Why output_tokens=0 when running create_final_entities?

[no-con]

Actually I can successfully run the workflow. But when running create_final_entities, the output_tokens kept being 0, which confused me. I don't know if this will have any effect on the final result. Can someone tell me what the main purpose of this step is? Is output_tokens usually 0? If 0 is not normal, what might be related to it?

The embedding model I used was GLM's embedding-3. I also tried the nomic-embed-text model provided by the local ollama service. They both resulted in output_tokens=0. The LLM I used is glm-4-0520 .

Here is the detailed log (the bold part is where I'm confused) :
20:57:59,749 graphrag.index.cli INFO Logging enabled at rag-glm\output\20240828-205759\reports\indexing-engine.log
20:57:59,753 graphrag.index.cli INFO Starting pipeline run for: 20240828-205759, dryrun=False
20:57:59,753 graphrag.index.cli INFO Using default configuration: {
"llm": {
"api_key": "==== REDACTED ====",
"type": "openai_chat",
"model": "glm-4-0520",
"max_tokens": 4000,
"temperature": 0.0,
"top_p": 1.0,
"n": 1,
"request_timeout": 180.0,
"api_base": "https://open.bigmodel.cn/api/paas/v4",
"api_version": null,
"proxy": null,
"cognitive_services_endpoint": null,
"deployment_name": null,
"model_supports_json": true,
"tokens_per_minute": 0,
"requests_per_minute": 0,
"max_retries": 10,
"max_retry_wait": 10.0,
"sleep_on_rate_limit_recommendation": true,
"concurrent_requests": 5
},
"parallelization": {
"stagger": 0.3,
"num_threads": 50
},
"async_mode": "threaded",
"root_dir": "rag-glm",
"reporting": {
"type": "file",
"base_dir": "output/${timestamp}/reports",
"storage_account_blob_url": null
},
"storage": {
"type": "file",
"base_dir": "output/${timestamp}/artifacts",
"storage_account_blob_url": null
},
"cache": {
"type": "file",
"base_dir": "cache",
"storage_account_blob_url": null
},
"input": {
"type": "file",
"file_type": "text",
"base_dir": "input",
"storage_account_blob_url": null,
"encoding": "utf-8",
"file_pattern": ".* \.txt$",
"file_filter": null,
"source_column": null,
"timestamp_column": null,
"timestamp_format": null,
"text_column": "text",
"title_column": null,
"document_attribute_columns": []
},
"embed_graph": {
"enabled": false,
"num_walks": 10,
"walk_length": 40,
"window_size": 2,
"iterations": 3,
"random_seed": 597832,
"strategy": null
},
"embeddings": {
"llm": {
"api_key": "==== REDACTED ====",
"type": "openai_embedding",
"model": "embedding-3",
"max_tokens": 4000,
"temperature": 0,
"top_p": 1,
"n": 1,
"request_timeout": 180.0,
"api_base": "https://open.bigmodel.cn/api/paas/v4",
"api_version": null,
"proxy": null,
"cognitive_services_endpoint": null,
"deployment_name": null,
"model_supports_json": null,
"tokens_per_minute": 0,
"requests_per_minute": 0,
"max_retries": 10,
"max_retry_wait": 10.0,
"sleep_on_rate_limit_recommendation": true,
"concurrent_requests": 1
},
"parallelization": {
"stagger": 0.3,
"num_threads": 50
},
"async_mode": "threaded",
"batch_size": 16,
"batch_max_tokens": 8191,
"target": "required",
"skip": [],
"vector_store": null,
"strategy": null
},
"chunks": {
"size": 1200,
"overlap": 300,
"group_by_columns": [
"id"
],
"strategy": null,
"encoding_model": null
},
"snapshots": {
"graphml": false,
"raw_entities": false,
"top_level_nodes": false
},
"entity_extraction": {
"llm": {
"api_key": "==== REDACTED ====",
"type": "openai_chat",
"model": "glm-4-0520",
"max_tokens": 4000,
"temperature": 0.0,
"top_p": 1.0,
"n": 1,
"request_timeout": 180.0,
"api_base": "https://open.bigmodel.cn/api/paas/v4",
"api_version": null,
"proxy": null,
"cognitive_services_endpoint": null,
"deployment_name": null,
"model_supports_json": true,
"tokens_per_minute": 0,
"requests_per_minute": 0,
"max_retries": 10,
"max_retry_wait": 10.0,
"sleep_on_rate_limit_recommendation": true,
"concurrent_requests": 5
},
"parallelization": {
"stagger": 0.3,
"num_threads": 50
},
"async_mode": "threaded",
"prompt": "prompts/entity_extraction.txt",
"entity_types": [
"organization",
"person",
"geo",
"event"
],
"max_gleanings": 0,
"strategy": null,
"encoding_model": null
},
"summarize_descriptions": {
"llm": {
