To get started with the SearchAgent SDK, you’ll first need to ensure that your environment is set up with all necessary dependencies. While specific installation commands are not provided here, typical Python package management tools like pip can be used to manage your environment.

​
Key Components

The SDK is comprised of several key components, each tailored to handle different types of content:

  • PDF Files
  • DOCX Files
  • Text Files
  • Webpages
  • Websites
  • YouTube Videos

These components allow the SearchAgent to Train, process and index content from these sources, making it searchable within your Search Agent.

​
Using the SearchAgent SDK

The following sections provide a step-by-step guide to using the SearchAgent SDK in your projects.

​
Initializing the SearchAgent

To use the SDK, start by importing and initializing the SearchAgent class:

from lyzr import SearchAgent 

# Initialize the SearchAgent
search_agent = SearchAgent()

​
Setup Vector Database

Let’s configure Qdrant Vector Database. please intall pip install qdrant_client

import qdrant_client

QDRANT_CLIENT_URL = "<YOUR-QDRANT-CLIENT-URL>"
QDRANT_API_KEY = "<YOUR-QDRANT-API-KEY>"

client = qdrant_client.QdrantClient(
   url= QDRANT_CLIENT_URL,
    api_key= QDRANT_CLIENT_URL,
)

vector_store_params = {
    "vector_store_type":"QdrantVectorStore",
    "client":client,
    "collection_name":"lyzr_core"
}

Search Agent supports variety of Vector Databases

​
Setup Large Language model

import os
import openai

os.environ["OPENAI_API_KEY"] = "<YOUR-OPENAI-API-KEY>"

llm_params = {
    "model": "gpt-4-turbo-preview",
    "api_key": "<YOUR-OPENAI-API-KEY>"
}

Search Agent supports variety of Large Language Models

​
Training Search Agent

With the SearchAgent initialized, you can begin adding content from various sources. The SDK provides methods for integrating different content types, as outlined below.

​
Adding PDF Files

search_agent.add_pdf(
    input_files=["path-to-file"],
    vector_store_params=vector_store_params,
    llm_params=llm_params
)

​
Adding DOCX Files

search_agent.add_docx(
    input_files=["path-to-file"],
    vector_store_params=vector_store_params,
    llm_params=llm_params
)

​
Adding Text Files

search_agent.add_text(
    input_files=["path-to-file"],
    vector_store_params=vector_store_params,
    llm_params=llm_params
)

​
Adding Webpages

search_agent.add_webpage(
    url="https://example.com",
    vector_store_params=vector_store_params,
    llm_params=llm_params
)

​
Adding Websites

search_agent.add_website(
    url="https://example.com",
    vector_store_params=vector_store_params,
    llm_params=llm_params
)

​
Adding YouTube Videos

search_agent.add_youtube(
    urls=["https://youtube.com/example"],
    vector_store_params=vector_store_params,
    llm_params=llm_params
)

# Ask a question
response = agent.query("<you-query>")

​
Sources

# Sources
for n, source in enumerate(response.source_nodes):
  print(source.text)
  print(source.score)
  print(source.metadata)

​
Advanced Configuration

Each method supports various parameters allowing for detailed customization of how content is processed and indexed. These include specifying whether to include hidden files, whether to process directories recursively, and how to handle file extensions.

InstallationOverview