main.py

import os
from dotenv import load_dotenv
from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
from fastapi import File, UploadFile
from kor.extraction import create_extraction_chain
from langchain_openai import ChatOpenAI
from langchain_community.document_loaders import PyPDFLoader
import json
from scrape_parse_combine import scrape_parse_combine
import schema_quick_analysis
import schema_indepth_analysis


def configure(): 
    load_dotenv()

configure()
app = FastAPI()
openai_key = os.getenv("openai_key")

llm = ChatOpenAI(
    model_name="gpt-4o",
    temperature=0,
    max_tokens=2000,
    openai_api_key=openai_key
)

app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)


@app.get("/ping")
async def ping():
    return "Hello, I am alive"

# Helper function. Upload a pdf_file and save it
def upload(file):
    file_name = ""
    try:
        contents = file.file.read()
        with open(file.filename, 'wb') as f:
            f.write(contents)
    except Exception:
        return {"message": "There was an error uploading the file"}
    finally:
        file.file.close()

    file_name += file.filename
    pdf_path = f"./{file_name}"
    return pdf_path


@app.post("/quick_analysis")
async def quick_analysis(file: UploadFile = File(...)):
    state_dict = {}
    pdf_path = upload(file)

    loader = PyPDFLoader(pdf_path)
    pages = loader.load_and_split()

    doc_info = ""
    for page in range(len(pages)):
        doc_info += pages[page].page_content

    state_dict["pdf_doc"] = doc_info

    chain = create_extraction_chain(
        llm, schema_quick_analysis.schema, encoder_or_encoder_class="json")
    doc_output = chain.invoke(doc_info)["data"]

    state_dict["website_url"] = doc_output["startup_info"]["website_url"]

    # Write JSON string to a file
    with open('pdf_data.json', 'w') as json_file:
        json.dump(state_dict, json_file)

    return {"quick_analysis": doc_output}



@app.post("/indepth_analysis")
async def indepth_analysis():

    scrape_parse_combine(openai_key)

    # Load JSON data from a file
    with open('pdf_data.json', 'r') as json_file:
        data = json.load(json_file)

    result = data["startup_info"]

    chain = create_extraction_chain(
        llm, schema_indepth_analysis.schema, encoder_or_encoder_class="json")

    doc_output = chain.invoke(result)["data"]

    return {"indepth_analysis": doc_output["startup_info"]}