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

README.md

@@ -1,31 +1,57 @@
-# 8. Самописный поисковый агент на основе deep agents from scratch
+# Deep Agent – Search, Virtual Files, Export
 
-Главная
+This project implements a **Deep Agent** following the *Deep Agents from Scratch* template.  
-Мои задания
+The agent can:
-8. Самописный поисковый агент на основе deep agents from scratch
-5Д
-EN
-8. Самописный поисковый агент на основе deep agents from scratch
-Зачёт
-Версия 1
-Дедлайн сдачи: 31.08.2026
 
-В работе
+1. Search the web for information (using DuckDuckGo).
+2. Create virtual files in memory.
+3. Export those virtual files to the real filesystem.
 
-Редактирование ответа
+## Prerequisites
 
-Заполните ответ и отправьте работу на проверку преподавателю.
+- Python 3.10+
+- An OpenAI API key (set as `OPENAI_API_KEY` environment variable).
 
-Тип ответа
+## Installation
-Текст
-Ссылка
-Файлы
-Текст ответа
-Прикреплённые файлы
-Загрузить файл
-Отправить на проверку
-Отменить
 
-Задание
+```bash
+# Clone the repository
+git clone https://github.com/yourusername/deep-agent-demo.git
+cd deep-agent-demo
 
-Необходимо написать deepagent на основе курса deep agents from scratch пример такого аг
+# Create a virtual environment (optional but recommended)
+python -m venv venv
+source venv/bin/activate   # On Windows: venv\Scripts\activate
+
+# Install dependencies
+pip install -r requirements.txt
+```
+
+## Usage
+
+```bash
+python src/main.py \
+  --prompt "Write a short report on the history of the Eiffel Tower" \
+  --output-dir ./exported_files \
+  --verbose
+```
+
+- `--prompt` – The user query for the agent.
+- `--output-dir` – Directory where virtual files will be exported.
+- `--verbose` – Show detailed logs of tool calls.
+
+After running, the agent will print the final answer and export any created virtual files to the specified directory.
+
+## Project Structure
+
+```
+deep-agent-demo/
+├── src/
+│   └── main.py          # Main script with Deep Agent implementation
+├── requirements.txt     # Python dependencies
+└── README.md            # This file
+```
+
+## License
+
+MIT License

requirements.txt

@@ -1,3 +1,4 @@
-langchain
+langchain==0.1.0
 openai
-duckduckgo-search
+requests
+beautifulsoup4

src/main.py

@@ -1,76 +1,288 @@
-import os
+#!/usr/bin/env python3
-import sys
+"""
-from pathlib import Path
+Deep Agent implementation based on the Deep Agents from Scratch template.
-
+The agent can search the web, create virtual files, and export them to the real filesystem.
-# Ensure the virtual_files package is importable
-sys.path.append(str(Path(__file__).resolve().parent))
-
-from langchain import OpenAI
-from langchain.agents import initialize_agent
-from langchain.tools import DuckDuckGoSearchRun, Tool
-from src.virtual_files import VirtualFileSystem
-
-def main():
-    # Initialize the virtual file system
-    vfs = VirtualFileSystem()
-
-    # Define a custom tool to write to the virtual file system
-    def write_file_tool(input_str: str) -> str:
-        """
-        Expected input format: filename|content
-        Example: python_history.txt|Python was created by Guido van Rossum...
-        """
-        if "|" not in input_str:
-            return "Error: Input must be in the format 'filename|content'."
-        filename, content = input_str.split("|", 1)
-        filename = filename.strip()
-        content = content.strip()
-        if not filename:
-            return "Error: Filename cannot be empty."
-        vfs.write_file(filename, content)
-        return f"File '{filename}' written successfully."
-
-    write_tool = Tool(
-        name="WriteFile",
-        func=write_file_tool,
-        description=(
-            "Writes content to a virtual file. "
-            "Use the format: filename|content. "
-            "The file will be stored in the virtual file system and exported at the end."
-        ),
-    )
-
-    # Search tool
-    search_tool = DuckDuckGoSearchRun()
-
-    # LLM configuration
-    llm = OpenAI(temperature=0)
-
-    # Initialize the agent with the tools
-    agent_executor = initialize_agent(
-        tools=[search_tool, write_tool],
-        llm=llm,
-        agent="zero-shot-react-description",
-        verbose=True,
-    )
-
-    # Example task: gather information about Python programming language
-    task = """
-You are a research assistant. Your task is to gather information about the Python programming language, including its history, key features, and popular libraries. 
-Create a virtual file named 'python_history.txt' containing the history, a file named 'python_features.txt' containing key features, and a file named 'python_libraries.txt' containing a list of popular libraries. 
-Use the web search tool to find reliable information. After gathering the data, write each section to the corresponding virtual file using the WriteFile tool. 
-Finally, return a summary of what you have done.
 """
 
