times
    concurrent_requests: 25 # the number of parallel inflight requests that may be made
    # batch_size: 16 # the number of documents to send in a single request
    # batch_max_tokens: 8191 # the maximum number of tokens to send in a single request
    # target: required # or optional

chunks:
  size: 300
  overlap: 100
  group_by_columns: [id] # by default, we don't allow chunks to cross documents

input:
  type: file # or blob
  file_type: text # or csv
  base_dir: "input"
  file_encoding: utf-8
  file_pattern: ".*\\.txt$"

cache:
  type: file # or blob
  base_dir: "cache"
  # connection_string: <azure_blob_storage_connection_string>
  # container_name: <azure_blob_storage_container_name>

storage:
  type: file # or blob
  base_dir: "output/${timestamp}/artifacts"
  # connection_string: <azure_blob_storage_connection_string>
  # container_name: <azure_blob_storage_container_name>

reporting:
  type: file # or console, blob
  base_dir: "output/${timestamp}/reports"
  # connection_string: <azure_blob_storage_connection_string>
  # container_name: <azure_blob_storage_container_name>

entity_extraction:
  ## llm: override the global llm settings for this task
  ## parallelization: override the global parallelization settings for this task
  ## async_mode: override the global async_mode settings for this task
  prompt: "prompts/entity_extraction.txt"
  entity_types: [organization, person, geo, event]
  max_gleanings: 0

summarize_descriptions:
  ## llm: override the global llm settings for this task
  ## parallelization: override the global parallelization settings for this task
  ## async_mode: override the global async_mode settings for this task
  prompt: "prompts/summarize_descriptions.txt"
  max_length: 500

claim_extraction:
  ## llm: override the global llm settings for this task
  ## parallelization: override the global parallelization settings for this task
  ## async_mode: override the global async_mode settings for this task
  # enabled: true
  prompt: "prompts/claim_extraction.txt"
  description: "Any claims or facts that could be relevant to information discovery."
  max_gleanings: 0

community_report:
  ## llm: override the global llm settings for this task
  ## parallelization: override the global parallelization settings for this task
  ## async_mode: override the global async_mode settings for this task
  prompt: "prompts/community_report.txt"
  max_length: 2000
  max_input_length: 8000

cluster_graph:
  max_cluster_size: 10

embed_graph:
  enabled: false # if true, will generate node2vec embeddings for nodes
  # num_walks: 10
  # walk_length: 40
  # window_size: 2
  # iterations: 3
  # random_seed: 597832

umap:
  enabled: false # if true, will generate UMAP embeddings for nodes

snapshots:
  graphml: True
  raw_entities: false
  top_level_nodes: True

local_search:
  # text_unit_prop: 0.5
  # community_prop: 0.1
  # conversation_history_max_turns: 5
  # top_k_mapped_entities: 10
  # top_k_relationships: 10
  # max_tokens: 12000

global_search:
  # max_tokens: 12000
  # data_max_tokens: 12000
  # map_max_tokens: 1000
  # reduce_max_tokens: 2000
  # concurrency: 32

Logs and screenshots

Additional Information

• GraphRAG Version: 0.3.6
• Operating System: MacOS Sequoia v15.0
• Python Version: 3.12.4
• Related Issues:

[hellocaio]

It's failing here in Pandas:

def check_key_length(columns: Index, key, value: DataFrame) -> None:
    """
    Checks if a key used as indexer has the same length as the columns it is
    associated with.

    Parameters
    ----------
    columns : Index The columns of the DataFrame to index.
    key : A list-like of keys to index with.
    value : DataFrame The value to set for the keys.

    Raises
    ------
    ValueError: If the length of key is not equal to the number of columns in value
                or if the number of columns referenced by key is not equal to number
                of columns.
    """
    if columns.is_unique:
        if len(value.columns) != len(key):
            raise ValueError("Columns must be same length as key")
    else:
        # Missing keys in columns are represented as -1
        if len(columns.get_indexer_non_unique(key)[0]) != len(value.columns):
            raise ValueError("Columns must be same length as key")

This is the source In GraphRAG: graphrag/index/verbs/graph/clustering/cluster_graph.py

LINE 106:

    # split the (level, graph) pairs into separate columns
    # TODO: There is probably a better way to do this
    output_df[[level_to, to]] = pd.DataFrame(
        output_df[to].tolist(), index=output_df.index
    )

[hellocaio]

After some debugging, I think this is the issue:

graphrag.index.verbs.graph.clustering.cluster_graph WARNING Graph has no nodes

Here is the full graph log (json)

Any idea why graph nodes are not being created?

[natoverse]

Routing to #657