Add app

.gitignore

@@ -0,0 +1,8 @@
+api_calls/.env
+api_calls/apiEnv
+.env
+*env
+*venv
+__pycache__/
+*pdfChatEnv
+*checkpoint.ipynb

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY . .
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,17 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from utils import chat_completion_request
+
+app = FastAPI()
+
+class ChatRequest(BaseModel):
+    input_str: str
+
+@app.get("/")
+async def root():
+    return {"message": "PDF Chatbot API"}
+
+@app.post("/chat")
+async def submit_query(request: ChatRequest):
+    chat_response = chat_completion_request(request.input_str)
+    return {"role": "assistant", "content": chat_response}

request.py

@@ -0,0 +1,27 @@
+import requests
+import json
+
+url = 'http://127.0.0.1:8000/generate'
+headers = {
+    'accept': 'application/json',
+    'Content-Type': 'application/json',
+}
+data = {
+    "name": "Laptop",
+    "notes": "4GB RAM, 256 GB Disk"
+}
+
+response = requests.post(url, headers=headers, data=json.dumps(data))
+
+print(response.json())
+# Check the status code of the response
+# if response.status_code == 200:
+#     try:
+#         print(response.json())
+#     except json.decoder.JSONDecodeError:
+#         print("Response is not in JSON format.")
+# else:
+#     print(f"Error: Received status code {response.status_code}")
+#     print("Response text:", response.text)
+
+

requirements.txt

@@ -0,0 +1,5 @@
+openai
+fastapi
+uvicorn
+requests
+python-dotenv

utils.py

@@ -0,0 +1,47 @@
+from openai import OpenAI
+import os
+import time
+from dotenv import dotenv_values
+
+# Load model and API endpoint from environment variables
+config = dotenv_values(".env")
+model = config.get("MODEL")
+api_endpoint = config.get("API_ENDPOINT")
+
+openai_api_base = api_endpoint + '/v1'
+
+# Initialize the OpenAI client
+client = OpenAI(
+    api_key="EMPTY",  # Replace with your actual API key if required
+    base_url=openai_api_base,
+)
+
+def chat_completion_request(input):
+
+    messages = [
+        {"role": "user", "content": f"{input}"},
+    ]
+    # Create chat completions using the OpenAI client
+    chat_response = client.chat.completions.create(
+        model=model,
+        messages=messages,
+        temperature=0,
+        max_tokens=500
+    )
+
+    # Extract the completion text from the response
+    if chat_response.choices:
+        completion_text = chat_response.choices[0].message.content
+    else:
+        completion_text = None
+
+    return completion_text
+
+
+# # Test the function
+# messages = [
+#     {"role": "user", "content": "Write a long essay on the topic of spring."}
+# ]
+
+# chat_response = chat_completion_request_openai(messages, client)
+# messages.append({"role": "assistant", "content": chat_response})