File size: 2,051 Bytes
9c1b620
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1189b48
9c1b620
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import Pinecone
from langchain.embeddings.sentence_transformer import SentenceTransformerEmbeddings
import pinecone
import asyncio
from langchain.document_loaders.sitemap import SitemapLoader


# Function to fetch data from website
# https://python.langchain.com/docs/modules/data_connection/document_loaders/integrations/sitemap
def get_website_data(sitemap_url):

    loop = asyncio.new_event_loop()
    asyncio.set_event_loop(loop)
    loader = SitemapLoader(
        sitemap_url
    )

    docs = loader.load()

    return docs

# Function to split data into smaller chunks


def split_data(docs):

    text_splitter = RecursiveCharacterTextSplitter(
        chunk_size=1000,
        chunk_overlap=200,
        length_function=len,
    )

    docs_chunks = text_splitter.split_documents(docs)
    return docs_chunks

# Function to create embeddings instance


def create_embeddings():

    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
    return embeddings

# Function to push data to Pinecone


def push_to_pinecone(pinecone_apikey, pinecone_environment, pinecone_index_name, embeddings, docs):

    pinecone.init(
        api_key=pinecone_apikey,
        environment=pinecone_environment
    )

    index_name = pinecone_index_name
    index = Pinecone.from_documents(docs, embeddings, index_name=index_name)
    return index

# Function to pull index data from Pinecone


def pull_from_pinecone(pinecone_apikey, pinecone_environment, pinecone_index_name, embeddings):

    pinecone.init(
        api_key=pinecone_apikey,
        environment=pinecone_environment
    )

    index_name = pinecone_index_name

    index = Pinecone.from_existing_index(index_name, embeddings)
    return index

# This function will help us in fetching the top relevent documents from our vector store - Pinecone Index


def get_similar_docs(index, query, k=2):

    similar_docs = index.similarity_search(query, k=k)
    return similar_docs