search

microsoft / graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system
https://microsoft.github.io/graphrag/
MIT License
20.17k stars 1.97k forks source link

[Issue]: <title> Prompts tuning issue #924

Open wolfhawkld opened 3 months ago

wolfhawkld commented 3 months ago

Is there an existing issue for this?

Describe the issue

When I'm creating the graph data by GraphRAG, no matter where I provide a general response role description (entity_extraction and summarize_description), and then re-generate the whole graph data, the general prompt role does not working still, is there any location or any way to add a general response prompt role description to restrict the query result? Thanks in advanced.

Steps to reproduce

No response

GraphRAG Config Used


encoding_model: cl100k_base
skip_workflows: []
llm:
  api_key: ${GRAPHRAG_API_KEY}
  type: azure_openai_chat # or azure_openai_chat
  model: gpt-4o
  model_supports_json: true # recommended if this is available for your model.
  # max_tokens: 4000
  # request_timeout: 180.0
  api_base: https://api.nlp.dev.uptimize.merckgroup.com
  api_version: 2023-09-01-preview
  # organization: <organization_id>
  deployment_name: gpt-4o
  # 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
  # temperature: 0 # temperature for sampling
  # top_p: 1 # top-p sampling
  # n: 1 # Number of completions to generate

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: azure_openai_embedding # or azure_openai_embedding
    model: text-embedding-3-large
    api_base: https://api.nlp.dev.uptimize.merckgroup.com
    api_version: 2023-09-01-preview
    # organization: <organization_id>
    deployment_name: text-embedding-3-large
    # 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
    # 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: 1200
  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: "custom_prompts/entity_extraction.txt"
  entity_types: [organization,person,geo,event]
  max_gleanings: 1

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: "custom_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: 1

community_reports:
  ## 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: "custom_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: false
  raw_entities: false
  top_level_nodes: false

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
  # llm_temperature: 0 # temperature for sampling
  # llm_top_p: 1 # top-p sampling
  # llm_n: 1 # Number of completions to generate
  # max_tokens: 12000

global_search:
  # llm_temperature: 0 # temperature for sampling
  # llm_top_p: 1 # top-p sampling
  # llm_n: 1 # Number of completions to generate
  # max_tokens: 12000
  # data_max_tokens: 12000
  # map_max_tokens: 1000
  # reduce_max_tokens: 2000
  # concurrency: 32

Logs and screenshots

No response

Additional Information

AlonsoGuevara commented 3 months ago

Hi!

As I undertand, the issue is related to GraphRAG not picking your custom prompts, right?

Could you please share the prompt_tune command you're using?

Thanks!

wolfhawkld commented 3 months ago

Hi Alonso,

Thank you for replying me back, this is my cmd: python -m graphrag.prompt_tune --root .\playground\langchain\knowledge_base\graph_base --domain 'a List of Prohibited Ingredients for Cosmetics' --method random --limit 2 --chunk-size 1200 --output custom_prompts

And I've found after tuning a new custom prompts, I need to re-generate the graph data again to make the prompts working right, am I right?