Nolan/collections summary (#1685)

* Add document summary to extraction process

* Collection summarization and inclusion in community generation

* Add test, fix mypy

* Clean up

* Fix test with new required body, remove print statements and add check

Author: NolanTrem

.pre-commit-config.yaml

@@ -17,6 +17,15 @@ repos:
         types: [python]
         pass_filenames: false
 
+  - repo: local
+    hooks:
+      - id: check-print-statements
+        name: Check for print statements
+        entry: bash -c 'echo "Checking for print statements..." && find . -name "*.py" ! -path "./py/cli/*" ! -path "./py/core/examples/*" ! -path "./py/migrations/*" ! -path "./py/tests/*" | xargs grep -n "print(" || exit 0 && echo "Found print statements!" && exit 1'
+        language: system
+        types: [python]
+        pass_filenames: false
+
   - repo: local
     hooks:
       - id: isort

js/sdk/__tests__/CollectionsIntegrationSuperUser.test.ts

@@ -35,14 +35,26 @@ describe("r2rClient V3 Collections Integration Tests", () => {
   test("Retrieve collection", async () => {
     const response = await client.collections.retrieve({ id: collectionId });
     expect(response.results).toBeDefined();
+    expect(response.results.id).toBe(collectionId);
+    expect(response.results.name).toBe("Test Collection");
+    expect(response.results.description).toBeNull();
   });
 
   test("Update collection", async () => {
     const response = await client.collections.update({
       id: collectionId,
       name: "Updated Test Collection",
+      generateDescription: true,
     });
     expect(response.results).toBeDefined();
+  }, 10000);
+
+  test("Retrieve updated collection", async () => {
+    const response = await client.collections.retrieve({ id: collectionId });
+    expect(response.results).toBeDefined();
+    expect(response.results.id).toBe(collectionId);
+    expect(response.results.name).toBe("Updated Test Collection");
+    expect(response.results.description).toBeDefined();
   });
 
   test("Ingest document and assign to collection", async () => {

js/sdk/__tests__/DocumentsAndCollectionsIntegrationUser.test.ts

@@ -114,7 +114,7 @@ describe("r2rClient V3 System Integration Tests User", () => {
 
     expect(response.results.document_id).toBeDefined();
     user1DocumentId = response.results.document_id;
-  }, 10000);
+  }, 15000);
 
   test("Create document as user 2 with file path", async () => {
     const response = await user2Client.documents.create({
@@ -126,7 +126,7 @@ describe("r2rClient V3 System Integration Tests User", () => {
 
     expect(response.results.document_id).toBeDefined();
     user2DocumentId = response.results.document_id;
-  }, 10000);
+  }, 15000);
 
   test("Retrieve document as user 1", async () => {
     const response = await user1Client.documents.retrieve({

js/sdk/__tests__/GraphsIntegrationSuperUser.test.ts

@@ -228,6 +228,7 @@ describe("r2rClient V3 Graphs Integration Tests", () => {
       predicate: "falls in love with",
       object: "Dunia",
       objectId: entity2Id,
+      description: "Razumikhn and Dunia are central to the story",
     });
 
     relationshipId = response.results.id;
@@ -236,6 +237,7 @@ describe("r2rClient V3 Graphs Integration Tests", () => {
     expect(response.results.subject).toBe("Razumikhin");
     expect(response.results.object).toBe("Dunia");
     expect(response.results.predicate).toBe("falls in love with");
+    expect(response.results.description).toBe("Razumikhn and Dunia are central to the story");
   });
 
   test("Retrieve the relationship", async () => {