add filename option for text documents (#47)

core/api.py

@@ -261,6 +261,7 @@ async def ingest_text(
     Args:
         request: IngestTextRequest containing:
             - content: Text content to ingest
+            - filename: Optional filename to help determine content type
             - metadata: Optional metadata dictionary
             - rules: Optional list of rules. Each rule should be either:
                    - MetadataExtractionRule: {"type": "metadata_extraction", "schema": {...}}
@@ -283,6 +284,7 @@ async def ingest_text(
         ):
             return await document_service.ingest_text(
                 content=request.content,
+                filename=request.filename,
                 metadata=request.metadata,
                 rules=request.rules,
                 use_colpali=request.use_colpali,

core/models/request.py

@@ -24,6 +24,7 @@ class IngestTextRequest(BaseModel):
     """Request model for ingesting text content"""
 
     content: str
+    filename: Optional[str] = None
     metadata: Dict[str, Any] = Field(default_factory=dict)
     rules: List[Dict[str, Any]] = Field(default_factory=list)
     use_colpali: Optional[bool] = None

core/services/document_service.py

@@ -36,7 +36,6 @@ import os
 logger = logging.getLogger(__name__)
 IMAGE = {im.mime for im in IMAGE}
 
-
 class DocumentService:
     def __init__(
         self,
@@ -185,6 +184,7 @@ class DocumentService:
     async def ingest_text(
         self,
         content: str,
+        filename: Optional[str] = None,
         metadata: Optional[Dict[str, Any]] = None,
         auth: AuthContext = None,
         rules: Optional[List[str]] = None,
@@ -197,6 +197,7 @@ class DocumentService:
 
         doc = Document(
             content_type="text/plain",
+            filename=filename,
             metadata=metadata or {},
             owner={"type": auth.entity_type, "id": auth.entity_id},
             access_control={

sdks/python/databridge/models.py

@@ -70,6 +70,7 @@ class IngestTextRequest(BaseModel):
     """Request model for ingesting text content"""
 
     content: str
+    filename: Optional[str] = None
     metadata: Dict[str, Any] = Field(default_factory=dict)
     rules: List[Dict[str, Any]] = Field(default_factory=list)
     use_colpali: bool = Field(default=False)

sdks/python/databridge/sync.py

@@ -150,6 +150,7 @@ class DataBridge:
     def ingest_text(
         self,
         content: str,
+        filename: Optional[str] = None,
         metadata: Optional[Dict[str, Any]] = None,
         rules: Optional[List[RuleOrDict]] = None,
         use_colpali: bool = True,
@@ -191,6 +192,7 @@ class DataBridge:
         """
         request = IngestTextRequest(
             content=content,
+            filename=filename,
             metadata=metadata or {},
             rules=[self._convert_rule(r) for r in (rules or [])],
             use_colpali=use_colpali,