From b75fde81853fe2a55d14eb3332d5fb74c819c9b9 Mon Sep 17 00:00:00 2001
From: Mahdi Bazrafshan <mba@ittalie.com>
Date: Sun, 26 Jul 2026 12:05:52 +0330
Subject: [PATCH] fix(models): add text field to ChunkMetadata for Qdrant
 storage

Why:
- Qdrant was storing only metadata, not chunk text
- Queries returned empty text in retrieved chunks
- Scores were low (~0.25) because embeddings were on empty strings

Changes:
- Added 'text' field to ChunkMetadata model
- Updated chunk_to_metadata() to copy text
---
 src/core/models.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/core/models.py b/src/core/models.py
index 9d997ba..27ef230 100644
--- a/src/core/models.py
+++ b/src/core/models.py
@@ -21,7 +21,6 @@ class Chunk(BaseModel):
     Strategy-specific fields (parent_id, enriched_content) are nullable
     when not applicable to the strategy that produced the chunk.
     """
-
     document_name: str
     chunk_id: str
     strategy_name: StrategyName
@@ -35,11 +34,11 @@ class Chunk(BaseModel):
 
 class ChunkMetadata(BaseModel):
     """Payload stored alongside every chunk vector in Qdrant."""
-
     document_name: str
     chunk_id: str
     strategy_name: StrategyName
     chunk_index: int
+    text: str
     token_count: int
     character_count: int
     parent_id: Optional[str] = None
@@ -52,6 +51,7 @@ def chunk_to_metadata(chunk: Chunk) -> ChunkMetadata:
         chunk_id=chunk.chunk_id,
         strategy_name=chunk.strategy_name,
         chunk_index=chunk.chunk_index,
+        text=chunk.text,
         token_count=chunk.token_count,
         character_count=chunk.character_count,
         parent_id=chunk.parent_id,
@@ -92,4 +92,4 @@ class PaginatedResponse(BaseModel):
     items: list = Field(default_factory=list)
     total: int = 0
     offset: int = 0
-    limit: int = 50
\ No newline at end of file
+    limit: int = 50