update codebase

api/app/ai/chatbot.py

@@ -0,0 +1,30 @@
+import os
+from openai import OpenAI
+import requests
+
+API_TOKEN = os.getenv("HUGGINGFACE_API_TOKEN")
+
+API_URL = "https://api-inference.huggingface.co/models/meta-llama/Llama-2-7b-chat-hf"
+headers = {"Authorization": f"Bearer {API_TOKEN}"}
+
+client = OpenAI(
+    organization=os.getenv("OPENAI_ORG_ID"), api_key=os.getenv("OPENAI_API_KEY")
+)
+
+
+def gpt_chatbot(user_request: str):
+    completion = client.chat.completions.create(
+        model="gpt-4o-mini",
+        messages=[
+            {"role": "system", "content": "You are a helpful assistant."},
+            {"role": "user", "content": user_request},
+        ],
+    )
+
+    return completion.choices[0].message.content    
+
+
+def llama_chatbot(user_request: str):
+    response = requests.post(API_URL, headers=headers, json={"inputs": user_request})
+
+    return response.json()[0]["generated_text"]

api/app/main.py

@@ -0,0 +1,56 @@
+from fastapi import FastAPI, Form
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.staticfiles import StaticFiles
+from fastapi.responses import HTMLResponse
+from .ai.chatbot import gpt_chatbot, llama_chatbot
+
+isProduction = False
+
+origins = ["*"]
+
+if isProduction:
+    app = FastAPI(
+        title="LLM API Endpoints",
+        docs_url=None,  # Disable docs (Swagger UI)
+        redoc_url=None,  # Disable redoc
+    )
+    #app.mount("/static", StaticFiles(directory="static"), name="static")
+else:
+    app = FastAPI(title="LLM API Endpoints")
+    #app.mount("/static", StaticFiles(directory="static"), name="static")
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=origins,
+    allow_credentials=True,
+    allow_methods=["POST", "GET", "PUT", "DELETE"],
+    allow_headers=["*"],
+)
+
+
+# Create a homepage route
+@app.get("/")
+async def index():
+    return {"server ok": True}
+
+
+@app.post("/api/chat/gpt4o/mini", tags=["OpenAI GPT-4o mini"])
+async def gpt_chat(user_request: str = Form(...)):
+    """
+    Chat with LLM Backend - GPT-4o mini
+    """
+    # Get the text content in the user request
+    result = gpt_chatbot(user_request=user_request)
+
+    return {"result": result}
+
+
+@app.post("/api/chat/llama", tags=["Llama 2 7B Chat"])
+async def llama_chat(user_request: str = Form(...)):
+    """
+    Chat with LLM Backend - Llama 2 7b Chat
+    """
+    # Get the text content in the user request
+    result = llama_chatbot(user_request=user_request)
+
+    return {"result": result}

api/test_main.py

@@ -0,0 +1,19 @@
+from fastapi.testclient import TestClient
+from app.main import app
+
+client = TestClient(app)
+
+def test_read_main():
+    response = client.get("/")
+    assert response.status_code == 200
+    assert response.json() == {"server ok": True}
+    
+def test_gpt_chat():
+    response = client.post("/api/chat/gpt3", data={"user_request": "What is OpenAI?"})
+    assert response.status_code == 200
+    assert response.json()["result"] != ""
+    
+def test_llama_chat():
+    response = client.post("/api/chat/llama", data={"user_request": "What is LLM?"})
+    assert response.status_code == 200
+    assert response.json()["result"] != ""