"api_key": "==== REDACTED ====",
"type": "openai_chat",
"model": "glm-4-0520",
"max_tokens": 4000,
"temperature": 0.0,
"top_p": 1.0,
"n": 1,
"request_timeout": 180.0,
"api_base": "https://open.bigmodel.cn/api/paas/v4",
"api_version": null,
"proxy": null,
"cognitive_services_endpoint": null,
"deployment_name": null,
"model_supports_json": true,
"tokens_per_minute": 0,
"requests_per_minute": 0,
"max_retries": 10,
"max_retry_wait": 10.0,
"sleep_on_rate_limit_recommendation": true,
"concurrent_requests": 5
},
"parallelization": {
"stagger": 0.3,
"num_threads": 50
},
"async_mode": "threaded",
"prompt": "prompts/summarize_descriptions.txt",
"max_length": 500,
"strategy": null
},
"community_reports": {
"llm": {
"api_key": "==== REDACTED ====",
"type": "openai_chat",
"model": "glm-4-0520",
"max_tokens": 4000,
"temperature": 0.0,
"top_p": 1.0,
"n": 1,
"request_timeout": 180.0,
"api_base": "https://open.bigmodel.cn/api/paas/v4",
"api_version": null,
"proxy": null,
"cognitive_services_endpoint": null,
"deployment_name": null,
"model_supports_json": true,
"tokens_per_minute": 0,
"requests_per_minute": 0,
"max_retries": 10,
"max_retry_wait": 10.0,
"sleep_on_rate_limit_recommendation": true,
"concurrent_requests": 5
},
"parallelization": {
"stagger": 0.3,
"num_threads": 50
},
"async_mode": "threaded",
"prompt": "prompts/community_report.txt",
"max_length": 2000,
"max_input_length": 8000,
"strategy": null
},
"claim_extraction": {
"llm": {
"api_key": "==== REDACTED ====",
"type": "openai_chat",
"model": "glm-4-0520",
"max_tokens": 4000,
"temperature": 0.0,
"top_p": 1.0,
"n": 1,
"request_timeout": 180.0,
"api_base": "https://open.bigmodel.cn/api/paas/v4",
"api_version": null,
"proxy": null,
"cognitive_services_endpoint": null,
"deployment_name": null,
"model_supports_json": true,
"tokens_per_minute": 0,
"requests_per_minute": 0,
"max_retries": 10,
"max_retry_wait": 10.0,
"sleep_on_rate_limit_recommendation": true,
"concurrent_requests": 5
},
"parallelization": {
"stagger": 0.3,
"num_threads": 50
},
"async_mode": "threaded",
"enabled": false,
"prompt": "prompts/claim_extraction.txt",
"description": "Any claims or facts that could be relevant to information discovery.",
"max_gleanings": 0,
"strategy": null,
"encoding_model": null
},
"cluster_graph": {
"max_cluster_size": 10,
"strategy": null
},
"umap": {
"enabled": false
},
"local_search": {
"text_unit_prop": 0.5,
"community_prop": 0.1,
"conversation_history_max_turns": 5,
"top_k_entities": 10,
"top_k_relationships": 10,
"temperature": 0.0,
"top_p": 1.0,
"n": 1,
"max_tokens": 12000,
"llm_max_tokens": 2000
},
"global_search": {
"temperature": 0.0,
"top_p": 1.0,
"n": 1,
"max_tokens": 12000,
"data_max_tokens": 12000,
"map_max_tokens": 1000,
"reduce_max_tokens": 2000,
"concurrency": 32
},
"encoding_model": "cl100k_base",
"skip_workflows": []
}
20:57:59,765 graphrag.index.create_pipeline_config INFO skipping workflows
20:57:59,765 graphrag.index.run INFO Running pipeline
20:57:59,765 graphrag.index.storage.file_pipeline_storage INFO Creating file storage at rag-glm\output\20240828-205759\artifacts
20:57:59,767 graphrag.index.input.load_input INFO loading input from root_dir=input
20:57:59,767 graphrag.index.input.load_input INFO using file storage for input
20:57:59,768 graphrag.index.storage.file_pipeline_storage INFO search rag-glm\input for files matching .*.txt $
20:57:59,769 graphrag.index.input.text INFO found text files from input, found [(' ****.txt', {})]
20:57:59,771 graphrag.index.input.text INFO Found 1 files, loading 1
20:57:59,773 graphrag.index.workflows.load INFO Workflow Run Order: ['create_base_text_units', 'create_base_extracted_entities', 'create_summarized_entities', 'create_base_entity_graph', 'create_final_entities', 'create_final_nodes', 'create_final_communities', 'join_text_units_to_entity_ids', 'create_final_relationships', 'join_text_units_to_relationship_ids', 'create_final_community_reports', 'create_final_text_units', 'create_base_documents', 'create_final_documents']
20:57:59,773 graphrag.index.run INFO Final # of rows loaded: 1
20:57:59,922 graphrag.index.run INFO Running workflow: create_base_text_units...
