Update settings.yaml

settings.yaml

@@ -1,9 +1,11 @@
+encoding_model: cl100k_base
+skip_workflows: []
 llm:
   api_key: "3bf18984-b4df-49ba-a30b-6cbae3964b08"
   type: openai_chat
   model_supports_json: true
-  model: "claude-3-5-sonnet-20240620"
-  api_base: "http://localhost:8000/v1"
+  model: claude-3-5-sonnet-20240620
+  api_base: http://localhost:8000/v1
   # max_tokens: 10000 # Adjusted based on Claude 3 Haiku's typical context window
   request_timeout: 30
   tokens_per_minute: 100000
@@ -11,9 +13,112 @@ llm:
   max_retry_wait: 5
   temperature: 0.1
   
-  embeddings:
+embeddings:
   async_mode: threaded
   llm:
+    api_key: "EMBEDDING_API_KEY"
     type: openai_embedding
-    model: "mixedbread-ai/mxbai-embed-large-v1"
-    api_base: "http://localhost:7997"
+    model: mixedbread-ai/mxbai-embed-large-v1
+    api_base: http://localhost:7997
+
+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: "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: "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: "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