fix: get documents API and text files connector

selfie/api/documents.py

@@ -1,3 +1,4 @@
+from datetime import datetime
 from typing import List, Optional
 
 from fastapi import APIRouter, Query
@@ -27,8 +28,8 @@ class FetchedDocument(BaseModel):
     id: int = Field(..., description="The unique identifier of the document")
     name: str = Field(..., description="The name of the document")
     size: int = Field(..., description="The size of the document")
-    created_at: str = Field(..., description="The timestamp of the document creation")
-    updated_at: str = Field(..., description="The timestamp of the document update")
+    created_at: datetime = Field(..., description="The timestamp of the document creation")
+    updated_at: datetime = Field(..., description="The timestamp of the document update")
     content_type: str = Field(..., description="The content type of the document")
     connector_name: str = Field(..., description="The name of the connector")
 

selfie/connectors/text_files/uischema.json

@@ -1,8 +1,5 @@
 {
   "files": {
-    "ui:widget": "nativeFile",
-    "ui:options": {
-      "accept": ".json"
-    }
+    "ui:widget": "nativeFile"
   }
 }

selfie/embeddings/__init__.py

@@ -74,6 +74,7 @@ def __init__(self, character_name, storage_path: str = config.embeddings_storage
             self.completion = completion or get_default_completion()
             self.character_name = character_name
             self.embeddings = Embeddings(
+                hybrid=True,
                 sqlite={"wal": True},
                 # For now, sqlite w/the default driver is the only way to use WAL.
                 content=True
@@ -346,6 +347,7 @@ async def recall(
         include_summary=True,
         local_llm=True,
         min_score=0.4,
+        hybrid_search_weight=1.0,  # TODO: Setting this to only use the dense index until this is tuned, e.g., with min_score
     ):
         if min_score is None:
             min_score = 0.4
@@ -354,7 +356,7 @@ async def recall(
             return {"documents": [], "summary": "No documents found.", "mean_score": 0}
         self.embeddings.load(self.storage_path)
 
-        results = self._query(where="similar(:topic)", parameters={"topic": topic}, limit=limit)
+        results = self._query(where=f"similar(:topic, {hybrid_search_weight})", parameters={"topic": topic}, limit=limit)
         documents_list: List[ScoredEmbeddingDocumentModel] = []
         for result in results:
             document = EmbeddingDocumentModel(