20:57:59,922 graphrag.index.run INFO dependencies for create_base_text_units: []
20:57:59,927 datashaper.workflow.workflow INFO executing verb orderby
20:57:59,930 datashaper.workflow.workflow INFO executing verb zip
20:57:59,934 datashaper.workflow.workflow INFO executing verb aggregate_override
20:57:59,939 datashaper.workflow.workflow INFO executing verb chunk
20:58:00,129 datashaper.workflow.workflow INFO executing verb select
20:58:00,133 datashaper.workflow.workflow INFO executing verb unroll
20:58:00,138 datashaper.workflow.workflow INFO executing verb rename
20:58:00,143 datashaper.workflow.workflow INFO executing verb genid
20:58:00,148 datashaper.workflow.workflow INFO executing verb unzip
20:58:00,154 datashaper.workflow.workflow INFO executing verb copy
20:58:00,160 datashaper.workflow.workflow INFO executing verb filter
20:58:00,172 graphrag.index.emit.parquet_table_emitter INFO emitting parquet table create_base_text_units.parquet
20:58:00,372 graphrag.index.run INFO Running workflow: create_base_extracted_entities...
20:58:00,373 graphrag.index.run INFO dependencies for create_base_extracted_entities: ['create_base_text_units']
20:58:00,373 graphrag.index.run INFO read table from storage: create_base_text_units.parquet
20:58:00,401 datashaper.workflow.workflow INFO executing verb entity_extract
20:58:00,406 graphrag.llm.openai.create_openai_client INFO Creating OpenAI client base_url=https://open.bigmodel.cn/api/paas/v4
20:58:01,148 graphrag.index.llm.load_llm INFO create TPM/RPM limiter for glm-4-0520: TPM=0, RPM=0
20:58:01,148 graphrag.index.llm.load_llm INFO create concurrency limiter for glm-4-0520: 5
20:58:09,613 httpx INFO HTTP Request: POST https://open.bigmodel.cn/api/paas/v4/chat/completions "HTTP/1.1 200 OK"
20:58:09,616 graphrag.llm.base.rate_limiting_llm INFO perf - llm.chat "Process" with 0 retries took 8.452999999979511. input_tokens=2936, output_tokens=117
20:58:21,412 httpx INFO HTTP Request: POST https://open.bigmodel.cn/api/paas/v4/chat/completions "HTTP/1.1 200 OK"
20:58:21,414 graphrag.llm.base.rate_limiting_llm INFO perf - llm.chat "Process" with 0 retries took 20.25. input_tokens=2936, output_tokens=564
20:58:27,334 httpx INFO HTTP Request: POST https://open.bigmodel.cn/api/paas/v4/chat/completions "HTTP/1.1 200 OK"
20:58:27,336 graphrag.llm.base.rate_limiting_llm INFO perf - llm.chat "Process" with 0 retries took 26.17099999997299. input_tokens=2408, output_tokens=757
20:58:27,362 datashaper.workflow.workflow INFO executing verb merge_graphs
20:58:27,367 graphrag.index.emit.parquet_table_emitter INFO emitting parquet table create_base_extracted_entities.parquet
20:58:27,523 graphrag.index.run INFO Running workflow: create_summarized_entities...
20:58:27,523 graphrag.index.run INFO dependencies for create_summarized_entities: ['create_base_extracted_entities']
20:58:27,524 graphrag.index.run INFO read table from storage: create_base_extracted_entities.parquet
20:58:27,544 datashaper.workflow.workflow INFO executing verb summarize_descriptions
20:58:27,557 graphrag.index.emit.parquet_table_emitter INFO emitting parquet table create_summarized_entities.parquet
20:58:27,719 graphrag.index.run INFO Running workflow: create_base_entity_graph...
