Spaces:
Running
Running
Echo-ai
commited on
Update app.py
Browse files
app.py
CHANGED
@@ -1,14 +1,16 @@
|
|
1 |
from fastapi import FastAPI, HTTPException
|
|
|
2 |
import requests
|
|
|
3 |
|
4 |
app = FastAPI()
|
5 |
|
6 |
-
# Ollama internal URL
|
7 |
OLLAMA_BASE_URL = "http://localhost:11434"
|
8 |
|
9 |
-
#
|
10 |
@app.get("/api/{path:path}")
|
11 |
-
async def
|
12 |
url = f"{OLLAMA_BASE_URL}/api/{path}"
|
13 |
params = {"query": query} if query else {}
|
14 |
try:
|
@@ -18,16 +20,25 @@ async def ollama_proxy(path: str, query: str = None):
|
|
18 |
except requests.exceptions.RequestException as e:
|
19 |
raise HTTPException(status_code=500, detail=str(e))
|
20 |
|
21 |
-
|
22 |
-
|
23 |
-
|
|
|
24 |
try:
|
25 |
-
|
|
|
26 |
response.raise_for_status()
|
27 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
except requests.exceptions.RequestException as e:
|
29 |
-
raise HTTPException(status_code=500, detail=str(e))
|
30 |
|
31 |
@app.get("/")
|
32 |
async def root():
|
33 |
-
return {"message": "Ollama running on Hugging Face Spaces!
|
|
|
1 |
from fastapi import FastAPI, HTTPException
|
2 |
+
from fastapi.responses import StreamingResponse
|
3 |
import requests
|
4 |
+
import json
|
5 |
|
6 |
app = FastAPI()
|
7 |
|
8 |
+
# Ollama internal URL
|
9 |
OLLAMA_BASE_URL = "http://localhost:11434"
|
10 |
|
11 |
+
# Generic proxy for other API endpoints
|
12 |
@app.get("/api/{path:path}")
|
13 |
+
async def ollama_proxy_get(path: str, query: str = None):
|
14 |
url = f"{OLLAMA_BASE_URL}/api/{path}"
|
15 |
params = {"query": query} if query else {}
|
16 |
try:
|
|
|
20 |
except requests.exceptions.RequestException as e:
|
21 |
raise HTTPException(status_code=500, detail=str(e))
|
22 |
|
23 |
+
# Handle /api/chat specifically
|
24 |
+
@app.post("/api/chat")
|
25 |
+
async def ollama_chat(body: dict):
|
26 |
+
url = f"{OLLAMA_BASE_URL}/api/chat"
|
27 |
try:
|
28 |
+
# Forward the request to Ollama with streaming support
|
29 |
+
response = requests.post(url, json=body, stream=True)
|
30 |
response.raise_for_status()
|
31 |
+
|
32 |
+
# Stream the response back to the client
|
33 |
+
def generate():
|
34 |
+
for chunk in response.iter_lines():
|
35 |
+
if chunk:
|
36 |
+
yield chunk + b"\n"
|
37 |
+
|
38 |
+
return StreamingResponse(generate(), media_type="text/event-stream")
|
39 |
except requests.exceptions.RequestException as e:
|
40 |
+
raise HTTPException(status_code=500, detail=f"Ollama error: {str(e)}")
|
41 |
|
42 |
@app.get("/")
|
43 |
async def root():
|
44 |
+
return {"message": "Ollama API proxy running on Hugging Face Spaces!"}
|