Spaces:
Runtime error
Runtime error
File size: 2,937 Bytes
be482eb |
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 82 83 84 85 86 87 88 89 |
import os
import pandas as pd
import pinecone
from dotenv import load_dotenv
from langchain.embeddings import OpenAIEmbeddings
from langchain.embeddings.sentence_transformer import \
SentenceTransformerEmbeddings
from langchain.llms import OpenAI
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import Pinecone
from pypdf import PdfReader
from sklearn.model_selection import train_test_split
from functools import lru_cache
#**********Functions to help you load documents to PINECONE***********
#Read PDF data
def read_pdf_data(pdf_file):
pdf_page = PdfReader(pdf_file)
text = ""
for page in pdf_page.pages:
text += page.extract_text()
return text
#Split data into chunks
def split_data(text):
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=50)
docs = text_splitter.split_text(text)
docs_chunks =text_splitter.create_documents(docs)
return docs_chunks
#Create embeddings instance
def create_embeddings_load_data():
#embeddings = OpenAIEmbeddings()
embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
return embeddings
@lru_cache
def pine_cone_index(pinecone_index_name: str | None):
load_dotenv()
pinecone.init(
api_key=os.getenv('PINECONE_API_KEY'),
environment=os.getenv('PINECONE_ENV'),
)
index_name = pinecone_index_name or os.getenv('PINECONE_INDEX_NAME')
if index_name is None:
raise ValueError('PINECONE_INDEX_NAME is not set')
return index_name
def push_to_pinecone(embeddings,docs,pinecone_index_name: str | None=None):
index_name = pine_cone_index(pinecone_index_name)
index = Pinecone.from_documents(docs, embeddings, index_name=index_name)
return index
#*********Functions for dealing with Model related tasks...************
#Read dataset for model creation
def read_data(data):
df = pd.read_csv(data,delimiter=',', header=None)
return df
#Create embeddings instance
def get_embeddings():
embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
return embeddings
#Generating embeddings for our input dataset
def create_embeddings(df,embeddings):
df[2] = df[0].apply(lambda x: embeddings.embed_query(x))
return df
#Splitting the data into train & test
def split_train_test__data(df_sample):
# Split into training and testing sets
sentences_train, sentences_test, labels_train, labels_test = train_test_split(
list(df_sample[2]), list(df_sample[1]), test_size=0.25, random_state=0)
print(len(sentences_train))
return sentences_train, sentences_test, labels_train, labels_test
#Get the accuracy score on test data
def get_score(svm_classifier,sentences_test,labels_test):
score = svm_classifier.score(sentences_test, labels_test)
return score
|