20:58:27,719 graphrag.index.run INFO dependencies for create_base_entity_graph: ['create_summarized_entities']
20:58:27,720 graphrag.index.run INFO read table from storage: create_summarized_entities.parquet
20:58:27,736 datashaper.workflow.workflow INFO executing verb cluster_graph
20:58:27,755 datashaper.workflow.workflow INFO executing verb select
20:58:27,757 graphrag.index.emit.parquet_table_emitter INFO emitting parquet table create_base_entity_graph.parquet
20:58:27,928 graphrag.index.run INFO Running workflow: create_final_entities...
20:58:27,929 graphrag.index.run INFO dependencies for create_final_entities: ['create_base_entity_graph']
20:58:27,929 graphrag.index.run INFO read table from storage: create_base_entity_graph.parquet
20:58:27,953 datashaper.workflow.workflow INFO executing verb unpack_graph
20:58:27,963 datashaper.workflow.workflow INFO executing verb rename
20:58:27,971 datashaper.workflow.workflow INFO executing verb select
20:58:27,980 datashaper.workflow.workflow INFO executing verb dedupe
20:58:27,989 datashaper.workflow.workflow INFO executing verb rename
20:58:27,998 datashaper.workflow.workflow INFO executing verb filter
20:58:28,21 datashaper.workflow.workflow INFO executing verb text_split
20:58:28,31 datashaper.workflow.workflow INFO executing verb drop
20:58:28,43 datashaper.workflow.workflow INFO executing verb merge
20:58:28,57 datashaper.workflow.workflow INFO executing verb text_embed
20:58:28,59 graphrag.llm.openai.create_openai_client INFO Creating OpenAI client base_url=https://open.bigmodel.cn/api/paas/v4
20:58:28,789 graphrag.index.llm.load_llm INFO create TPM/RPM limiter for embedding-3: TPM=0, RPM=0
20:58:28,789 graphrag.index.llm.load_llm INFO create concurrency limiter for embedding-3: 1
20:58:28,790 graphrag.index.verbs.text.embed.strategies.openai INFO embedding 17 inputs via 17 snippets using 2 batches. max_batch_size=16, max_tokens=8191
20:58:29,537 httpx INFO HTTP Request: POST https://open.bigmodel.cn/api/paas/v4/embeddings "HTTP/1.1 200 OK"
20:58:29,912 graphrag.llm.base.rate_limiting_llm INFO perf - llm.embedding "Process" with 0 retries took 1.125. input_tokens=411, output_tokens=0
20:58:30,52 httpx INFO HTTP Request: POST https://open.bigmodel.cn/api/paas/v4/embeddings "HTTP/1.1 200 OK"
20:58:30,66 graphrag.llm.base.rate_limiting_llm INFO perf - llm.embedding "Process" with 0 retries took 0.14100000000325963. input_tokens=6, output_tokens=0
20:58:30,88 datashaper.workflow.workflow INFO executing verb drop
20:58:30,98 datashaper.workflow.workflow INFO executing verb filter
20:58:30,114 graphrag.index.emit.parquet_table_emitter INFO emitting parquet table create_final_entities.parquet
20:58:30,328 graphrag.index.run INFO Running workflow: create_final_nodes...
20:58:30,332 graphrag.index.run INFO dependencies for create_final_nodes: ['create_base_entity_graph']
20:58:30,332 graphrag.index.run INFO read table from storage: create_base_entity_graph.parquet
20:58:30,356 datashaper.workflow.workflow INFO executing verb layout_graph
20:58:30,374 datashaper.workflow.workflow INFO executing verb unpack_graph
20:58:30,387 datashaper.workflow.workflow INFO executing verb unpack_graph
20:58:30,400 datashaper.workflow.workflow INFO executing verb drop
20:58:30,413 datashaper.workflow.workflow INFO executing verb filter
20:58:30,440 datashaper.workflow.workflow INFO executing verb select
20:58:30,453 datashaper.workflow.workflow INFO executing verb rename
20:58:30,465 datashaper.workflow.workflow INFO executing verb join
20:58:30,484 datashaper.workflow.workflow INFO executing verb convert
20:58:30,531 datashaper.workflow.workflow INFO executing verb rename
20:58:30,534 graphrag.index.emit.parquet_table_emitter INFO emitting parquet table create_final_nodes.parquet
20:58:30,723 graphrag.index.run INFO Running workflow: create_final_communities...
