fix db engine config

cognee/infrastructure/InfrastructureConfig.py

@@ -2,6 +2,7 @@ import logging
 import os
 
 from cognee.config import Config
+from .data.chunking.config import get_chunk_config
 from .databases.relational import DuckDBAdapter, DatabaseEngine
 from .databases.vector.vector_db_interface import VectorDBInterface
 from .databases.vector.embeddings.DefaultEmbeddingEngine import DefaultEmbeddingEngine
@@ -18,6 +19,7 @@ config.load()
 from cognee.infrastructure.databases.relational.config import get_relationaldb_config
 
 relational = get_relationaldb_config()
+chunk_config = get_chunk_config()
 class InfrastructureConfig():
 
     system_root_directory: str = config.system_root_directory
@@ -38,7 +40,7 @@ class InfrastructureConfig():
     connect_documents = config.connect_documents
     database_directory_path: str = None
     database_file_path: str = None
-    chunk_strategy = config.chunk_strategy
+    chunk_strategy = chunk_config.chunk_strategy
     chunk_engine = None
     graph_topology = config.graph_topology
     monitoring_tool = config.monitoring_tool
@@ -86,10 +88,10 @@ class InfrastructureConfig():
             self.connect_documents = config.connect_documents
 
         if self.chunk_strategy is None:
-            self.chunk_strategy = config.chunk_strategy
+            self.chunk_strategy = chunk_config.chunk_strategy
 
         if self.chunk_engine is None:
-            self.chunk_engine = DefaultChunkEngine()
+            self.chunk_engine = chunk_config.chunk_engine
 
         if self.graph_topology is None:
             self.graph_topology = config.graph_topology

cognee/infrastructure/data/chunking/config.py

@@ -0,0 +1,27 @@
+from functools import lru_cache
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+from cognee.infrastructure.data.chunking.DefaultChunkEngine import DefaultChunkEngine
+from cognee.shared.data_models import ChunkStrategy
+
+
+class ChunkConfig(BaseSettings):
+    chunk_size: int = 1500
+    chunk_overlap: int = 0
+    chunk_strategy: object = ChunkStrategy.PARAGRAPH
+    chunk_engine: object = DefaultChunkEngine()
+
+
+    model_config = SettingsConfigDict(env_file = ".env", extra = "allow")
+
+    def to_dict(self) -> dict:
+        return {
+            "chunk_size": self.chunk_size,
+            "chunk_overlap": self.chunk_overlap,
+            "chunk_strategy": self.chunk_strategy
+        }
+
+
+@lru_cache
+def get_chunk_config():
+    return ChunkConfig()

cognee/tests/test_library.py

@@ -24,9 +24,9 @@ async def  main():
 
     dataset_name = "cs_explanations"
 
-    # explanation_file_path = "test_data/Natural_language_processing.txt"
+    explanation_file_path = os.path.join(os.getcwd(), "test_data/Natural_language_processing.txt")
     #
-    # await cognee.add([explanation_file_path], dataset_name)
+    await cognee.add([explanation_file_path], dataset_name)
     
     # dataset_name = "short_stories"
     # # data_directory_path is defined above
@@ -46,15 +46,15 @@ async def  main():
     Some notable LLMs are OpenAI's GPT series of models (e.g., GPT-3.5 and GPT-4, used in ChatGPT and Microsoft Copilot), Google's PaLM and Gemini (the latter of which is currently used in the chatbot of the same name), xAI's Grok, Meta's LLaMA family of open-source models, Anthropic's Claude models, Mistral AI's open source models, and Databricks' open source DBRX.
     """
 
-
-    dataset_name = "cs_explanations"
-    await cognee.add(
-        [
-            text_1,
-            text_2
-        ],
-        dataset_name
-    )
+    #
+    # dataset_name = "cs_explanations"
+    # await cognee.add(
+    #     [
+    #         text_1,
+    #         text_2
+    #     ],
+    #     dataset_name
+    # )
 
     await cognee.cognify([ "cs_explanations"])