Gratulacje!

Agenty text-to-query z MongoDB i LangGraph

Apoorva Joshi

Senior AI/ML Developer Advocate, MongoDB

Gotowy produkt!

agentic10.jpg

Agenty text-to-query z MongoDB i LangGraph

Zestaw narzędzi agenta

from langchain_mongodb.agent_toolkit.toolkit import MongoDBDatabaseToolkit

# Initialize the MongoDB database toolkit
toolkit = MongoDBDatabaseToolkit(db=db, llm=llm)

# Extract the tools from the toolkit
tools = toolkit.get_tools()
Agenty text-to-query z MongoDB i LangGraph

Inżynieria promptów

from langchain_mongodb.agent_toolkit import MONGODB_AGENT_SYSTEM_PROMPT

# Create a templated prompt for the LLM
prompt = ChatPromptTemplate.from_messages(
    [
        ("system", MONGODB_AGENT_SYSTEM_PROMPT),
        ("system", "Do not re-run tools unless absolutely necessary. If you are not
                    able to get enough information using the tools, reply with
                    I DON'T KNOW. You have access to the following tools: {tool_names}."),
        MessagesPlaceholder(variable_name="messages"),
    ]
)
Agenty text-to-query z MongoDB i LangGraph

Orkiestracja agenta

langgraph.png

Agenty text-to-query z MongoDB i LangGraph

Pamięć

mongosaver.png

thread_checkpoint.png

Agenty text-to-query z MongoDB i LangGraph

Co dalej?

 

Więcej o MongoDB i agentach Text-to-Query

Więcej o LangChain i LangGraph

Agenty text-to-query z MongoDB i LangGraph

Gratulacje!

Agenty text-to-query z MongoDB i LangGraph

Preparing Video For Download...