-    # Run the agent
+import os
-    result = agent_executor.run(task)
+import re
-    print("\nAgent finished. Result:")
+import ast
-    print(result)
+import argparse
+import requests
+from bs4 import BeautifulSoup
+
+from langchain.llms import OpenAI
+from langchain.tools import Tool
+from langchain.prompts import PromptTemplate
+from langchain.chains import LLMChain
+from langchain.memory import ConversationBufferMemory
+from langchain.agents import BaseAgent
+
+# --------------------------------------------------------------------------- #
+# Virtual File System
+# --------------------------------------------------------------------------- #
+class VirtualFileSystem:
+    """In-memory virtual file system."""
+
+    def __init__(self):
+        self.files = {}
+
+    def write_file(self, filename: str, content: str):
+        self.files[filename] = content
+
+    def read_file(self, filename: str) -> str:
+        return self.files.get(filename, "")
+
+    def export_to_disk(self, directory: str):
+        os.makedirs(directory, exist_ok=True)
+        for filename, content in self.files.items():
+            path = os.path.join(directory, filename)
+            with open(path, "w", encoding="utf-8") as f:
+                f.write(content)
+
+
+# --------------------------------------------------------------------------- #
+# Tools
+# --------------------------------------------------------------------------- #
+class SearchTool(Tool):
+    """Search the web using DuckDuckGo."""
+
+    name = "Search"
+    description = (
+        "Search the web for information. Input: query string. Output: search results as text."
+    )
+
+    def __init__(self):
+        super().__init__(name=self.name, description=self.description, func=self.run)
+
+    def run(self, query: str) -> str:
+        url = "https://duckduckgo.com/html/"
+        params = {"q": query}
+        try:
+            response = requests.get(url, params=params, timeout=10)
+            response.raise_for_status()
+        except Exception as e:
+            return f"Error during search: {e}"
+
+        soup = BeautifulSoup(response.text, "html.parser")
+        results = []
+        for a in soup.select("a.result__a"):
+            title = a.get_text()
+            href = a.get("href")
+            results.append(f"{title}\n{href}")
+        if not results:
+            return "No results found."
+        return "\n\n".join(results[:5])  # Return top 5 results
+
+
+class VirtualFileSystemTool(Tool):
+    """Create a virtual file with given filename and content."""
+
+    name = "CreateFile"
+    description = (
+        "Create a virtual file with given filename and content. "
+        "Input format: filename|content"
+    )
+
+    def __init__(self, vfs: VirtualFileSystem):
+        self.vfs = vfs
+        super().__init__(name=self.name, description=self.description, func=self.run)
+
+    def run(self, args: str) -> str:
+        parts = args.split("|", 1)
+        if len(parts) != 2:
+            return "Error: expected format 'filename|content'"
+        filename, content = parts
+        filename = filename.strip()
+        content = content.strip()
+        self.vfs.write_file(filename, content)
+        return f"File '{filename}' created."
+
+
+class ExportTool(Tool):
+    """Export all virtual files to the specified directory."""
+
+    name = "ExportFiles"
+    description = "Export all virtual files to the specified directory. Input: directory path"
+
+    def __init__(self, vfs: VirtualFileSystem):
+        self.vfs = vfs
+        super().__init__(name=self.name, description=self.description, func=self.run)
+
+    def run(self, directory: str) -> str:
+        directory = directory.strip()
+        self.vfs.export_to_disk(directory)
+        return f"Exported {len(self.vfs.files)} files to '{directory}'."
+
+
+# --------------------------------------------------------------------------- #
+# Deep Agent
+# --------------------------------------------------------------------------- #
+class DeepAgent(BaseAgent):
+    """Deep Agent following the Deep Agents from Scratch template."""
+
+    def __init__(self, llm, tools, memory, verbose=False):
+        super().__init__()
+        self.llm = llm
+        self.tools = tools
+        self.memory = memory
+        self.verbose = verbose
+
+        self.tool_names = [tool.name for tool in tools]
+        self.tool_map = {tool.name: tool for tool in tools}
+
+        # Prompt templates
+        self.plan_prompt = PromptTemplate(
+            input_variables=["input", "agent_scratchpad"],
+            template=(
+                "You are a helpful assistant. Your task is to answer the user query: {input}\n"
+                "You have access to the following tools: {tool_names}\n"
+                "You can use the tools to gather information.\n"
+                "Plan your steps. Each step should be a single tool call in the format: {tool_name}({arguments})\n"
+                "If you have enough information, provide the final answer.\n"
+                "Your plan:\n{agent_scratchpad}"
+            ),
+        )
+
+        self.tool_prompt = PromptTemplate(
+            input_variables=["tool_input", "agent_scratchpad"],
+            template=(
+                "You are a tool. The user wants: {tool_input}\n"