20:58:30,724 graphrag.index.run INFO dependencies for create_final_communities: ['create_base_entity_graph']
20:58:30,724 graphrag.index.run INFO read table from storage: create_base_entity_graph.parquet
20:58:30,754 datashaper.workflow.workflow INFO executing verb unpack_graph
20:58:30,771 datashaper.workflow.workflow INFO executing verb unpack_graph
20:58:30,787 datashaper.workflow.workflow INFO executing verb aggregate_override
20:58:30,804 datashaper.workflow.workflow INFO executing verb join
20:58:30,824 datashaper.workflow.workflow INFO executing verb join
20:58:30,845 datashaper.workflow.workflow INFO executing verb concat
20:58:30,860 datashaper.workflow.workflow INFO executing verb filter
20:58:30,897 datashaper.workflow.workflow INFO executing verb aggregate_override
20:58:30,914 datashaper.workflow.workflow INFO executing verb join
20:58:30,935 datashaper.workflow.workflow INFO executing verb filter
20:58:30,971 datashaper.workflow.workflow INFO executing verb fill
20:58:30,988 datashaper.workflow.workflow INFO executing verb merge
20:58:31,7 datashaper.workflow.workflow INFO executing verb copy
20:58:31,25 datashaper.workflow.workflow INFO executing verb select
20:58:31,27 graphrag.index.emit.parquet_table_emitter INFO emitting parquet table create_final_communities.parquet
20:58:31,213 graphrag.index.run INFO Running workflow: join_text_units_to_entity_ids...
20:58:31,214 graphrag.index.run INFO dependencies for join_text_units_to_entity_ids: ['create_final_entities']
20:58:31,214 graphrag.index.run INFO read table from storage: create_final_entities.parquet
20:58:31,261 datashaper.workflow.workflow INFO executing verb select
20:58:31,280 datashaper.workflow.workflow INFO executing verb unroll
20:58:31,299 datashaper.workflow.workflow INFO executing verb aggregate_override
20:58:31,303 graphrag.index.emit.parquet_table_emitter INFO emitting parquet table join_text_units_to_entity_ids.parquet
20:58:31,506 graphrag.index.run INFO Running workflow: create_final_relationships...
20:58:31,507 graphrag.index.run INFO dependencies for create_final_relationships: ['create_final_nodes', 'create_base_entity_graph']
20:58:31,508 graphrag.index.run INFO read table from storage: create_final_nodes.parquet
20:58:31,519 graphrag.index.run INFO read table from storage: create_base_entity_graph.parquet
20:58:31,557 datashaper.workflow.workflow INFO executing verb unpack_graph
20:58:31,577 datashaper.workflow.workflow INFO executing verb filter
20:58:31,618 datashaper.workflow.workflow INFO executing verb rename
20:58:31,637 datashaper.workflow.workflow INFO executing verb filter
20:58:31,679 datashaper.workflow.workflow INFO executing verb drop
20:58:31,700 datashaper.workflow.workflow INFO executing verb compute_edge_combined_degree
20:58:31,724 datashaper.workflow.workflow INFO executing verb convert
20:58:31,764 datashaper.workflow.workflow INFO executing verb convert
20:58:31,766 graphrag.index.emit.parquet_table_emitter INFO emitting parquet table create_final_relationships.parquet
20:58:31,970 graphrag.index.run INFO Running workflow: join_text_units_to_relationship_ids...
20:58:31,971 graphrag.index.run INFO dependencies for join_text_units_to_relationship_ids: ['create_final_relationships']
20:58:31,971 graphrag.index.run INFO read table from storage: create_final_relationships.parquet
20:58:32,20 datashaper.workflow.workflow INFO executing verb select
20:58:32,41 datashaper.workflow.workflow INFO executing verb unroll
20:58:32,64 datashaper.workflow.workflow INFO executing verb aggregate_override
20:58:32,87 datashaper.workflow.workflow INFO executing verb select
20:58:32,89 graphrag.index.emit.parquet_table_emitter INFO emitting parquet table join_text_units_to_relationship_ids.parquet
20:58:32,288 graphrag.index.run INFO Running workflow: create_final_community_reports...
