Deep Agent Search

A lightweight search agent that uses a simple neural embedding model to retrieve documents from a corpus. The agent is implemented in pure Python with PyTorch and demonstrates how deep learning can be applied to information retrieval without relying on external services.

Author: Artur Kuzakhmetov
Course: DeepAgents – Perplexity (Lecture 09.04.2026)
Deadline: 31.08.2026

Features

• Custom neural encoder – word embeddings trained from scratch.
• Cosine similarity ranking – fast and interpretable.
• Command‑line interface – run searches directly from the terminal.
• Unit tests – ensure correctness of embeddings, similarity, and ranking.
• No external services – everything runs locally on CPU or GPU.

Installation

# Clone the repository
git clone https://git.brojs.ru/kuzakhmetovartur/8.-samopisnyy-poiskovyy-agent-na-osnove-<repo>.git
cd 8.-samopisnyy-poiskovyy-agent-na-osnove-<repo>

# Create a virtual environment (recommended)
python3 -m venv venv
source venv/bin/activate

# Install dependencies
pip install -r requirements.txt

Note

: The project requires Python 3.8+ and PyTorch ≥ 1.8.0.

Usage

Command‑line

python -m src.main "deep learning models"

The script prints the top 5 results with relevance scores.

Programmatic

from src.agent import SearchAgent

corpus = [
    "Deep learning models can capture complex patterns in data.",
    "Search engines index documents to provide relevant results.",
    # ...
]

agent = SearchAgent(corpus)
results = agent.search("deep learning", top_k=3)

for res in results:
    print(f"Doc {res.doc_id} (score={res.score:.4f}): {res.text}")

Testing

Run the unit tests with:

python -m unittest discover -s tests

All tests should pass:

$ python -m unittest discover -s tests
....
----------------------------------------------------------------------
Ran 6 tests in 0.12s

OK

Extending the Agent

• Training – call agent.train() to fine‑tune embeddings on the corpus.
• Custom tokenizer – replace _tokenize in src/agent.py with a more advanced tokenizer.
• Different similarity – swap cosine_similarity with dot‑product or Euclidean distance.

License

This project is released under the MIT License.

---

Academic Integrity
All code is written from scratch by the student. No external services or pre‑trained models are used. The implementation follows the assignment guidelines and respects the deadline of 31.08.2026.