upsert-file endpoint accepts metadata (openai#123)

examples/authentication-methods/no-auth/main.py

@@ -1,7 +1,8 @@
 # This is a version of the main.py file found in ../../../server/main.py without authentication.
 # Copy and paste this into the main file at ../../../server/main.py if you choose to use no authentication for your retrieval plugin.
+from typing import Optional
 import uvicorn
-from fastapi import FastAPI, File, HTTPException, Body, UploadFile
+from fastapi import FastAPI, File, Form, HTTPException, Body, UploadFile
 from fastapi.staticfiles import StaticFiles
 
 from models.api import (
@@ -15,6 +16,8 @@
 from datastore.factory import get_datastore
 from services.file import get_document_from_file
 
+from models.models import DocumentMetadata, Source
+
 
 app = FastAPI()
 app.mount("/.well-known", StaticFiles(directory=".well-known"), name="static")
@@ -35,8 +38,18 @@
 )
 async def upsert_file(
     file: UploadFile = File(...),
+    metadata: Optional[str] = Form(None),
 ):
-    document = await get_document_from_file(file)
+    try:
+        metadata_obj = (
+            DocumentMetadata.parse_raw(metadata)
+            if metadata
+            else DocumentMetadata(source=Source.file)
+        )
+    except:
+        metadata_obj = DocumentMetadata(source=Source.file)
+
+    document = await get_document_from_file(file, metadata_obj)
 
     try:
         ids = await datastore.upsert([document])

examples/memory/main.py

@@ -3,8 +3,9 @@
 # Copy and paste this into the main file at ../../server/main.py if you choose to give the model access to the upsert endpoint
 # and want to access the openapi.json when you run the app locally at http://0.0.0.0:8000/sub/openapi.json.
 import os
+from typing import Optional
 import uvicorn
-from fastapi import FastAPI, File, HTTPException, Depends, Body, UploadFile
+from fastapi import FastAPI, File, Form, HTTPException, Depends, Body, UploadFile
 from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
 from fastapi.staticfiles import StaticFiles
 
@@ -19,6 +20,8 @@
 from datastore.factory import get_datastore
 from services.file import get_document_from_file
 
+from models.models import DocumentMetadata, Source
+
 
 bearer_scheme = HTTPBearer()
 BEARER_TOKEN = os.environ.get("BEARER_TOKEN")
@@ -51,9 +54,18 @@ def validate_token(credentials: HTTPAuthorizationCredentials = Depends(bearer_sc
 )
 async def upsert_file(
     file: UploadFile = File(...),
-    token: HTTPAuthorizationCredentials = Depends(validate_token),
+    metadata: Optional[str] = Form(None),
 ):
-    document = await get_document_from_file(file)
+    try:
+        metadata_obj = (
+            DocumentMetadata.parse_raw(metadata)
+            if metadata
+            else DocumentMetadata(source=Source.file)
+        )
+    except:
+        metadata_obj = DocumentMetadata(source=Source.file)
+
+    document = await get_document_from_file(file, metadata_obj)
 
     try:
         ids = await datastore.upsert([document])

server/main.py

@@ -1,6 +1,7 @@
 import os
+from typing import Optional
 import uvicorn
-from fastapi import FastAPI, File, HTTPException, Depends, Body, UploadFile
+from fastapi import FastAPI, File, Form, HTTPException, Depends, Body, UploadFile
 from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
 from fastapi.staticfiles import StaticFiles
 
@@ -15,6 +16,8 @@
 from datastore.factory import get_datastore
 from services.file import get_document_from_file
 
+from models.models import DocumentMetadata, Source
+
 bearer_scheme = HTTPBearer()
 BEARER_TOKEN = os.environ.get("BEARER_TOKEN")
 assert BEARER_TOKEN is not None
@@ -46,8 +49,18 @@ def validate_token(credentials: HTTPAuthorizationCredentials = Depends(bearer_sc
 )
 async def upsert_file(
     file: UploadFile = File(...),
+    metadata: Optional[str] = Form(None),
 ):
-    document = await get_document_from_file(file)
+    try:
+        metadata_obj = (
+            DocumentMetadata.parse_raw(metadata)
+            if metadata
+            else DocumentMetadata(source=Source.file)
+        )
+    except:
+        metadata_obj = DocumentMetadata(source=Source.file)
+
+    document = await get_document_from_file(file, metadata_obj)
 
     try:
         ids = await datastore.upsert([document])

services/file.py

@@ -8,14 +8,14 @@
 import csv
 import pptx
 
-from models.models import Document, DocumentMetadata, Source
+from models.models import Document, DocumentMetadata
 
 
-async def get_document_from_file(file: UploadFile) -> Document:
+async def get_document_from_file(
+    file: UploadFile, metadata: DocumentMetadata
+) -> Document:
     extracted_text = await extract_text_from_form_file(file)
-    metadata = DocumentMetadata(
-        source=Source.file,
-    )
+
     doc = Document(text=extracted_text, metadata=metadata)
 
     return doc