refac

backend/open_webui/routers/ollama.py

@@ -86,6 +86,17 @@ log = logging.getLogger(__name__)
 #
 ##########################################
 
+# Headers that become stale after aiohttp auto-decompresses the upstream
+# response body.  Forwarding them verbatim causes desktop / programmatic
+# clients to attempt decompression of an already-decoded payload, resulting
+# in ZlibError.  See https://github.com/aio-libs/aiohttp/issues/4462.
+_STRIP_PROXY_HEADERS = frozenset({'Content-Encoding', 'Content-Length', 'Transfer-Encoding'})
+
+
+def _clean_proxy_headers(raw_headers) -> dict:
+    """Return a copy of *raw_headers* with stale encoding headers removed."""
+    return {k: v for k, v in raw_headers.items() if k not in _STRIP_PROXY_HEADERS}
+
 
 async def send_get_request(url, key=None, user: UserModel = None):
     timeout = aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST)
@@ -163,7 +174,7 @@ async def send_request(
         r.raise_for_status()
 
         if stream:
-            response_headers = dict(r.headers)
+            response_headers = _clean_proxy_headers(r.headers)
             if content_type:
                 response_headers['Content-Type'] = content_type
 

backend/open_webui/routers/openai.py

@@ -76,6 +76,17 @@ log = logging.getLogger(__name__)
 #
 ##########################################
 
+# Headers that become stale after aiohttp auto-decompresses the upstream
+# response body.  Forwarding them verbatim causes desktop / programmatic
+# clients to attempt decompression of an already-decoded payload, resulting
+# in ZlibError.  See https://github.com/aio-libs/aiohttp/issues/4462.
+_STRIP_PROXY_HEADERS = frozenset({'Content-Encoding', 'Content-Length', 'Transfer-Encoding'})
+
+
+def _clean_proxy_headers(raw_headers) -> dict:
+    """Return a copy of *raw_headers* with stale encoding headers removed."""
+    return {k: v for k, v in raw_headers.items() if k not in _STRIP_PROXY_HEADERS}
+
 
 async def send_get_request(
     request: Request = None,
@@ -1219,7 +1230,7 @@ async def generate_chat_completion(
             return StreamingResponse(
                 stream_wrapper(r, content_handler=stream_chunks_handler),
                 status_code=r.status,
-                headers=dict(r.headers),
+                headers=_clean_proxy_headers(r.headers),
             )
         else:
             try:
@@ -1304,7 +1315,7 @@ async def embeddings(request: Request, form_data: dict, user):
             return StreamingResponse(
                 stream_wrapper(r),
                 status_code=r.status,
-                headers=dict(r.headers),
+                headers=_clean_proxy_headers(r.headers),
             )
         else:
             try:
@@ -1425,7 +1436,7 @@ async def responses(
             return StreamingResponse(
                 stream_wrapper(r),
                 status_code=r.status,
-                headers=dict(r.headers),
+                headers=_clean_proxy_headers(r.headers),
             )
         else:
             try:
@@ -1542,7 +1553,7 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
             return StreamingResponse(
                 stream_wrapper(r),
                 status_code=r.status,
-                headers=dict(r.headers),
+                headers=_clean_proxy_headers(r.headers),
             )
         else:
             try: