Tender Analysis

Django + React app for analyzing tender / RFP PDF documents with an LLM, based on a user-defined checklist of questions.

The flow right now:

1. Upload PDF (tender file)

2. Pick / create a checklist (list of questions)

3. Backend runs analysis over the PDF for each question and returns answers like:

   {
     "answers": [
       {
         "question": "What is the submission deadline for the tender?",
         "answer": "2027-12-31+01:00 23:59:00+01:00"
       },
       {
         "question": "Who is the contact person for the tender?",
         "answer": "BWI GmbH"
       }
     ]
   }
   
   

Example Results

setup and getting started

backend

1. Create and activate virtual environment

python -m venv venv
source venv/bin/activate      # macOS / Linux
# venv\Scripts\activate       # Windows

pip install -r requirements.txt

cd forgent_app
python manage.py makemigrations
python manage.py migrate
python manage.py runserver

frontend

cd frontend
npm install
npm run dev

todos:

• improve the LLM prompt
• conditin handling different from question handling, enforce LLM to handle conditions as binary only
• instruct LLM to prettify results e.g. in case of date time formats
• quality and correctness of results
• save anaylsis results in history to view later
• remove extra unused files

extra implementation

• UI to show from where in the document is answer retrieved
• switch to RAG setup for answering

error handling

• llm input context limit
• max upload size