mirror of
https://github.com/microsoft/graphrag.git
synced 2025-07-24 01:11:58 +00:00
f5b4d2fea5
* Remove excess vars from gh-pages build * Delete redundant javascript ci * Pull apart testing CI * Clean up integration tests build * Move storage tests to integration CI * Take py 3.10 out of smoke tests matrix * Use minimum supported python version for most tests * Re-run main CI on any test change * Add Josh and Kenny to author list * Update auto-resolve perms
65 lines
1.1 KiB
YAML
65 lines
1.1 KiB
YAML
input:
|
|
file_type: text
|
|
base_dir: ../../fixtures/min-csv
|
|
file_pattern: .*\.txt$
|
|
|
|
storage:
|
|
type: memory
|
|
|
|
cache:
|
|
type: memory
|
|
|
|
workflows:
|
|
- name: create_base_text_units
|
|
config:
|
|
text_chunk:
|
|
strategy:
|
|
type: sentence
|
|
|
|
# Just lump everything together
|
|
chunk_by: []
|
|
|
|
- name: create_base_extracted_entities
|
|
config:
|
|
graphml_snapshot: True
|
|
entity_extract:
|
|
strategy:
|
|
type: nltk
|
|
|
|
- name: create_base_entity_graph
|
|
config:
|
|
graphml_snapshot: True
|
|
embed_graph_enabled: True
|
|
cluster_graph:
|
|
strategy:
|
|
type: leiden
|
|
verbose: True
|
|
|
|
- name: create_final_nodes
|
|
|
|
- name: create_base_documents
|
|
|
|
- name: create_final_communities
|
|
- name: create_final_text_units
|
|
config:
|
|
text_embed:
|
|
strategy:
|
|
type: mock
|
|
|
|
- name: create_final_entities
|
|
config:
|
|
text_embed:
|
|
strategy:
|
|
type: mock
|
|
|
|
- name: create_final_documents
|
|
config:
|
|
text_embed:
|
|
strategy:
|
|
type: mock
|
|
- name: create_final_relationships
|
|
config:
|
|
text_embed:
|
|
strategy:
|
|
type: mock
|