Build a RAG Agent with uAgents and Langchain

Introduction

In this guide, we'll walk through how to create Agents capable of answering questions based on any provided document using the Fetch.ai uAgents and AI Engine Python libraries as well as OpenAI and Cohere. The aim is to assist you in building a LangChain Retrieval-Augmented Generation (RAG) Agent!

ℹ️

Also, rememeber that you can have a look and eventually download the source code used within this guide from Github here (opens in a new tab).

The uAgents and AI Engine libraries offer a decentralized and modular framework for creating RAG Agents, improving the process of creating them. These tools streamline the integration of AI models like OpenAI and Cohere, enabling more efficient and scalable development of intelligent Agents. With enhanced interoperability, security, and resource management, this framework allows developers to quickly build and deploy sophisticated Agents that can effectively answer questions based on any provided document, making the entire process faster and more robust.

ℹ️

Check out the AI Engine package (opens in a new tab) and uAgents (opens in a new tab) packages to download them and start integrating this tools within your Agents project!

Current version of the AI Engine package is . Current version of the uAgents package is .

Let's dive into the LangChain RAG Agents development!

Prerequisites

Make sure you have read the following resources before going on with this guide:

LangChain and Cohere Overview

LangChain

In the context of a RAG agent, LangChain helps by:

Document Loading and Parsing: it processes and structures data from web pages.
Vector Storage: LangChain indexes documents into vectors, making it easier to perform similarity searches.
Question Answering: it generates answers by querying the indexed data, providing context-aware responses.

Cohere

Cohere offers advanced NLP models that assist in refining the answers generated by LangChain:

Contextual Compression: it filters and prioritizes data based on relevance, ensuring that the Agent focuses on the most important information.
Enhanced Accuracy: Cohere's NLP models improve the quality of the generated answers by understanding the context of the query more effectively.

How These Work Together in a RAG Agent

By combining LangChain for document retrieval and Cohere for NLP enhancement, this setup allows our Agents to process complex queries with context-aware responses, improving accuracy and user experience. LangChain handles the heavy lifting of document parsing and information retrieval, while Cohere fine-tunes the response to ensure high-quality, relevant answers.

API KEYs

You will need two API keys to correctly go through this guide:

One from OpenAI
One from Cohere.

Follow the steps provided below to obtain them:

OpenAI API Key

Visit the OpenAI website (opens in a new tab).
Sign up or log in to your account.
Navigate to the API section.
Generate or retrieve your API key.

Cohere API Key

Visit the Cohere website (opens in a new tab).
Sign up or log in to your account.
Go to the API Keys section.
Copy an existing key or create a new one.

Project structure and overview

Project structure

The project is structured as follows:


langchain-rag/
.
├── poetry.lock
├── pyproject.toml
└── src
    ├── agents
    │   ├── langchain_rag_agent.py
    │   └── langchain_rag_user.py
    ├── main.py
    └── messages
        └── requests.py

The source code directory (src) contains the following directories and files:

agents: contains the scripts for the LangChain Agents.
- langchain_rag_agent.py: it is the script for the RAG agent (retrieves info, finds documents, generates answers).
- langchain_rag_user.py: Script for the User agent (asks questions, handles responses).
main.py: Starts both the RAG and user agents.
messages: Defines custom message models.
- requests.py: Defines the RagRequest message model (question, URL, optional deep read).

Environment variables

You'll need to set up environment variables for your project to run correctly. These variables include your API keys, which should be stored in a .env file within the src directory.

To do this, navigate to the src directory. Here, create and source the .env file. Within this one, add the following:


export COHERE_API_KEY="YOUR_COHERE_API_KEY"
export OPENAI_API_KEY="YOUR_OPENAI_API_KEY"

Langchain RAG setup

Project dependencies

You'll need several Python packages for the project. These can be managed efficiently using Poetry (opens in a new tab). The following dependencies are required for the correct development of the Langchain RAG Agent project:


[tool.poetry.dependencies]
python = ">=3.10,<3.12"
uagents = "^0.17.1"
requests = "^2.31.0"
langchain = "^0.3.7"
openai = "^1.54.5"
langchain-openai = "^0.2.9"
tiktoken = "^0.8.0"
cohere = "^5.11.4"
faiss-cpu = "^1.9.0.post1"
validators = "^0.34.0"
uagents-ai-engine = "^0.6.0"
unstructured = "^0.16.5"
langchain-community = "^0.3.7"

