added score_threshold to the configs and .env.template

.env.template

@@ -24,6 +24,7 @@ TOP_K_MATCHES=1
 # MongoDB Configuration
 MONGODB_URI=mongodb+srv://username:[email protected]/database?retryWrites=true&w=majority
 MONGODB_NAME=ctp_slack_bot
+SCORE_THRESHOLD=0.5
 
 # Hugging Face Configuration
 HF_API_TOKEN=🤗

src/ctp_slack_bot/core/config.py

@@ -31,6 +31,7 @@ class Settings(BaseSettings): # TODO: Strong guarantees of validity, because gar
     # MongoDB Configuration
     MONGODB_URI: SecretStr # TODO: Contemplate switching to MongoDsn type for the main URL, and separate out the credentials to SecretStr variables.
     MONGODB_NAME: str
+    SCORE_THRESHOLD: NonNegativeFloat
 
     # Hugging Face Configuration
     HF_API_TOKEN: Optional[SecretStr] = None

src/ctp_slack_bot/models/base.py

@@ -1,6 +1,6 @@
 from abc import ABC, abstractmethod
-from pydantic import BaseModel, ConfigDict
-from typing import Any, Dict, final, Self, Sequence
+from pydantic import BaseModel, ConfigDict, Field
+from typing import Any, Dict, final, Self, Sequence, Optional
 
 
 class Chunk(BaseModel):
@@ -13,7 +13,23 @@ class Chunk(BaseModel):
 
     model_config = ConfigDict(frozen=True)
 
+@final
+class VectorQuery(BaseModel):
+    """Model for vector database similarity search queries.
+    
+    Attributes:
+        query_text: The text to be vectorized and used for similarity search
+        k: Number of similar documents to retrieve
+        score_threshold: Minimum similarity score threshold for inclusion in results
+        filter_metadata: Optional filters for metadata fields
+    """
+
+    query_embeddings: Sequence[float]
+    k: int
+    score_threshold: float = Field(default=0.7)
+    filter_metadata: Optional[Dict[str, Any]] = None
 
+    
 @final
 class VectorizedChunk(Chunk):
     """A class representing a vectorized chunk of content."""

src/ctp_slack_bot/models/vector_query.py

@@ -1,17 +0,0 @@
-from pydantic import BaseModel, Field, model_validator
-from typing import Any, Dict, Optional, Sequence
-
-class VectorQuery(BaseModel):
-    """Model for vector database similarity search queries.
-    
-    Attributes:
-        query_text: The text to be vectorized and used for similarity search
-        k: Number of similar documents to retrieve
-        score_threshold: Minimum similarity score threshold for inclusion in results
-        filter_metadata: Optional filters for metadata fields
-    """
-
-    query_embeddings: Sequence[float]
-    k: int
-    score_threshold: float = Field(default=0.7)
-    filter_metadata: Optional[Dict[str, Any]] = None