Add LLM util (#225)

Author: katarinasupe

README.md

@@ -267,6 +267,7 @@ YIELD node, rank;
 | [katz_centrality_online](https://memgraph.com/docs/mage/query-modules/cpp/katz-centrality-online)                | C++    | Online implementation of the Katz centrality. Outputs the approximate result for Katz centrality while maintaining the order of rankings.                                                                                         |
 | [kmeans](https://memgraph.com/docs/mage/query-modules/python/kmeans)                                             | Python | An algorithm for clustering given data.                                                                                                                                                                                                  |
 | [link_prediction_gnn](https://memgraph.com/docs/mage/query-modules/python/link-prediction-with-gnn)              | Python | A module for predicting links in graphs using graph neural networks.                                                                                                                                                          |
+| [llm_util](https://memgraph.com/docs/mage/query-modules/python/llm-util)                                        | Python | A module that contains procedures describing graphs in a format best suited for large language models (LLMs).     |
 | [max_flow](https://memgraph.com/docs/mage/query-modules/python/max-flow)                                         | Python | An algorithm for calculating maximum flow through a graph using capacity scaling                                                                                                                                                  |
 | [meta_util](https://memgraph.com/docs/mage/query-modules/python/meta-util)                                                                                                             | Python | A module that contains procedures describing graphs on a meta-level.                                                                    |
 | [node_classification_with_gnn](https://memgraph.com/docs/mage/query-modules/python/node-classification-with-gnn) | Python | A graph neural network-based node classification module.                                                                                                                                                                            |

e2e/llm_util_test/test_schema_default_with_relationship_props/input.cyp

@@ -0,0 +1 @@
+CREATE (n:Person {name: "Kate", age: 27})-[:IS_FRIENDS_WITH {since: "2023-06-21"}]->(m:Person:Student {name: "James", age: 30, year: "second"})-[:STUDIES_AT]->(:University {name: "University of Zagreb"}) CREATE (p:Person:Student {name: "Anthony", age: 25})-[:STUDIES_AT]->(:University {name: "University of Vienna"}) WITH n, m CREATE (n)-[:LIVES_IN]->(:City {name: "Zagreb"})<-[:LIVES_IN]-(m);

e2e/llm_util_test/test_schema_default_with_relationship_props/test.yml

@@ -0,0 +1,4 @@
+query: >
+    CALL llm_util.schema() YIELD schema RETURN schema;
+output:
+  - schema: "Node properties are the following:\nNode name: 'Person', Node properties: [{'property': 'name', 'type': 'str'}, {'property': 'age', 'type': 'int'}, {'property': 'year', 'type': 'str'}]\nNode name: 'Student', Node properties: [{'property': 'name', 'type': 'str'}, {'property': 'age', 'type': 'int'}, {'property': 'year', 'type': 'str'}]\nNode name: 'University', Node properties: [{'property': 'name', 'type': 'str'}]\nNode name: 'City', Node properties: [{'property': 'name', 'type': 'str'}]\n\nRelationship properties are the following:\nRelationship Name: 'IS_FRIENDS_WITH', Relationship Properties: [{'property': 'since', 'type': 'str'}]\n\nThe relationships are the following:\n['(:Person)-[:IS_FRIENDS_WITH]->(:Person)']\n['(:Person)-[:IS_FRIENDS_WITH]->(:Student)']\n['(:Person)-[:LIVES_IN]->(:City)']\n['(:Person)-[:STUDIES_AT]->(:University)']\n['(:Student)-[:STUDIES_AT]->(:University)']\n['(:Student)-[:LIVES_IN]->(:City)']\n"

e2e/llm_util_test/test_schema_default_without_relationship_props/input.cyp

@@ -0,0 +1 @@
+CREATE (n:Person {name: "Kate", age: 27})-[:IS_FRIENDS_WITH]->(m:Person:Student {name: "James", age: 30, year: "second"})-[:STUDIES_AT]->(:University {name: "University of Zagreb"}) CREATE (p:Person:Student {name: "Anthony", age: 25})-[:STUDIES_AT]->(:University {name: "University of Vienna"}) WITH n, m CREATE (n)-[:LIVES_IN]->(:City {name: "Zagreb"})<-[:LIVES_IN]-(m);

e2e/llm_util_test/test_schema_default_without_relationship_props/test.yml

@@ -0,0 +1,5 @@
+query: >
+    CALL llm_util.schema() YIELD schema RETURN schema;
+output:
+  - schema: "Node properties are the following:\nNode name: 'Person', Node properties: [{'property': 'name', 'type': 'str'}, {'property': 'age', 'type': 'int'}, {'property': 'year', 'type': 'str'}]\nNode name: 'Student', Node properties: [{'property': 'name', 'type': 'str'}, {'property': 'age', 'type': 'int'}, {'property': 'year', 'type': 'str'}]\nNode name: 'University', Node properties: [{'property': 'name', 'type': 'str'}]\nNode name: 'City', Node properties: [{'property': 'name', 'type': 'str'}]\n\nRelationship properties are the following:\n\nThe relationships are the following:\n['(:Person)-[:IS_FRIENDS_WITH]->(:Person)']\n['(:Person)-[:IS_FRIENDS_WITH]->(:Student)']\n['(:Person)-[:LIVES_IN]->(:City)']\n['(:Person)-[:STUDIES_AT]->(:University)']\n['(:Student)-[:STUDIES_AT]->(:University)']\n['(:Student)-[:LIVES_IN]->(:City)']\n"
+ 

e2e/llm_util_test/test_schema_empty/input.cyp

@@ -0,0 +1,4 @@
+query: >
+  CALL llm_util.schema() YIELD * RETURN *;
+exception:
+    - Can't generate a graph schema since there is no data in the database.

e2e/llm_util_test/test_schema_empty/test.yml

@@ -0,0 +1 @@
+CREATE (n);

e2e/llm_util_test/test_schema_error_argument/input.cyp

@@ -0,0 +1,4 @@
+query: >
+  CALL llm_util.schema('wrong_arg') YIELD * RETURN *;
+exception:
+    - Can't generate a graph schema since the provided output_type is not correct. Please choose raw or prompt_ready.

e2e/llm_util_test/test_schema_error_argument/test.yml

@@ -0,0 +1 @@
+CREATE (n:Person {name: "Kate", age: 27})-[:IS_FRIENDS_WITH]->(m:Person:Student {name: "James", age: 30, year: "second"})-[:STUDIES_AT]->(:University {name: "University of Zagreb"}) CREATE (p:Person:Student {name: "Anthony", age: 25})-[:STUDIES_AT]->(:University {name: "University of Vienna"}) WITH n, m CREATE (n)-[:LIVES_IN]->(:City {name: "Zagreb"})<-[:LIVES_IN]-(m);