TanWenyan/leaudit-platform-backend
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(rag): add temporary chat attachments

Browse Source
This commit is contained in:
wren
2026-05-25 15:37:37 +08:00
parent 0f385c9839
commit 75c077da77
16 changed files with 2257 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastapi_modules/fastapi_leaudit/rag_engine/retriever.py
+18 -6
View File
@@ -183,10 +183,15 @@ class RagRetriever:
"source": meta.get("source") or meta.get("document_name") or dataset_name,
"score": score,
"chunk_index": int(meta.get("chunk_index") or idx),
"document_name": document_name,
"document_id": meta.get("document_id"),
"page": meta.get("page"),
}
"document_name": document_name,
"document_id": meta.get("document_id"),
"page": meta.get("page"),
"source_scope": meta.get("source_scope"),
"attachment_id": meta.get("attachment_id"),
"conversation_id": meta.get("conversation_id"),
"tenant_code": meta.get("tenant_code"),
"user_id": meta.get("user_id"),
}
)
return chunks
@@ -285,6 +290,11 @@ class RagRetriever:
"document_name": document_name,
"document_id": meta.get("document_id"),
"page": meta.get("page"),
"source_scope": meta.get("source_scope"),
"attachment_id": meta.get("attachment_id"),
"conversation_id": meta.get("conversation_id"),
"tenant_code": meta.get("tenant_code"),
"user_id": meta.get("user_id"),
}
)
@@ -392,10 +402,10 @@ class RagRetriever:
{
"position": index + 1,
"dataset_id": str(chunk.get("dataset_id") or ""),
"dataset_name": dataset_name,
"dataset_name": chunk.get("dataset_name") or dataset_name,
"document_id": str(chunk.get("document_id") or ""),
"document_name": chunk.get("document_name") or chunk.get("source", ""),
"data_source_type": "upload_file",
"data_source_type": chunk.get("data_source_type") or chunk.get("source_scope") or "upload_file",
"segment_id": chunk.get("id", ""),
"retriever_from": "rag",
"score": round(float(chunk.get("score") or 0.0), 4),
@@ -405,6 +415,8 @@ class RagRetriever:
"index_node_hash": "",
"content": chunk.get("text", "")[:500],
"page": None,
"source_scope": chunk.get("source_scope") or "",
"attachment_id": chunk.get("attachment_id") or "",
}
for index, chunk in enumerate(context_chunks)
]