AI Lawyer - Everyday Legal Help (India)

AI Lawyer - Everyday Legal Help (India)

A chat assistant that helps people in India with everyday legal problems such as unpaid salary, deposits and consumer refunds. It builds your case, answers from a legal knowledge base and drafts notices. Not legal advice.

Made by rolmaxx on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: This Space is a conversational assistant for everyday legal problems in India. It turns a messy story into structured facts, answers from a knowledge base of Indian laws, and drafts a legal notice or consumer complaint. It was built as a hiring assignment and is clear that it is not a lawyer.

Who it suits: It suits ordinary people facing unpaid pay, a withheld deposit or a faulty product, and developers who want to study a small retrieval-based legal assistant. It also suits students who want to practice a dispute.

Industry | Who uses it | How they use it | Example
Employment | Employees | Understand an unpaid salary or final settlement claim | Describe a missed settlement and get a structured summary
Housing | Tenants | Prepare for a security deposit dispute | Ask what a deposit claim needs
Consumer rights | Shoppers | Seek a refund for a defective product | Get a draft consumer complaint
Education | Law students | Practice arguing a case in role-play mode | Argue against the other side's likely points

You can skip it if your matter is criminal, in court or high in value, since the tool says those need a real advocate.

Where to use it:

• A web browser: open the Space page on Hugging Face
• Windows, macOS or Linux: run a copy with Python
• Your own provider key: the app can use Gemini, OpenAI or Groq models

Use case | Who | What they get back
Build a case | Anyone with a dispute | Facts sorted into a structured case
Get a grounded answer | Employees and shoppers | An answer based on the retrieved legal text
Draft a document | Consumers and tenants | A draft legal notice or consumer complaint
Practice the argument | Students | A role-play of the other side

How to set it up: The online page needs nothing. A local copy needs Python, packages and an API key.

• A web browser for the online demo
• Python for a local copy
• The packages listed in requirements.txt
• An API key for the model provider you choose, set as an environment variable
• The settings listed in the example env file

1. To use it online, open the Space page on Hugging Face.
2. To run a copy, install the Hugging Face hub package.
3. Download the Space into a local folder.
4. Move into the folder and install Gradio 4.44.1 and the listed packages.
5. Set your API key and start the app.

pip install -U huggingface_hub
hf download rolmaxx/AI-Lawyer --repo-type space --local-dir AI-Lawyer
cd AI-Lawyer
pip install gradio==4.44.1
pip install -r requirements.txt
python app.py

The README's own local run sets the key first.

export GEMINI_API_KEY="your-key-here"
pip install -r requirements.txt
python app.py

To switch provider, change one line in config.py and set the matching key.

MODEL_PROVIDER = "gemini"   # or "openai" | "groq"

How to use it: Open the chat and describe your problem in plain words. The assistant organizes the facts, asks for what is missing and answers from its knowledge base. You can ask it to draft a legal notice or consumer complaint, or switch to role-play to practice arguing with the other side.

Tool | What it does
Case building | Turns a messy story into structured facts
Grounded answers | Answers from a retrieval knowledge base of Indian laws
Document drafts | Writes a legal notice or consumer complaint draft
Role-play mode | Lets you practice arguing with the other side

Example: You write that your employer has not paid your final settlement after you resigned. The assistant sorts out the dates and amounts, answers from the labour-law material it holds and offers a draft legal notice. For high-risk cases, it points you to a real lawyer or free legal aid.

For newcomers and experts: If you are new to this, treat it as a way to get your facts in order before you talk to anyone. Read the draft carefully and check it with a qualified person.

If you know the field, the app uses retrieval over a local index with strict prompts against invented law. If the retrieved text lacks an answer, it says so instead of making up sections or cases. The Space names Llama 3.3 70B, Llama 3 8B and a Qwen3 embedding model, and the code lets you swap providers in one line.

You describe your problem
A case object holds the structured facts
The knowledge base is searched
The model answers from what was found
You can draft a notice or role-play

Good to know: Coverage differs by area, so check where your problem sits.

Title: Knowledge base coverage
Area | Coverage
Salary and wages | Strong, with the wage and industrial relations codes
Consumer disputes | Strong, with the 2019 consumer protection act
Limitation periods | Useful for working out deadlines
Rent | Weak, mostly references with a note that rent law is a state matter

• License: MIT
• Cost to run: an API key from the model provider you choose, such as Gemini, OpenAI or Groq
• Data it reaches: what you type about your case, sent to the model provider, plus its local knowledge files
• Not for: replacing a lawyer, since crime cases, trials and large claims need a real advocate or free legal aid

On Hugging Face, 13 November 2026

• Likes: 2
• Built with: gradio
• License: mit

Links

• Space: https://huggingface.co/spaces/rolmaxx/AI-Lawyer
• Files: https://huggingface.co/spaces/rolmaxx/AI-Lawyer/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.