Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -106,7 +106,7 @@ def generate_chunked_response(prompt, model, max_tokens=1000, num_calls=3, tempe
|
|
106 |
f"https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/@cf/meta/llama-3.1-8b-instruct",
|
107 |
headers={"Authorization": f"Bearer {API_TOKEN}"},
|
108 |
json={
|
109 |
-
"stream":
|
110 |
"messages": [
|
111 |
{"role": "system", "content": "You are a friendly assistant"},
|
112 |
{"role": "user", "content": prompt}
|
@@ -114,7 +114,7 @@ def generate_chunked_response(prompt, model, max_tokens=1000, num_calls=3, tempe
|
|
114 |
"max_tokens": max_tokens,
|
115 |
"temperature": temperature
|
116 |
},
|
117 |
-
stream=
|
118 |
)
|
119 |
|
120 |
for line in response.iter_lines():
|
|
|
106 |
f"https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/@cf/meta/llama-3.1-8b-instruct",
|
107 |
headers={"Authorization": f"Bearer {API_TOKEN}"},
|
108 |
json={
|
109 |
+
"stream": true,
|
110 |
"messages": [
|
111 |
{"role": "system", "content": "You are a friendly assistant"},
|
112 |
{"role": "user", "content": prompt}
|
|
|
114 |
"max_tokens": max_tokens,
|
115 |
"temperature": temperature
|
116 |
},
|
117 |
+
stream=true
|
118 |
)
|
119 |
|
120 |
for line in response.iter_lines():
|