Fix Chroma DB if multiple docs are inserted

libs/agno/agno/vectordb/chroma/chromadb.py

@@ -90,15 +90,19 @@ def doc_exists(self, document: Document) -> bool:
         Returns:
             bool: True if document exists, False otherwise.
         """
-        if self.client:
-            try:
-                collection: Collection = self.client.get_collection(name=self.collection_name)
-                collection_data: GetResult = collection.get(include=[IncludeEnum.documents])
-                if collection_data.get("documents") != []:
-                    return True
-            except Exception as e:
-                logger.error(f"Document does not exist: {e}")
-        return False
+        if not self.client:
+            logger.warning("Client not initialized")
+            return False
+
+        try:
+            collection: Collection = self.client.get_collection(name=self.collection_name)
+            collection_data: GetResult = collection.get(include=[IncludeEnum.documents])
+            existing_documents = collection_data.get("documents", [])
+            cleaned_content = document.content.replace("\x00", "\ufffd")
+            if cleaned_content in existing_documents:
+                return True
+        except Exception as e:
+            logger.error(f"Document does not exist: {e}")
 
     def name_exists(self, name: str) -> bool:
         """Check if a document with a given name exists in the collection.

libs/agno/tests/unit/vectordb/test_chromadb.py

@@ -163,3 +163,21 @@ def test_custom_embedder(mock_embedder):
     finally:
         if os.path.exists(TEST_PATH):
             shutil.rmtree(TEST_PATH)
+
+
+def test_multiple_document_operations(chroma_db, sample_documents):
+    """Test multiple document operations including batch inserts"""
+    # Test batch insert
+    first_batch = sample_documents[:2]
+    chroma_db.insert(first_batch)
+    assert chroma_db.get_count() == 2
+
+    # Test adding another document
+    second_batch = [sample_documents[2]]
+    chroma_db.insert(second_batch)
+    assert chroma_db.get_count() == 3
+
+    # Verify all documents are searchable
+    curry_results = chroma_db.search("curry", limit=1)
+    assert len(curry_results) == 1
+    assert "curry" in curry_results[0].content.lower()