Skip to content

Instantly share code, notes, and snippets.

@janakiramm
Created March 14, 2024 09:56
Show Gist options
  • Save janakiramm/8fcfc6c055c09a6f5dc5248b890f0567 to your computer and use it in GitHub Desktop.
Save janakiramm/8fcfc6c055c09a6f5dc5248b890f0567 to your computer and use it in GitHub Desktop.
Python code to build a content summarization application based on Gemini and LangChain
### Install required modules and set the envvar for Gemini API Key
#pip install google.generativeai
#pip install langchain-google-genai
#pip install langchain
#pip install langchain_community
#pip install jupyter
#export GOOGLE_API_KEY="YOUR_GOOGLE_API_KEY"
#Import Modules
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_google_genai import GoogleGenerativeAIEmbeddings
from langchain_community.document_loaders import WebBaseLoader
from langchain.chains import StuffDocumentsChain
from langchain.chains.llm import LLMChain
from langchain.prompts import PromptTemplate
#Initialize Model
llm = ChatGoogleGenerativeAI(model="gemini-pro")
#Load the blog
loader = WebBaseLoader("https://thenewstack.io/the-building-blocks-of-llms-vectors-tokens-and-embeddings/")
docs = loader.load()
#Define the Summarize Chain
template = """Write a concise summary of the following:
"{text}"
CONCISE SUMMARY:"""
prompt = PromptTemplate.from_template(template)
llm_chain = LLMChain(llm=llm, prompt=prompt)
stuff_chain = StuffDocumentsChain(llm_chain=llm_chain, document_variable_name="text")
#Invoke Chain
response=stuff_chain.invoke(docs)
print(response["output_text"])
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment