Create app.py

app.py

@@ -0,0 +1,70 @@
+from langchain.chat_models import ChatOpenAI
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.chains import LLMChain
+from langchain.prompts import PromptTemplate
+from langchain.schema.messages import HumanMessage, SystemMessage
+from langchain.schema.document import Document
+from langchain.vectorstores import FAISS
+from langchain.retrievers.multi_vector import MultiVectorRetriever
+import os
+import uuid
+import base64
+from fastapi import FastAPI, Request, Form, Response, File, UploadFile
+from fastapi.responses import HTMLResponse, JSONResponse
+from fastapi.templating import Jinja2Templates
+from fastapi.encoders import jsonable_encoder
+from fastapi.middleware.cors import CORSMiddleware
+import json
+from dotenv import load_dotenv
+load_dotenv()
+
+app = FastAPI()
+templates = Jinja2Templates(directory="templates")
+
+# Configure CORS
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  
+    allow_credentials=True,
+    allow_methods=["*"], 
+    allow_headers=["*"],
+)
+openai_api_key =  os.getenv("apikey") # Replace with your actual API key
+embeddings = OpenAIEmbeddings(openai_api_key=openai_api_key)
+
+
+db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
+
+# Define the prompt template
+prompt_template = """
+You are an expert in skin cancer, etc.
+Answer the question based only on the following context, which can include text, images, and tables:
+{context}
+Question: {question}
+Don't answer if you are not sure and decline to answer and say "Sorry, I don't have much information about it."
+Just return the helpful answer in as much detail as possible.
+Answer:
+"""
+
+qa_chain = LLMChain(llm=ChatOpenAI(model="gpt-4", openai_api_key = openai_api_key, max_tokens=1024),
+                    prompt=PromptTemplate.from_template(prompt_template))
+
+@app.get("/", response_class=HTMLResponse)
+async def index(request: Request):
+    return templates.TemplateResponse("index.html", {"request": request})
+
+@app.post("/get_answer")
+async def get_answer(question: str = Form(...)):
+    relevant_docs = db.similarity_search(question)
+    context = ""
+    relevant_images = []
+    for d in relevant_docs:
+        if d.metadata['type'] == 'text':
+            context += '[text]' + d.metadata['original_content']
+        elif d.metadata['type'] == 'table':
+            context += '[table]' + d.metadata['original_content']
+        elif d.metadata['type'] == 'image':
+            context += '[image]' + d.page_content
+            relevant_images.append(d.metadata['original_content'])
+    result = qa_chain.run({'context': context, 'question': question})
+    return JSONResponse({"relevant_images": relevant_images[0], "result": result})