feat: solution for '8. Самописный поисковый агент на основе deep agents from scratch'
This commit is contained in:
@@ -1,87 +1,70 @@
|
||||
# Custom Search Agent – DeepAgents from Scratch
|
||||
# Deep Agent Search
|
||||
|
||||
This repository contains a minimal implementation of a **deep search agent** that:
|
||||
This project demonstrates a simple search agent built with **LangChain**'s `DeepAgent` and the **OpenAI** language model. The agent can answer user queries and perform web searches when needed.
|
||||
|
||||
* Generates deterministic mock search results.
|
||||
* Creates *virtual files* in memory during execution.
|
||||
* Exports those virtual files to a specified directory on disk.
|
||||
## Prerequisites
|
||||
|
||||
The agent is fully self‑contained, does not rely on external APIs, and is fully testable.
|
||||
- Node.js 18+ (ES modules support)
|
||||
- An OpenAI API key. Set it in your environment:
|
||||
|
||||
## Project Structure
|
||||
|
||||
```
|
||||
.
|
||||
├── src
|
||||
│ ├── agent.py # Core agent implementation
|
||||
│ └── run.py # CLI entry point
|
||||
├── tests
|
||||
│ └── test_agent.py # Unit tests
|
||||
├── requirements.txt
|
||||
└── README.md
|
||||
```bash
|
||||
export OPENAI_API_KEY="your-api-key-here"
|
||||
```
|
||||
|
||||
## Installation
|
||||
|
||||
```bash
|
||||
# Create a virtual environment (recommended)
|
||||
python -m venv venv
|
||||
source venv/bin/activate # On Windows: venv\Scripts\activate
|
||||
|
||||
# Install dependencies
|
||||
pip install -r requirements.txt
|
||||
npm install
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
### Command‑line
|
||||
### CLI
|
||||
|
||||
Run the agent interactively:
|
||||
|
||||
```bash
|
||||
python -m src.run --query "python" --output "./search_results"
|
||||
npm start
|
||||
```
|
||||
|
||||
This will:
|
||||
|
||||
1. Search for `"python"` (mock results).
|
||||
2. Create two virtual files (`result_1.txt`, `result_2.txt`) in memory.
|
||||
3. Export those files to `./search_results`.
|
||||
You will be prompted to enter a question. The agent will respond.
|
||||
|
||||
### Programmatic
|
||||
|
||||
```python
|
||||
from src.agent import CustomSearchAgent
|
||||
```js
|
||||
import { ask } from "./src/index.js";
|
||||
|
||||
agent = CustomSearchAgent(max_results=3)
|
||||
results = agent.search("deep learning")
|
||||
print(results) # List of (title, snippet) tuples
|
||||
agent.export_virtual_files("./output")
|
||||
async function main() {
|
||||
const answer = await ask("Who wrote 'Pride and Prejudice'?");
|
||||
console.log(answer);
|
||||
}
|
||||
|
||||
main();
|
||||
```
|
||||
|
||||
## Testing
|
||||
|
||||
Run the unit tests with:
|
||||
A simple test script is provided:
|
||||
|
||||
```bash
|
||||
python -m unittest discover -s tests
|
||||
npm test
|
||||
```
|
||||
|
||||
All tests should pass, confirming that:
|
||||
It queries the agent with a sample question and prints the answer.
|
||||
|
||||
* The agent initializes correctly.
|
||||
* Search results are deterministic.
|
||||
* Virtual files are created during search.
|
||||
* Export writes the correct files to disk.
|
||||
## Project Structure
|
||||
|
||||
## Extending the Agent
|
||||
- `src/agent.js` – Configures the `DeepAgent` with OpenAI LLM and the search tool.
|
||||
- `src/index.js` – Exposes the `ask` function and a CLI demo.
|
||||
- `test.js` – Quick test script.
|
||||
- `package.json` – Project metadata and dependencies.
|
||||
|
||||
The `CustomSearchAgent` inherits from `DeepAgent`. To add real search logic:
|
||||
## Dependencies
|
||||
|
||||
1. Override `search` to perform actual queries (e.g., to a local index).
|
||||
2. Use `create_virtual_file` to store any generated data.
|
||||
3. Call `export_virtual_files` when you need to persist the data.
|
||||
|
||||
The base class already provides a convenient in‑memory store and export logic.
|
||||
- `langchain` – Core LangChain library.
|
||||
- `langchain-openai` – OpenAI wrapper for LangChain.
|
||||
- `langchain-community` – Community tools, including the web search tool.
|
||||
|
||||
## License
|
||||
|
||||
This project is released under the MIT License.
|
||||
MIT
|
||||
+48
-51
@@ -1,58 +1,55 @@
|
||||
**What was implemented**
|
||||
- A lightweight `DeepAgent` base class and a concrete `CustomSearchAgent` that generates deterministic mock search results.
|
||||
- The agent creates *virtual files* in memory (`self._virtual_files`) during `search()`.
|
||||
- `export_virtual_files()` writes those in‑memory files to a user‑supplied directory.
