Update settings.yaml

ragtest/settings.yaml

@@ -1,78 +1,145 @@
-async_mode: threaded
-cache:
-  base_dir: cache
-  type: file
-chunks:
-  group_by_columns:
-  - id
-  overlap: 64
-  size: 512
-claim_extraction:
-  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
+
+encoding_model: cl100k_base
+skip_workflows: []
+llm:
+  api_key: ${GRAPHRAG_API_KEY}
+  type: openai_chat # or azure_openai_chat
+  model: mistral-nemo:12b-instruct-2407-fp16
+  model_supports_json: true # recommended if this is available for your model.
+  max_tokens: 8192
+  # 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: 3
+  # 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:
-  async_mode: threaded
+  ## parallelization: override the global parallelization settings for embeddings
+  async_mode: threaded # or asyncio
   llm:
-    api_base: http://localhost:11434/api
     api_key: ${GRAPHRAG_API_KEY}
-    concurrent_requests: 25
+    type: openai_embedding # or azure_openai_embedding
     model: nomic-embed-text:latest
-    model_supports_json: true
-    provider: openai_embedding
-    type: openai_embedding
-encoding_model: cl100k_base
-entity_extraction:
-  entity_types:
-  - organization
-  - person
-  - geo
-  - event
-  max_gleanings: 0
-  prompt: prompts/entity_extraction.txt
-global_search:
-  concurrency: 32
+    api_base: http://localhost:11434/api
+    # api_version: 2024-02-15-preview
+    # organization: <organization_id>
+    # deployment_name: <azure_model_deployment_name>
+    # tokens_per_minute: 150_000 # set a leaky bucket throttle
+    # requests_per_minute: 10_000 # set a leaky bucket throttle
+    max_retries: 3
+    # max_retry_wait: 10.0
+    # sleep_on_rate_limit_recommendation: true # whether to sleep when azure suggests wait-times
+    concurrent_requests: 25 # the number of parallel inflight requests that may be made
+    #batch_size: 1 # the number of documents to send in a single request
+    #batch_max_tokens: 4000 # the maximum number of tokens to send in a single request
+    # target: required # or optional
+
+
+
+chunks:
+  size: 512
+  overlap: 64
+  group_by_columns: [id] # by default, we don't allow chunks to cross documents
+
 input:
-  base_dir: input
+  type: file # or blob
+  file_type: text # or csv
+  base_dir: "input"
   file_encoding: utf-8
-  file_pattern: .*\.txt$
-  file_type: text
-  type: file
-llm:
-  api_base: http://localhost:11434/v1
-  api_key: ${GRAPHRAG_API_KEY}
-  concurrent_requests: 25
-  max_tokens: 1024
-  model: qwen2:7b
-  model_supports_json: true
-  provider: openai_chat
-  temperature: 0.5
-  type: openai
-local_search: null
-parallelization:
-  num_threads: 50
-  stagger: 0.3
-reporting:
-  base_dir: output/${timestamp}/reports
-  type: file
-skip_workflows: []
-snapshots:
-  graphml: true
-  raw_entities: true
-  top_level_nodes: true
+  file_pattern: ".*\\.txt$"
+
+cache:
+  type: file # or blob
+  base_dir: "cache"
+  # connection_string: <azure_blob_storage_connection_string>
+  # container_name: <azure_blob_storage_container_name>
+
 storage:
-  base_dir: output/${timestamp}/artifacts
-  type: file
+  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
-  prompt: prompts/summarize_descriptions.txt
+
+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_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: "prompts/community_report.txt"
+  max_length: 2000
+  max_input_length: 4000
+
+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
+  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
+  # max_tokens: 12000
+
+global_search:
+  # max_tokens: 12000
+  # data_max_tokens: 12000
+  # map_max_tokens: 1000
+  # reduce_max_tokens: 2000
+  # concurrency: 32