Pushing agents and tools changes

5_agents_and_tools/1_agent_and_tools_basics.py

@@ -1,12 +1,11 @@
-# Import necessary libraries
-from dotenv import load_dotenv  # To load environment variables from a .env file
-from langchain import hub  # To pull prompt templates from the hub
-from langchain.agents import (  # To create and run agents
+from dotenv import load_dotenv
+from langchain import hub
+from langchain.agents import (
     AgentExecutor,
     create_react_agent,
 )
-from langchain_core.tools import Tool  # To define tools the agent can use
-from langchain_openai import ChatOpenAI  # To use the OpenAI model
+from langchain_core.tools import Tool
+from langchain_openai import ChatOpenAI
 
 # Load environment variables from .env file
 load_dotenv()
@@ -26,31 +25,34 @@ def get_current_time(*args, **kwargs):
     Tool(
         name="Time",  # Name of the tool
         func=get_current_time,  # Function that the tool will execute
-        description="Useful for when you need to know the current time",  # Description of the tool
+        # Description of the tool
+        description="Useful for when you need to know the current time",
     ),
 ]
 
 # Pull the prompt template from the hub
+# ReAct = Reason and Action
+# https://smith.langchain.com/hub/hwchase17/react
 prompt = hub.pull("hwchase17/react")
 
 # Initialize a ChatOpenAI model
 llm = ChatOpenAI(
     model="gpt-4o", temperature=0
-)  # Using GPT-4 model with deterministic output
+)
 
 # Create the ReAct agent using the create_react_agent function
 agent = create_react_agent(
-    llm=llm,  # Language model the agent will use to generate responses
-    tools=tools,  # List of tools the agent can use
-    prompt=prompt,  # Prompt template to guide the agent
-    stop_sequence=True,  # Add a stop sequence to prevent hallucinations
+    llm=llm,
+    tools=tools,
+    prompt=prompt,
+    stop_sequence=True,
 )
 
 # Create an agent executor from the agent and tools
 agent_executor = AgentExecutor.from_agent_and_tools(
-    agent=agent,  # Agent to execute
-    tools=tools,  # List of tools available to the agent
-    verbose=True,  # Enable detailed logging for debugging purposes
+    agent=agent,
+    tools=tools,
+    verbose=True,
 )
 
 # Run the agent with a test query

5_agents_and_tools/agent_deep_dive/1_agent_react_chat.py

@@ -24,7 +24,8 @@ def search_wikipedia(query):
     from wikipedia import summary
 
     try:
-        return summary(query, sentences=2)  # Limit to two sentences for brevity
+        # Limit to two sentences for brevity
+        return summary(query, sentences=2)
     except:
         return "I couldn't find any information on that."
 
@@ -47,11 +48,12 @@ def search_wikipedia(query):
 prompt = hub.pull("hwchase17/structured-chat-agent")
 
 # Initialize a ChatOpenAI model
-llm = ChatOpenAI()
+llm = ChatOpenAI(model="gpt-4o")
 
 # Create a structured Chat Agent with Conversation Buffer Memory
 # ConversationBufferMemory stores the conversation history, allowing the agent to maintain context across interactions
-memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+memory = ConversationBufferMemory(
+    memory_key="chat_history", return_messages=True)
 
 # create_structured_chat_agent initializes a chat agent designed to interact using a structured prompt and tools
 # It combines the language model (llm), tools, and prompt to create an interactive agent

5_agents_and_tools/agent_deep_dive/2_react_docstore.py → 5_agents_and_tools/agent_deep_dive/2_agent_react_docstore.py

@@ -22,7 +22,8 @@
 # Check if the Chroma vector store already exists
 if os.path.exists(persistent_directory):
     print("Loading existing vector store...")
-    db = Chroma(persist_directory=persistent_directory, embedding_function=None)
+    db = Chroma(persist_directory=persistent_directory,
+                embedding_function=None)
 else:
     raise FileNotFoundError(
         f"The directory {persistent_directory} does not exist. Please check the path."
@@ -32,7 +33,8 @@
 embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
 
 # Load the existing vector store with the embedding function
-db = Chroma(persist_directory=persistent_directory, embedding_function=embeddings)
+db = Chroma(persist_directory=persistent_directory,
+            embedding_function=embeddings)
 
 # Create a retriever for querying the vector store
 # `search_type` specifies the type of search (e.g., similarity)
@@ -98,7 +100,8 @@
 question_answer_chain = create_stuff_documents_chain(llm, qa_prompt)
 
 # Create a retrieval chain that combines the history-aware retriever and the question answering chain
-rag_chain = create_retrieval_chain(history_aware_retriever, question_answer_chain)
+rag_chain = create_retrieval_chain(
+    history_aware_retriever, question_answer_chain)
 
 
 # Set Up ReAct Agent with Document Store Retriever
@@ -123,15 +126,16 @@
 )
 
 agent_executor = AgentExecutor.from_agent_and_tools(
-    agent=agent, tools=tools, handle_parsing_errors=True
+    agent=agent, tools=tools, handle_parsing_errors=True, verbose=True,
 )
 
 chat_history = []
 while True:
     query = input("You: ")
     if query.lower() == "exit":
         break
-    response = agent_executor.invoke({"input": query, "chat_history": chat_history})
+    response = agent_executor.invoke(
+        {"input": query, "chat_history": chat_history})
     print(f"AI: {response['output']}")
 
     # Update history

5_agents_and_tools/tools_deep_dive/3_tool_base_tool.py

@@ -1,16 +1,22 @@
 # Docs: https://python.langchain.com/v0.1/docs/modules/tools/custom_tools/
 
 # Import necessary libraries
+import os
 from typing import Type
 
+from dotenv import load_dotenv
 from langchain import hub
 from langchain.agents import AgentExecutor, create_tool_calling_agent
 from langchain.pydantic_v1 import BaseModel, Field
 from langchain_core.tools import BaseTool
 from langchain_openai import ChatOpenAI
 
 
+load_dotenv()
+
 # Pydantic models for tool arguments
+
+
 class SimpleSearchInput(BaseModel):
     query: str = Field(description="should be a search query")
 
@@ -21,6 +27,8 @@ class MultiplyNumbersArgs(BaseModel):
 
 
 # Custom tool with only custom input
+
+
 class SimpleSearchTool(BaseTool):
     name = "simple_search"
     description = "useful for when you need to answer questions about current events"
@@ -31,7 +39,12 @@ def _run(
         query: str,
     ) -> str:
         """Use the tool."""
-        return f"Search results for: {query}"
+        from tavily import TavilyClient
+
+        api_key = os.getenv("TAVILY_API_KEY")
+        client = TavilyClient(api_key=api_key)
+        results = client.search(query=query)
+        return f"Search results for: {query}\n\n\n{results}\n"
 
 
 # Custom tool with custom input and output
@@ -78,7 +91,7 @@ def _run(
 )
 
 # Test the agent with sample queries
-response = agent_executor.invoke({"input": "Search for 'LangChain updates'"})
+response = agent_executor.invoke({"input": "Search for Apple Intelligence"})
 print("Response for 'Search for LangChain updates':", response)
 
 response = agent_executor.invoke({"input": "Multiply 10 and 20"})

pyproject.toml

@@ -21,6 +21,7 @@ bs4 = "^0.0.2"
 firecrawl-py = "^0.0.13"
 langchainhub = "^0.1.18"
 wikipedia = "^1.4.0"
+tavily-python = "^0.3.3"
 
 [tool.pyright]
 # https://github.com/microsoft/pyright/blob/main/docs/configuration.md