forked from microsoft/graphrag
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathsettings.yaml
173 lines (153 loc) · 6.02 KB
/
settings.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
encoding_model: o200k_base
skip_workflows: []
llm:
api_key: ${GRAPHRAG_LLM_API_KEY}
type: openai_chat # or azure_openai_chat
model: ${GRAPHRAG_LLM_MODEL}
model_supports_json: true # recommended if this is available for your model.
# max_tokens: 4000
# request_timeout: 180.0
api_base: ${GRAPHRAG_LLM_API_BASE}
# 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
# [充值与限速 - Moonshot AI 开放平台](https://platform.moonshot.cn/docs/pricing/limits)
tokens_per_minute: 383_000 # set a leaky bucket throttle
requests_per_minute: 4_900 # set a leaky bucket throttle
# max_retries: 2
# 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
concurrent_requests: ${GRAPHRAG_LLM_CONCURRENT_REQUESTS}
# temperature: 0 # temperature for sampling
# top_p: 1 # top-p sampling
# n: 1 # Number of completions to generate
parallelization:
stagger: ${GRAPHRAG_LLM_THREAD_COUNT}
# num_threads: 50 # the number of threads to use for parallel processing
# [Limit - Moonshot AI 开放平台](https://platform.moonshot.cn/docs/price/limit#%E5%85%85%E5%80%BC%E4%B8%8E%E9%99%90%E9%80%9F)
num_threads: ${GRAPHRAG_LLM_THREAD_COUNT} # 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_EMBEDDING_API_KEY}
# type: openai_embedding # or azure_openai_embedding
model: ${GRAPHRAG_EMBEDDING_MODEL}
type: ${GRAPHRAG_EMBEDDING_TYPE}
# api_base: https://eroad.openai.azure.com
api_base: ${GRAPHRAG_EMBEDDING_API_BASE}
# model: bce-embedding-base_v1
# api_version: 2024-02-15-preview
api_version: 2024-05-01-preview
# organization: <organization_id>
# deployment_name: <azure_model_deployment_name>
deployment_name: ${GRAPHRAG_EMBEDDING_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
# 25 时 have exceeded call rate limit of your current OpenAI S0 pricing tier
# 8 时没出现 429
concurrent_requests: ${GRAPHRAG_EMBEDDING_CONCURRENT_REQUESTS}
# batch_size: 16 # the number of documents to send in a single request
# batch_max_tokens: 8191 # the maximum number of tokens to send in a single request
# target: required # or optional
chunks:
size: 500
overlap: 50
group_by_columns: [id] # by default, we don't allow chunks to cross documents
input:
type: file # or blob
file_type: text # or csv
base_dir: "input"
file_encoding: utf-8
file_pattern: ".*\\.txt$"
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:
## strategy:
## type:
## 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:
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:
# concurrent_requests: 4
# parallelization:
# stagger: ${GRAPHRAG_LLM_THREAD_COUNT}
# num_threads: 4
## 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: 4000
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: 3000
# reduce_max_tokens: 2000
concurrency: 8