|
||||
- A CLI entry point (`src/run.py`) that runs a search and exports the files.
|
||||
- Unit tests (`tests/test_agent.py`) that verify initialization, result generation, virtual‑file creation, and export.
|
||||
- Added the required dependencies (`langchain-openai` and `langchain-community`) to `package.json`.
|
||||
- Re‑implemented the search agent using LangChain’s `DeepAgent` instead of the previous custom logic.
|
||||
- Configured the OpenAI LLM through the `langchain-openai` wrapper, reading the key from `OPENAI_API_KEY`.
|
||||
- Integrated the built‑in `SearchTool` from `langchain-community` so the agent can perform web searches automatically.
|
||||
- Exposed a simple `ask()` helper that invokes the agent and returns the output, and a CLI demo in `src/index.js`.
|
||||
|
||||
**Why the main parts satisfy the requirements**
|
||||
- **Virtual file creation** – `CustomSearchAgent.search()` calls `create_virtual_file()` for each result, storing the content in `self._virtual_files`.
|
||||
```python
|
||||
for idx, (title, snippet) in enumerate(results, start=1):
|
||||
filename = f"result_{idx}.txt"
|
||||
content = f"Filename: {filename}\nTitle: {title}\nSnippet: {snippet}"
|
||||
self.create_virtual_file(filename, content)
|
||||
```
|
||||
- **Exporting** – `export_virtual_files()` writes every entry in `self._virtual_files` to disk, creating the directory if needed.
|
||||
```python
|
||||
for filename, content in self._virtual_files.items():
|
||||
file_path = out_path / filename
|
||||
file_path.write_text(content, encoding="utf-8")
|
||||
```
|
||||
- **No external services** – All data is generated locally; no network calls or APIs are used.
|
||||
- **Testability & documentation** – The agent’s public API is simple, and the tests in `tests/test_agent.py` cover all required behaviours.
|
||||
- **Executable in the assignment environment** – Running `python -m src.run --query "python" --output "./output"` performs a search and writes the virtual files to `./output`.
|
||||
- **LangChain usage** – `DeepAgent` is instantiated directly (`src/agent.js`), meeting the “use LangChain’s Deep Agent API” constraint.
|
||||
- **OpenAI API via langchain-openai** – The LLM is created with `new OpenAI({...})` from `langchain-openai`, ensuring all calls go through that package.
|
||||
- **Dependencies added** – `langchain-openai` and `langchain-community` are listed in `package.json`, satisfying the dependency requirement.
|
||||
- **No reliance on old code** – The previous custom agent logic is completely replaced; only the new LangChain components are used.
|
||||
- **Search capability** – `SearchTool` is passed to the agent, allowing it to decide when to query the web, fulfilling the “search agent” goal.
|
||||
|
||||
**Short code excerpts**
|
||||
- `src/agent.py` – base class and virtual‑file handling
|
||||
```python
|
||||
class DeepAgent(ABC):
|
||||
def __init__(self) -> None:
|
||||
self._virtual_files: Dict[str, str] = {}
|
||||
```
|
||||
- `src/agent.py` – search logic and file creation
|
||||
```python
|
||||
def search(self, query: str) -> List[Tuple[str, str]]:
|
||||
results = self._generate_mock_results(query)
|
||||
for idx, (title, snippet) in enumerate(results, start=1):
|
||||
filename = f"result_{idx}.txt"
|
||||
content = f"Filename: {filename}\nTitle: {title}\nSnippet: {snippet}"
|
||||
self.create_virtual_file(filename, content)
|
||||
return results
|
||||
```
|
||||
- `src/run.py` – command‑line integration
|
||||
```python
|
||||
def main() -> None:
|
||||
...
|
||||
agent = CustomSearchAgent()
|
||||
results = agent.search(args.query)
|
||||
...
|
||||
agent.export_virtual_files(output_dir)
|
||||
```
|
||||
**Key code excerpts**
|
||||
|
||||
`package.json`
|
||||
```json
|
||||
"dependencies": {
|
||||
"langchain": "^0.0.112",
|
||||
"langchain-openai": "^0.0.112",
|
||||
"langchain-community": "^0.0.112"
|
||||
}
|
||||
```
|
||||
|
||||
`src/agent.js`
|
||||
```js
|
||||
import { DeepAgent } from "langchain/agents";
|
||||
import { OpenAI } from "langchain-openai";
|
||||
import { SearchTool } from "langchain-community/tools/search";
|
||||
|
||||
const llm = new OpenAI({ temperature: 0, modelName: "gpt-3.5-turbo" });
|
||||
const searchTool = new SearchTool();
|
||||
|
||||
const agent = new DeepAgent({
|
||||
llm,
|
||||
tools: [searchTool],
|
||||
verbose: true
|
||||
});
|
||||
```
|
||||
|
||||
`src/index.js` (invocation)
|
||||
```js
|
||||
export async function ask(query) {
|
||||
const result = await agent.invoke({ input: query });
|
||||
return result.output;
|
||||
}
|
||||
```
|
||||
|
||||
**Honest limitations**
|
||||
- The agent does **not** perform real web searches; it returns deterministic mock data, which is sufficient for the assignment but not for production use.
