The link of upload files is broken in the chat view pingcap#466

backend/.env.example

@@ -0,0 +1,28 @@
+ENVIRONMENT=production
+
+# You can generate a new secret key by running the following command
+# $ python3 -c "import secrets; print(secrets.token_urlsafe(32))"
+# SECRET_KEY is very important, please do not share it with others,
+# SECRET_KEY must greater or equal to 32 characters.
+SECRET_KEY=
+
+# Replace with your own sentry dsn, leave it commented if you don't want to use sentry
+# SENTRY_DSN=https://[email protected]/xxxxxx
+
+# Replace with your own TiDB cluster connection information,
+# TiDB Serverless is recommended. You can quickly create one from https://tidbcloud.com/
+TIDB_HOST=xxxxx.prod.aws.tidbcloud.com
+TIDB_USER=
+TIDB_PASSWORD=
+TIDB_DATABASE=
+TIDB_SSL=true
+
+# EMBEDDING_MAX_TOKENS indicates the max size of document chunks.
+#
+# EMBEDDING_MAX_TOKENS should be smaller than the embedding model's max tokens due
+# to the tokenizer difference. (see: https://github.com/pingcap/autoflow/issues/397)
+#
+# Go to https://tidb.ai/docs/embedding-model to check the max tokens of the embedding model.
+#
+# Notice: this variable will be deprecated in the future.
+EMBEDDING_MAX_TOKENS=2048

backend/app/api/main.py

@@ -53,7 +53,7 @@
 api_router.include_router(feedback.router, tags=["chat"])
 api_router.include_router(user.router, tags=["user"])
 api_router.include_router(api_key.router, tags=["auth"])
-api_router.include_router(download.router)
+api_router.include_router(download.router, tags=["download_file"])
 api_router.include_router(admin_chat_engine.router, tags=["admin/chat_engine"])
 api_router.include_router(admin_document_router, tags=["admin/documents"])
 api_router.include_router(admin_feedback.router, tags=["admin/feedback"])

backend/app/api/routes/download.py

@@ -1,24 +1,28 @@
-from fastapi import FastAPI, HTTPException
+from fastapi import FastAPI, HTTPException, APIRouter
 from fastapi.responses import FileResponse
 
-from app.models import Upload
-from app.rag.datasource import FileDataSource
-from app.file_storage import default_file_storage
+from sqlmodel import select, Session, col
+from app.api.deps import SessionDep
+from app.models import Document
+from app.repositories import document_repo
+import os
 
 router = APIRouter()
 
-@router.get("/documents/{document_id}/download")
-def download_file(document_id: int):
-    isfound = False    
-    for f_config in FileDataSource.config:
-        if f_config["file_id"] == document_id:
-            isfound = True
-    # 找到了就返回文件
-    if isfound == True:
-        upload = FileDataSource.session.get(Upload, document_id)
-        return FileResponse(path=upload.path, filename=upload.name, media_type='application/octet-stream')
-    # 没找到应该 302 到对应的 url，但先404
+@router.get("/documents/{doc_id}/download")
+def download_file(
+    doc_id: int,
+    session: SessionDep
+):
+    doc = session.get(Document, doc_id)
+    if not doc:
+        raise HTTPException(status_code = 404, detail = "File not found")
+
+    DATA_PATH = "../data"
+    source_uri = os.path.join(DATA_PATH, doc.source_uri) 
+    if os.path.exists(source_uri):
+        return FileResponse(path = source_uri, filename = doc.name, media_type = doc.mime_type)
     else:
-        raise HTTPException(status_code=404, detail="lmw : File not found")
+        raise HTTPException(status_code = 404, detail = "File not found")