conda create -n graphrag python=3.11conda activate graphrag

pip install graphrag

mkdir graphrag

cd graphragmkdir ./sudongpo/input

python -m graphrag.index --init --root ./sudongpo

#settings.yamlencoding_model: cl100k_baseskip_workflows: []llm:api_key: $这里把deepseek的api key拷贝进来，把前后两个'$'都替换掉$type: openai_chat # or azure_openai_chatmodel: deepseek-chatmodel_supports_json: false # recommended if this is available for your model.max_tokens: 4000request_timeout: 180.0api_base: https://api.deepseek.com/v1# api_version: 2024-02-15-preview# organization: <organization_id># deployment_name: <azure_model_deployment_name>tokens_per_minute: 30000 # set a leaky bucket throttlerequests_per_minute: 30 # set a leaky bucket throttlemax_retries: 20max_retry_wait: 10.0sleep_on_rate_limit_recommendation: true # whether to sleep when azure suggests wait-timesconcurrent_requests: 10 # 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 embeddingsasync_mode: threaded # or asynciollm:api_key: $这里把智谱的api key拷贝进来，把前后两个'$'都替换掉$type: openai_embedding # or azure_openai_embeddingmodel: embedding-2api_base: https://open.bigmodel.cn/api/paas/v4# api_version: 2024-02-15-preview# organization: <organization_id># deployment_name: <azure_model_deployment_name># tokens_per_minute: 150_000 # set a leaky bucket throttle# requests_per_minute: 10_000 # set a leaky bucket throttle# max_retries: 10# max_retry_wait: 10.0sleep_on_rate_limit_recommendation: true # whether to sleep when azure suggests wait-timesconcurrent_requests: 10 # the number of parallel inflight requests that may be madebatch_size: 16 # the number of documents to send in a single requestbatch_max_tokens: 8191 # the maximum number of tokens to send in a single request# target: required # or optionalchunks:size: 1200overlap: 100group_by_columns: [id] # by default, we don't allow chunks to cross documents
input:type: file # or blobfile_type: text # or csvbase_dir: "input"file_encoding: utf-8file_pattern: ".*\\.txt$"
cache:type: file # or blobbase_dir: "cache"# connection_string: <azure_blob_storage_connection_string># container_name: <azure_blob_storage_container_name>
storage:type: file # or blobbase_dir: "output/${timestamp}/artifacts"# connection_string: <azure_blob_storage_connection_string># container_name: <azure_blob_storage_container_name>
reporting:type: file # or console, blobbase_dir: "output/${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 taskprompt: "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 taskprompt: "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: trueprompt: "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 taskprompt: "prompts/community_report.txt"max_length: 2000max_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: falseraw_entities: falsetop_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

python -m graphrag.index --root ./sudongpo

python -m graphrag.query --root ./sudongpo --method global "苏东坡为什么一直被贬，还能乐观豁达？"