Stop digging through test cases, requirement docs, and logs manually. Build your own QA Assistant that can answer your questions using natural language — powered by OpenAI and LangChain.

👋 Why This?

As QA engineers, we often deal with:

• Test cases in JSON or Jira/Xray
• BDD specs in .feature files
• Markdown requirements
• Logs in .txt and .html
• Allure reports and PDFs

…scattered across tools and folders.

The problem? Searching across all these files is slow, repetitive, and error-prone.

The solution? An AI-powered bot that understands all your test artifacts and answers your questions — like a real assistant.

🧠 What This Bot Does

It allows you to:

✅ Ask things like:

• “What are the test steps in TC-002?”
• “Summarize login test cases.”
• “What does the PDF say about edge cases?”

📁 It reads from:

• .json → structured test cases
• .feature → BDD scenarios
• .md, .txt, .html → requirements, logs, reports
• .pdf, .docx → spec files

🔎 Then it:

• Breaks the content into searchable chunks
• Creates semantic embeddings
• Stores it in a FAISS vector DB
• Uses OpenAI to generate responses in natural language

🛠️ Tech Stack

• LangChain — to connect everything
• OpenAI — to generate QA-friendly responses
• FAISS — to index content for fast semantic search
• Python — because we like speed and simplicity

🚀 How to Use It

1. 🔄 Clone the Repo

git clone https://github.com/aiqualitylab/AI-QA-Assistant-Bot.git
cd AI-QA-Assistant-Bot

2. 📦 Install Dependencies

pip install -r requirements.txt

3. 🔐 Set Your OpenAI Key

Create a .env file:

OPENAI_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

🔐 You can get your API key from: https://platform.openai.com/account/api-keys

4. 🚀 Run the Assistant

python bot.py

If it’s your first run, it will index the documents. After that, it reuses the saved index.

You’ll see:

🤖 QA Assistant Ready! Ask anything (type 'exit' to quit')

Start asking questions — and get instant, AI-powered answers.

💬 Example Use Cases

• 🔍 “What’s in TC-003?”
• 📝 “Summarize all test cases about checkout”
• 🐞 “What do the logs say about payment errors?”
• 📋 “Give me test steps for login with invalid credentials”

🛠️ Behind the Scenes

Under the hood:

• Document loaders handle multiple formats using langchain_community.loaders
• Recursive chunking splits large text into overlapping pieces
• OpenAIEmbeddings converts chunks into vectors
• FAISS indexes and searches them semantically
• RetrievalQA runs your question against the best-matching documents

💡 Why It Matters

QA engineers shouldn’t have to:

• Ctrl+F through hundreds of lines
• Switch between Jira, Confluence, Allure, Git
• Manually correlate logs and test cases

This assistant lets you work smarter, not harder.

🧪 Demo Available

Try it out locally on your own test artifacts. Clone the repo 👉 https://github.com/aiqualitylab/AI-QA-Assistant-Bot

Have questions or suggestions? Drop a comment below or open an issue on GitHub!

git clone https://github.com/aiqualitylab/AI-QA-Assistant-Bot
cd qa-bot

pip install -r requirements.txt