graphrag/tests/integration/_pipeline/megapipeline.yml
Nathan Evans 61b3d6d56a
Migrate helper verbs (#1248)
* Remove genid

* Move snapshot_rows

* Move snapshot

* Delete spread_json

* Delete unzip

* Delete zip

* Move unpack_graph

* Move compute_edge_combined_degree

* Delete create_graph

* Delete concat

* Delete text replace

* Delete text_translate

* Move text_split

* Inline aggregate override

* Move cluster_graph

* Move merge_graphs

* Semver

* Move text_chunk

* Move layout_graph and fix some __init__s

* Move extract_covariates

* Rename text_split -> split_text

* Move extract_entities

* Move summarize_descriptions

* Rename text_chunk -> chunk_text

* Move community report creation

* Remove verb-level packing operators

* Streamline some naming

* Streamline param name/order

* Move mock LLM data to tests

* Fixed missed rename

* Update some strategy refs

* Rename run_gi

* Inject mock responses into integ test config
2024-10-09 13:46:44 -07:00

87 lines
2.1 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: graph_intelligence
llm:
type: static_response
responses:
- '("entity"<|>COMPANY_A<|>COMPANY<|>Company_A is a test company)
##
("entity"<|>COMPANY_B<|>COMPANY<|>Company_B owns Company_A and also shares an address with Company_A)
##
("entity"<|>PERSON_C<|>PERSON<|>Person_C is director of Company_A)
##
("relationship"<|>COMPANY_A<|>COMPANY_B<|>Company_A and Company_B are related because Company_A is 100% owned by Company_B and the two companies also share the same address)<|>2)
##
("relationship"<|>COMPANY_A<|>PERSON_C<|>Company_A and Person_C are related because Person_C is director of Company_A<|>1))'
- name: create_summarized_entities
config:
summarize_descriptions:
strategy:
type: graph_intelligence
llm:
type: static_response
responses:
- This is a MOCK response for the LLM. It is summarized!
- 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