loader = TextLoader(“/content/constitution of Islamic Republic of Pakistan.txt”)
documents = loader.load()
text_splitter = RecursiveCharacterTextSplitter(chunk_size=600, chunk_overlap=20)
docs = text_splitter.split_documents(documents)
embeddings = OpenAIEmbeddings()
Create vector database
pinecone.init(
api_key=os.getenv(‘PINECONE_API_KEY’),
environment=os.getenv(‘PINECONE_ENV’)
)
index_name = “constitutionofpakistan”
pinecone_index = pinecone.Index(index_name)
Upload vectors to Pinecone
db = Pinecone.from_documents(docs, embeddings, index_name=index_name)