Messages Data Model

RagRequest Model

We now need to define the requests.py file under the messages folder in the project:

windows
echo. > requests.py

The script looks like the following:

requests.py
 
from typing import Optional
from uagents import Model, Field
 
 
class RagRequest(Model):
    question: str = Field(
        description="The question that the user wants to have an answer for."
    )
    url: str = Field(description="The url of the docs where the answer is.")
    deep_read: Optional[str] = Field(
        description="Specifies weather all nested pages referenced from the starting URL should be read or not. The value should be yes or no.",
        default="no",
    )

Here's a breakdown of the RagRequest message data model:

question (str): it is the user's question that needs to be answered based on the provided website URL.
url (str): it is the URL of the website where the answer should be found.
deep_read (Optional[str], default="no"): this optional field allows you to specify whether the RAG Agent should follow and read nested pages (i.e., pages linked from the starting URL). Valid values are "yes" or "no". By default, it is set to "no", meaning that the Agent only will focus on the initial page linked to the URL.

Agents

LangChain RAG Agent

This step involves setting up the LangChain Retrieval-Augmented Generation (RAG) Agent which can scrape web content, retrieve relevant documents, and generate answers to user queries based on the retrieved content.

Let's start by creating the file within the agents directory, under src directory of our project, and name it langchain_rag_agent.py by using the following command:

windows
echo. > langchain_rag_agent.py

The Agent is defined as a local agent with a Mailbox and it can answer questions by fetching and summarizing information from a given website URL.

The script for this Agent looks as follows:

langchain_rag_agent.py
import traceback
from uagents import Agent, Context, Protocol
import validators
from messages.requests import RagRequest
import os
from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate
from langchain_community.document_loaders import UnstructuredURLLoader
import requests
from bs4 import BeautifulSoup
from urllib.parse import urlparse
from langchain_openai import OpenAIEmbeddings
from langchain_community.vectorstores import FAISS
from langchain.retrievers import ContextualCompressionRetriever
from langchain.retrievers.document_compressors import CohereRerank
from ai_engine import UAgentResponse, UAgentResponseType
import nltk
from uagents.setup import fund_agent_if_low
 
nltk.download("punkt")
nltk.download("averaged_perceptron_tagger")
 
LANGCHAIN_RAG_SEED = "YOUR_LANGCHAIN_RAG_SEED"
 
agent = Agent(
    name="langchain_rag_agent",
    seed=LANGCHAIN_RAG_SEED,
    mailbox=True,
)
 
fund_agent_if_low(agent.wallet.address())
 
docs_bot_protocol = Protocol("DocsBot")
 
PROMPT_TEMPLATE = """
Answer the question based only on the following context:
 
{context}
 
---
 
Answer the question based on the above context: {question}
"""
 
 
def create_retriever(
        ctx: Context, url: str, deep_read: bool
) -> ContextualCompressionRetriever:
    def scrape(site: str):
        if not validators.url(site):
            ctx.logger.info(f"Url {site} is not valid")
            return
 
        r = requests.get(site)
        soup = BeautifulSoup(r.text, "html.parser")
 
        parsed_url = urlparse(url)
        base_domain = parsed_url.scheme + "://" + parsed_url.netloc
 
        link_array = soup.find_all("a")
        for link in link_array:
            href: str = link.get("href", "")
            if len(href) == 0:
                continue
            current_site = f"{base_domain}{href}" if href.startswith("/") else href
            if (
                    ".php" in current_site
                    or "#" in current_site
                    or not current_site.startswith(url)
                    or current_site in urls
            ):
                continue
            urls.append(current_site)
            scrape(current_site)
 
    urls = [url]
    if deep_read:
        scrape(url)
        ctx.logger.info(f"After deep scraping - urls to parse: {urls}")
 
    try:
        loader = UnstructuredURLLoader(urls=urls)
        docs = loader.load_and_split()
        db = FAISS.from_documents(docs, OpenAIEmbeddings())
        compression_retriever = ContextualCompressionRetriever(
            base_compressor=CohereRerank(), base_retriever=db.as_retriever()
        )
        return compression_retriever
    except Exception as exc:
        ctx.logger.error(f"Error happened: {exc}")
        traceback.format_exception(exc)
 
