feat: solution for '8. Самописный поисковый агент на основе deep agents from scratch'

README.md

@@ -1,97 +1,43 @@
-# Deep Agent Search
+# DeepAgent
 
-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.
+DeepAgent is a minimal example of a deep learning based search agent.  
+It demonstrates how to combine a neural network with a simple search algorithm
+(Monte‑Carlo Tree Search style) without relying on external search libraries.
 
 ## Installation
 
 ```bash
-# 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
+python -m venv .venv
+source .venv/bin/activate   # On Windows use `.venv\\Scripts\\activate`
 
-# Install dependencies
-pip install -r requirements.txt
+# Install the package
+pip install .
 ```
 
-> **Note**: The project requires Python 3.8+ and PyTorch ≥ 1.8.0.
-
 ## Usage
 
-### Command‑line
-
-```bash
-python -m src.main "deep learning models"
-```
-
-The script prints the top 5 results with relevance scores.
-
-### Programmatic
-
 ```python
-from src.agent import SearchAgent
+from src.search_agent import SearchAgent, PolicyValueNet
 
-corpus = [
-    "Deep learning models can capture complex patterns in data.",
-    "Search engines index documents to provide relevant results.",
-    # ...
-]
+# Create a policy‑value network
+net = PolicyValueNet(input_dim=1, action_space=2)
 
-agent = SearchAgent(corpus)
-results = agent.search("deep learning", top_k=3)
+# Create the agent
+agent = SearchAgent(policy_value_net=net, max_depth=3)
 
-for res in results:
-    print(f"Doc {res.doc_id} (score={res.score:.4f}): {res.text}")
+# Run the agent on a simple state
+state = 0
+action = agent.act(state)
+print(f"Chosen action: {action}")
 ```
 
-## Testing
-
-Run the unit tests with:
+## Running Tests
 
 ```bash
-python -m unittest discover -s tests
+pytest
 ```
 
-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.
+MIT License – see the [LICENSE](LICENSE) file for details.