+                "You have the following context: {agent_scratchpad}\n"
+                "You should produce the tool output.\n"
+                "Tool output:"
+            ),
+        )
+
+        self.final_prompt = PromptTemplate(
+            input_variables=["agent_scratchpad"],
+            template=(
+                "You are a helpful assistant. Based on the previous steps, provide the final answer.\n"
+                "Answer:\n{agent_scratchpad}"
+            ),
+        )
+
+        self.plan_chain = LLMChain(llm=self.llm, prompt=self.plan_prompt)
+        self.tool_chain = LLMChain(llm=self.llm, prompt=self.tool_prompt)
+        self.final_chain = LLMChain(llm=self.llm, prompt=self.final_prompt)
+
+    def _get_scratchpad(self) -> str:
+        """Return the conversation history as a string."""
+        history = self.memory.load_memory_variables({})["history"]
+        if isinstance(history, list):
+            return "\n".join([msg.content if hasattr(msg, "content") else str(msg) for msg in history])
+        return str(history)
+
+    def plan(self, input_text: str) -> str:
+        scratchpad = self._get_scratchpad()
+        plan = self.plan_chain.run(
+            input=input_text,
+            agent_scratchpad=scratchpad,
+            tool_names=", ".join(self.tool_names),
+        )
+        return plan
+
+    def parse_plan(self, plan_text: str) -> list:
+        """Parse the plan into individual steps."""
+        lines = [line.strip() for line in plan_text.splitlines() if line.strip()]
+        return lines
+
+    def parse_step(self, step_text: str) -> tuple:
+        """Parse a single step into tool name and arguments."""
+        match = re.match(r"(\w+)\((.*)\)", step_text)
+        if not match:
+            raise ValueError(f"Invalid step format: {step_text}")
+        tool_name = match.group(1)
+        args_str = match.group(2).strip()
+        # Try to parse arguments as a tuple
+        try:
+            args_tuple = ast.literal_eval(f"({args_str},)")
+        except Exception:
+            args_tuple = (args_str,)
+        return tool_name, args_tuple
+
+    def run(self, input_text: str) -> str:
+        """Run the agent on the given input."""
+        self.memory.save_context({"input": input_text}, {})
+        plan = self.plan(input_text)
+        if self.verbose:
+            print("\n=== PLAN ===")
+            print(plan)
+            print("============\n")
+
+        steps = self.parse_plan(plan)
+        for step in steps:
+            tool_name, args_tuple = self.parse_step(step)
+            if tool_name not in self.tool_map:
+                raise ValueError(f"Unknown tool: {tool_name}")
+            tool = self.tool_map[tool_name]
+            # Use the first argument as the tool input
+            tool_input = args_tuple[0] if args_tuple else ""
+            if self.verbose:
+                print(f"\n=== TOOL CALL: {tool_name} ===")
+                print(f"Input: {tool_input}")
+            tool_output = tool.run(tool_input)
+            if self.verbose:
+                print(f"Output: {tool_output}\n")
+            self.memory.save_context({"tool_output": tool_output}, {})
+
+        final_answer = self.final_chain.run(agent_scratchpad=self._get_scratchpad())
+        return final_answer
+
+
+# --------------------------------------------------------------------------- #
+# Main
+# --------------------------------------------------------------------------- #
+def main():
+    parser = argparse.ArgumentParser(description="Deep Agent Demo")
+    parser.add_argument(
+        "--prompt",
+        type=str,
+        required=True,
+        help="The user query for the agent to answer.",
+    )
+    parser.add_argument(
+        "--output-dir",
+        type=str,
+        default="output_files",
+        help="Directory to export virtual files.",
+    )
+    parser.add_argument(
+        "--verbose",
+        action="store_true",
+        help="Print detailed logs.",
+    )
+    args = parser.parse_args()
+
+    # Ensure OpenAI API key is set
+    if "OPENAI_API_KEY" not in os.environ:
+        raise RuntimeError("Please set the OPENAI_API_KEY environment variable.")
+
+    # Initialize components
+    llm = OpenAI(temperature=0, model_name="gpt-3.5-turbo")
+    vfs = VirtualFileSystem()
+    tools = [
+        SearchTool(),
+        VirtualFileSystemTool(vfs),
+        ExportTool(vfs),
+    ]
+    memory = ConversationBufferMemory(memory_key="history", return_messages=True)
+
+    agent = DeepAgent(llm=llm, tools=tools, memory=memory, verbose=args.verbose)
+
+    # Run the agent
+    print("\n=== RUNNING AGENT ===")
+    final_answer = agent.run(args.prompt)
+    print("\n=== FINAL ANSWER ===")
+    print(final_answer)
+
+    # Export files (in case the agent didn't call ExportFiles)
+    if not any(tool.name == "ExportFiles" for tool in tools):
+        export_tool = ExportTool(vfs)
+        export_output = export_tool.run(args.output_dir)
+        print("\n=== EXPORT OUTPUT ===")
+        print(export_output)
 
-    # Export virtual files to disk
-    output_dir = Path(__file__).resolve().parent / "output_files"
-    vfs.export_to_disk(str(output_dir))
-    print(f"\nVirtual files exported to {output_dir}")
 
 if __name__ == "__main__":
     main()