 
@docs_bot_protocol.on_message(model=RagRequest, replies={UAgentResponse})
async def answer_question(ctx: Context, sender: str, msg: RagRequest):
    ctx.logger.info(f"Received message from {sender}, session: {ctx.session}")
    ctx.logger.info(
        f"input url: {msg.url}, question: {msg.question}, is deep scraping: {msg.deep_read}"
    )
 
    parsed_url = urlparse(msg.url)
    if not parsed_url.scheme or not parsed_url.netloc:
        ctx.logger.error("invalid input url")
        await ctx.send(
            sender,
            UAgentResponse(
                message="Input url is not valid",
                type=UAgentResponseType.FINAL,
            ),
        )
        return
    base_domain = parsed_url.scheme + "://" + parsed_url.netloc
    ctx.logger.info(f"Base domain: {base_domain}")
 
    retriever = create_retriever(ctx, url=msg.url, deep_read=msg.deep_read == "yes")
 
    compressed_docs = retriever.get_relevant_documents(msg.question)
    context_text = "\n\n---\n\n".join([doc.page_content for doc in compressed_docs])
    prompt_template = ChatPromptTemplate.from_template(PROMPT_TEMPLATE)
    prompt = prompt_template.format(context=context_text, question=msg.question)
 
    model = ChatOpenAI(model="gpt-4o-mini")
    response = model.predict(prompt)
    ctx.logger.info(f"Response: {response}")
    await ctx.send(
        sender, UAgentResponse(message=response, type=UAgentResponseType.FINAL)
    )
 
 
agent.include(docs_bot_protocol, publish_manifest=True)
 
if __name__ == "__main__":
    agent.run()

The Agent fetches and processes information from specified URLs to answer users' questions.

Let's explore the script above in more detail. We start by importing multiple modules, including tools for making HTTP requests, parsing HTML, and handling Natural Language Processing (NLP). The Agent uses OpenAI's GPT-4o-mini model to generate answers based on the retrieved documents. We then create an Agent called langchain_rag_agent() with a unique seed. Check out the Mailbox guide for additional information on how to set up Mailboxes for your Agents. Make sure to have enough funds in the Agent's wallet for it to correctly register in the Almanac contract . You can use the fund_agent_if_low function on the testnet to add funds to your Agent's wallet if needed.

Next, we define the DocsBot protocol using the Protocol class of the uagents library to handle message interactions. This protocol uses a predefined prompt template to structure the questions and context for the language model.

The create_retriever() function is responsible for fetching and parsing web pages. If necessary, it can perform deep scraping, which involves gathering all linked pages within the same domain. The function validates URLs, retrieves HTML content, and uses BeautifulSoup to parse the HTML and find links. The documents are then loaded and split using LangChain's UnstructuredURLLoader, indexed with FAISS, and compressed with Cohere, creating a retriever that can extract relevant information.

The answer_question() function, decorated with the .on_message() handler , is triggered when the Agent receives a message matching the RagRequest message data model. The function validates the input URL and creates a retriever to fetch relevant documents based on the question. The context alongside with the question are then used to create a prompt for the language model (ChatOpenAI), which generates the final answer.

The generated answer is then sent back to the user.

Finally, the Agent is set to include the DocsBot protocol. We can then run the Agent's script; it will start the Agent and allow it to receive and process incoming messages.

To correctly run the code, you need to provide the name, seed, mailbox, LANGCHAIN_RAG_SEED, PROMPT_TEMPLATE and AGENT_MAILBOX_KEY parameters.

LangChain User Agent

We are now ready to define the LangChain User Agent which interacts with the LangChain RAG Agent we defined above to ask a question based on documents found at specified URLs. The user Agent request the RAG Agent to retrieve and process information from the web page and then to handle the response. The Agent is defined as a local Agent with an endpoint (opens in a new tab).

