Build RAG Pipeline with Function Calling Easily

 This video is a step-by-step tutorial to build an end-to-end RAG pipeline with function calling using Llama Index with Router query engine.

Code:

!pip install python-dotenv==1.0.0

!pip install llama-index==0.10.27

!pip install llama-index-llms-openai==0.1.15

!pip install llama-index-embeddings-openai==0.1.7

import nest_asyncio

nest_asyncio.apply()

from llama_index.core import SimpleDirectoryReader

documents = SimpleDirectoryReader(input_files=["mypdf.pdf"]).load_data()

from llama_index.core.node_parser import SentenceSplitter

splitter = SentenceSplitter(chunk_size=1024)

nodes = splitter.get_nodes_from_documents(documents)

print(len(nodes))

print(nodes[0])

from llama_index.core import Settings

from llama_index.llms.openai import OpenAI

from llama_index.embeddings.openai import OpenAIEmbedding

Settings.llm = OpenAI(model="gpt-3.5-turbo")

Settings.embed_model = OpenAIEmbedding(model="text-embedding-ada-002")

from google.colab import userdata

import os

os.environ["OPENAI_API_KEY"] = userdata.get('OPENAI_API_KEY')

from llama_index.core import SummaryIndex, VectorStoreIndex

summary_index = SummaryIndex(nodes)

vector_index = VectorStoreIndex(nodes)

summary_query_engine = summary_index.as_query_engine(

    response_mode="tree_summarize",

    use_async=True,

)

vector_query_engine = vector_index.as_query_engine()

from llama_index.core.tools import QueryEngineTool

summary_tool = QueryEngineTool.from_defaults(

    query_engine=summary_query_engine,

    description=(

        "Useful for summarization questions related to MetaGPT"

    ),

)

vector_tool = QueryEngineTool.from_defaults(

    query_engine=vector_query_engine,

    description=(

        "Useful for retrieving specific context from the MetaGPT paper."

    ),

)

from llama_index.core.query_engine.router_query_engine import RouterQueryEngine

from llama_index.core.selectors import LLMSingleSelector

query_engine = RouterQueryEngine(

    selector=LLMSingleSelector.from_defaults(),

    query_engine_tools=[

        summary_tool,

        vector_tool,

    ],

    verbose=True

)

response = query_engine.query("What is the summary of the document?")

print(str(response))

response = query_engine.query("Who is Fahd Mirza?")

print(str(response))