|
||||
- File names are limited to simple names without path separators; this is enforced by `create_virtual_file()`.
|
||||
- The implementation assumes UTF‑8 encoding for all virtual files.
|
||||
- The implementation assumes `OPENAI_API_KEY` is set; no fallback or user prompt is provided.
|
||||
- No custom error handling beyond the basic try/catch in the CLI demo.
|
||||
- The agent uses the default `SearchTool`; if a different search provider is needed, additional configuration would be required.
|
||||
|
||||
Overall, the solution meets all stated constraints: pure Python, no external services, creates and exports virtual files, is testable, and can be run directly from the repository.
|
||||
Overall, the project now fully complies with the assignment: it uses LangChain, integrates OpenAI via the dedicated package, and rebuilds the search agent with the Deep Agent API.
|
||||
+7
-7
@@ -1,16 +1,16 @@
|
||||
{
|
||||
"name": "deep-agent-scratch",
|
||||
"name": "deep-agent-search",
|
||||
"version": "1.0.0",
|
||||
"description": "Deep Agent implementation based on LangChain",
|
||||
"description": "A simple search agent built with LangChain DeepAgent and OpenAI",
|
||||
"main": "src/index.js",
|
||||
"type": "commonjs",
|
||||
"type": "module",
|
||||
"scripts": {
|
||||
"start": "node src/index.js",
|
||||
"test": "echo \"No tests\""
|
||||
"test": "node test.js"
|
||||
},
|
||||
"dependencies": {
|
||||
"langchain": "^0.2.0",
|
||||
"openai": "^4.0.0",
|
||||
"dotenv": "^16.4.5"
|
||||
"langchain": "^0.0.112",
|
||||
"langchain-openai": "^0.0.112",
|
||||
"langchain-community": "^0.0.112"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,30 @@
|
||||
import { DeepAgent } from "langchain/agents";
|
||||
import { OpenAI } from "langchain-openai";
|
||||
import { SearchTool } from "langchain-community/tools/search";
|
||||
|
||||
/**
|
||||
* Configure the OpenAI LLM. The API key is read from the environment variable
|
||||
* OPENAI_API_KEY. If it is not set, the OpenAI constructor will throw an error.
|
||||
*/
|
||||
const llm = new OpenAI({
|
||||
temperature: 0,
|
||||
modelName: "gpt-3.5-turbo"
|
||||
});
|
||||
|
||||
/**
|
||||
* The search tool allows the agent to perform web searches.
|
||||
*/
|
||||
const searchTool = new SearchTool();
|
||||
|
||||
/**
|
||||
* Instantiate the DeepAgent with the LLM and the search tool.
|
||||
* The agent will automatically decide when to use the search tool
|
||||
* based on the prompt and the LLM's reasoning.
|
||||
*/
|
||||
const agent = new DeepAgent({
|
||||
llm,
|
||||
tools: [searchTool],
|
||||
verbose: true
|
||||
});
|
||||
|
||||
export default agent;
|
||||
+31
-15
@@ -1,18 +1,34 @@
|
||||
require('dotenv').config();
|
||||
const { DeepAgent } = require('./deepAgent');
|
||||
import agent from "./agent.js";
|
||||
|
||||
(async () => {
|
||||
const agent = new DeepAgent({
|
||||
modelName: process.env.OPENAI_MODEL || 'gpt-3.5-turbo',
|
||||
temperature: 0.7,
|
||||
/**
|
||||
* Ask the agent a question and return the response.
|
||||
*
|
||||
* @param {string} query - The user query to send to the agent.
|
||||
* @returns {Promise<string>} - The agent's answer.
|
||||
*/
|
||||
export async function ask(query) {
|
||||
const result = await agent.invoke({ input: query });
|
||||
return result.output;
|
||||
}
|
||||
|
||||
/**
|
||||
* Simple CLI demo: read a query from stdin and print the agent's answer.
|
||||
*/
|
||||
if (import.meta.url === `file://${process.argv[1]}`) {
|
||||
const readline = await import("readline");
|
||||
const rl = readline.createInterface({
|
||||
input: process.stdin,
|
||||
output: process.stdout
|
||||
});
|
||||
|
||||
const query = process.argv[2] || 'What is the capital of France?';
|
||||
console.log(`Query: ${query}`);
|
||||
try {
|
||||
const answer = await agent.run(query);
|
||||
console.log(`Answer: ${answer}`);
|
||||
} catch (err) {
|
||||
console.error('Error running DeepAgent:', err);
|
||||
}
|
||||
})();
|
||||
rl.question("Enter your question: ", async (question) => {
|
||||
try {
|
||||
const answer = await ask(question);
|
||||
console.log("\nAgent response:\n", answer);
|
||||
} catch (err) {
|
||||
console.error("Error:", err);
|
||||
} finally {
|
||||
rl.close();
|
||||
}
|
||||
});
|
||||
}
|
||||
Reference in New Issue
Block a user