20:58:32,288 graphrag.index.run INFO dependencies for create_final_community_reports: ['create_final_nodes', 'create_final_relationships']
20:58:32,289 graphrag.index.run INFO read table from storage: create_final_nodes.parquet
20:58:32,295 graphrag.index.run INFO read table from storage: create_final_relationships.parquet
20:58:32,356 datashaper.workflow.workflow INFO executing verb prepare_community_reports_nodes
20:58:32,380 datashaper.workflow.workflow INFO executing verb prepare_community_reports_edges
20:58:32,405 datashaper.workflow.workflow INFO executing verb restore_community_hierarchy
20:58:32,430 datashaper.workflow.workflow INFO executing verb prepare_community_reports
20:58:32,431 graphrag.index.verbs.graph.report.prepare_community_reports INFO Number of nodes at level=0 => 17
20:58:32,470 datashaper.workflow.workflow INFO executing verb create_community_reports
20:58:59,146 httpx INFO HTTP Request: POST https://open.bigmodel.cn/api/paas/v4/chat/completions "HTTP/1.1 200 OK"
20:58:59,148 graphrag.llm.base.rate_limiting_llm INFO perf - llm.chat "create_community_report" with 0 retries took 26.67200000002049. input_tokens=2341, output_tokens=694
20:58:59,195 datashaper.workflow.workflow INFO executing verb window
20:58:59,197 graphrag.index.emit.parquet_table_emitter INFO emitting parquet table create_final_community_reports.parquet
20:58:59,424 graphrag.index.run INFO Running workflow: create_final_text_units...
20:58:59,435 graphrag.index.run INFO dependencies for create_final_text_units: ['join_text_units_to_relationship_ids', 'create_base_text_units', 'join_text_units_to_entity_ids']
20:58:59,436 graphrag.index.run INFO read table from storage: join_text_units_to_relationship_ids.parquet
20:58:59,445 graphrag.index.run INFO read table from storage: create_base_text_units.parquet
20:58:59,448 graphrag.index.run INFO read table from storage: join_text_units_to_entity_ids.parquet
20:58:59,499 datashaper.workflow.workflow INFO executing verb select
20:58:59,524 datashaper.workflow.workflow INFO executing verb rename
20:58:59,549 datashaper.workflow.workflow INFO executing verb join
20:58:59,580 datashaper.workflow.workflow INFO executing verb join
20:58:59,611 datashaper.workflow.workflow INFO executing verb aggregate_override
20:58:59,638 datashaper.workflow.workflow INFO executing verb select
20:58:59,640 graphrag.index.emit.parquet_table_emitter INFO emitting parquet table create_final_text_units.parquet
20:58:59,849 graphrag.index.run INFO Running workflow: create_base_documents...
20:58:59,849 graphrag.index.run INFO dependencies for create_base_documents: ['create_final_text_units']
20:58:59,850 graphrag.index.run INFO read table from storage: create_final_text_units.parquet
20:58:59,911 datashaper.workflow.workflow INFO executing verb unroll
20:58:59,942 datashaper.workflow.workflow INFO executing verb select
20:58:59,969 datashaper.workflow.workflow INFO executing verb rename
20:58:59,995 datashaper.workflow.workflow INFO executing verb join
20:59:00,27 datashaper.workflow.workflow INFO executing verb aggregate_override
20:59:00,56 datashaper.workflow.workflow INFO executing verb join
20:59:00,87 datashaper.workflow.workflow INFO executing verb rename
20:59:00,114 datashaper.workflow.workflow INFO executing verb convert
20:59:00,146 graphrag.index.emit.parquet_table_emitter INFO emitting parquet table create_base_documents.parquet
20:59:00,375 graphrag.index.run INFO Running workflow: create_final_documents...
20:59:00,376 graphrag.index.run INFO dependencies for create_final_documents: ['create_base_documents']
20:59:00,376 graphrag.index.run INFO read table from storage: create_base_documents.parquet
20:59:00,447 datashaper.workflow.workflow INFO executing verb rename
20:59:00,478 graphrag.index.emit.parquet_table_emitter INFO emitting parquet table create_final_documents.parquet
20:59:00,574 graphrag.index.cli INFO All workflows completed successfully.

[MisterAndry]

Hi, do you have any files in .../cache/entite_extraction folder?
If so, is there ant values for result field?

[no-con]

Sorry for delay reply.

Do you mean entity_extraction ? And I'm not sure what you mean by 'ant value', maybe 'any'? I can get some file with name chat_xxxxx in .../cache/entity_extraction folder, and the result field has some content. But I think these files are created in step create_base_extracted_entities.