Update app/llm.py
Browse files- app/llm.py +3 -2
app/llm.py
CHANGED
@@ -8,6 +8,7 @@ import llama_cpp
|
|
8 |
import llama_cpp.llama_tokenizer
|
9 |
from pydantic import BaseModel
|
10 |
from fastapi import APIRouter
|
|
|
11 |
|
12 |
class GenModel(BaseModel):
|
13 |
question: str
|
@@ -71,7 +72,7 @@ def health():
|
|
71 |
|
72 |
# Chat Completion API
|
73 |
@llm_router.post("/chat/", tags=["llm"])
|
74 |
-
async def chat(chatm:ChatModel):
|
75 |
try:
|
76 |
st = time()
|
77 |
output = llm_chat.create_chat_completion(
|
@@ -94,7 +95,7 @@ async def chat(chatm:ChatModel):
|
|
94 |
|
95 |
# Chat Completion API
|
96 |
@llm_router.post("/generate", tags=["llm"])
|
97 |
-
async def generate(gen:GenModel):
|
98 |
gen.system = "You are an helpful medical AI assistant."
|
99 |
gen.temperature = 0.5
|
100 |
gen.seed = 42
|
|
|
8 |
import llama_cpp.llama_tokenizer
|
9 |
from pydantic import BaseModel
|
10 |
from fastapi import APIRouter
|
11 |
+
from users import current_active_user
|
12 |
|
13 |
class GenModel(BaseModel):
|
14 |
question: str
|
|
|
72 |
|
73 |
# Chat Completion API
|
74 |
@llm_router.post("/chat/", tags=["llm"])
|
75 |
+
async def chat(chatm:ChatModel, user: User = Depends(current_active_user)):
|
76 |
try:
|
77 |
st = time()
|
78 |
output = llm_chat.create_chat_completion(
|
|
|
95 |
|
96 |
# Chat Completion API
|
97 |
@llm_router.post("/generate", tags=["llm"])
|
98 |
+
async def generate(gen:GenModel, user: User = Depends(current_active_user)):
|
99 |
gen.system = "You are an helpful medical AI assistant."
|
100 |
gen.temperature = 0.5
|
101 |
gen.seed = 42
|