Create a file for this Agent:

windows
echo. > langchain_rag_user.py

The script looks as follows:

langchain_rag_user.py
 
from uagents import Agent, Context, Protocol
from messages.requests import RagRequest
from ai_engine import UAgentResponse
from uagents.setup import fund_agent_if_low
 
 
QUESTION = "How to install uagents using pip"
URL = "https://fetch.ai/docs/guides/agents/installing-uagent"
DEEP_READ = (
    "no"
)
 
RAG_AGENT_ADDRESS = "YOUR_LANGCHAIN_RAG_AGENT_ADDRESS"
 
user = Agent(
    name="langchain_rag_user",
    port=8000,
    endpoint=["http://127.0.0.1:8000/submit"],
)
fund_agent_if_low(user.wallet.address())
rag_user = Protocol("LangChain RAG user")
 
 
@rag_user.on_interval(60, messages=RagRequest)
async def ask_question(ctx: Context):
    ctx.logger.info(
        f"Asking RAG agent to answer {QUESTION} based on document located at {URL}, reading nested pages too: {DEEP_READ}"
    )
    await ctx.send(
        RAG_AGENT_ADDRESS, RagRequest(question=QUESTION, url=URL, deep_read=DEEP_READ)
    )
 
 
@rag_user.on_message(model=UAgentResponse)
async def handle_data(ctx: Context, sender: str, data: UAgentResponse):
    ctx.logger.info(f"Got response from RAG agent: {data.message}")
 
 
user.include(rag_user)
 
if __name__ == "__main__":
    rag_user.run()

Here, we create the User Agent which interacts with the LangChain RAG Agent we previously defined. The User Agent periodically asks the RAG Agent a predefined question and then handles the response.

After importing all required modules and classes, a specific QUESTION is provided: "How to install uagents using pip". We also provide the URL for the web page where the relevant information can be found to answer the question. The DEEP_READ variable is set to no; this indicates that the Agent should only read the main page.

The RAG_AGENT_ADDRESS variable holds the address of the RAG Agent responsible of retrieving and processing the web page content to answer the user's question.

We can then define the User Agent. We create the langchain_rag_user with a specific port and endpoint; this last one is essential to allow for communication with the RAG Agent. Make sure your Agent has enough funds to register in the Almanac contract. On the Testnet, you can use the fund_agent_if_low() function to fund your Agent's wallet if needed.

We then proceed and define the protocol . A protocol named LangChain RAG user is created using the Protocol class from the uagents library to handle the Agent's interactions. This protocol contains two important functions:

The ask_question() function, which is decorated with the .on_interval() handler and which is set to run at 60-second intervals. This function sends a RagRequest message to the LangChain RAG Agent, asking it to answer the QUESTION based on the specified URL. It then logs the QUESTION and URL details for debugging purposes.
The handle_data() function is decorated with the .on_message() handler and it handles incoming messages from the LangChain RAG Agent. When a response is received, it logs the response message.

Finally, the LangChain RAG user protocol is included using the .include() method into the Agent which is then run by calling rag_user.run() in the main block.

Remember to provide the QUESTION, URL, DEEP_READ, RAG_AGENT_ADDRESS, name, seed and endpoint parameters to correctly run this code.

Main script

We are now ready to define the main script for our project. In the src folder of the project, we create a Python script named main.py using the following command:

windows
echo. > main.py

We can now write the code for it.

It will look as follows:

main.py
 
from uagents import Bureau
from agents.langchain_rag_agent import agent
from agents.langchain_rag_user import user
 
 
if __name__ == "__main__":
    bureau = Bureau(endpoint="http://127.0.0.1:8000/submit", port=8000)
    print(f"Adding RAG agent to Bureau: {agent.address}")
    bureau.add(agent)
    print(f"Adding user agent to Bureau: {user.address}")
    bureau.add(user)
    bureau.run()

Cool! All scripts are now set up! You will need to connect the local Agent to the Agentverse using a Mailbox . The Mailbox enables your Agents to be retrievable for communication and interaction with any other registered Agent on the Almanac contract and Fetch Network. In this example, the langchain_rag_agent will be connected to the Agentverse using a Mailbox . The langchain_rag_user Agent is used as a testing Agent for the RAG Agent being registered on the Agentverse and made subsequently available on DeltaV for queries.

By creating an Agent Function and registering it via the Agentverse, you will make it retrievable to the AI Engine for interaction with users via natural language queries made on DeltaV .

The langchain_rag_user Agent is used as a testing Agent for the RAG Agent being registered on the Agentverse and made subsequently available on DeltaV for queries.

Expected output

The expected output for this example should be similar to the following one. Here, we questioned the RAG Agent with the question How to install uagents using pip from the RAG User Agent:

Was this page helpful?

You can also leave detailed feedbackon Github

Hosted agent REST endpoints