Spaces:
Sleeping
Sleeping
File size: 5,477 Bytes
53a8795 |
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 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 |
import streamlit as st
import os
from langchain_groq import ChatGroq
from langchain_community.document_loaders import WebBaseLoader
from langchain_community.embeddings import OllamaEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain_core.prompts import ChatPromptTemplate
from langchain.chains import create_retrieval_chain
from langchain_community.vectorstores import FAISS
from langchain_community.document_loaders import PyPDFLoader
from langchain_community.document_loaders import PyPDFDirectoryLoader
from langchain_community.embeddings import HuggingFaceBgeEmbeddings
# from langchain.vectorstores.cassandra import Cassandra
from langchain_community.vectorstores import Cassandra
from langchain_community.llms import Ollama
from cassandra.auth import PlainTextAuthProvider
import tempfile
import cassio
from PyPDF2 import PdfReader
from cassandra.cluster import Cluster
import warnings
from langchain.vectorstores import Pinecone
import pinecone
from pinecone import Pinecone, ServerlessSpec
from langchain_pinecone import PineconeVectorStore
warnings.filterwarnings("ignore")
from dotenv import load_dotenv
import time
load_dotenv()
ASTRA_DB_SECURE_BUNDLE_PATH ="G:/GENAI/Medical_chat_bot/src/secure-connect-medical-bot.zip"
LANGCHAIN_TRACING_V2"]="true"
LANGCHAIN_API_KEY=os.getenv('LANGCHAIN_API_KEY')
LANGCHAIN_PROJECT="Medical_chatbot"
LANGCHAIN_ENDPOINT="https://api.smith.langchain.com"
def doc_loader(pdf_reader):
# print('im from doc_loc fn')
encode_kwargs = {'normalize_embeddings': True}
huggigface_embeddings=HuggingFaceBgeEmbeddings(
model_name='BAAI/bge-small-en-v1.5',
# model_name='sentence-transformers/all-MiniLM-16-v2',
model_kwargs={'device':'cpu'},
encode_kwargs=encode_kwargs)
loader=PyPDFLoader(pdf_reader)
documents=loader.load_and_split()
# print('iam after documents loader called')
text_splitter=RecursiveCharacterTextSplitter(chunk_size=1000,chunk_overlap=200)
final_documents=text_splitter.split_documents(documents)
# print('iam after final_documents called',final_documents)
os.environ['PINECONE_API_KEY'] = os.environ['pinecone']
os.environ['PINECONE_API_ENV'] = "pdf_query_db"
pc = Pinecone(api_key=os.getenv('PINECONE_API_KEY'))
index = pc.Index("pdf-query-index")
namespace = "pdf_query_medical"
def namespace_exists(index, namespace):
try:
stats = index.describe_index_stats()
return namespace in stats['namespaces']
except pinecone.core.client.exceptions.NotFoundException:
return False
if namespace_exists(index, namespace):
print(f"Namespace '{namespace}' exist.")
pinecone_vector_store = PineconeVectorStore(embedding=huggigface_embeddings,index_name="pdf-query-index", namespace=namespace)
# pinecone_vector_store = index.query(f"SELECT * FROM {namespace}")
# return pinecone_vector_store
else:
print(f"Namespace '{namespace}' does not exist. It will be created upon upsertion.")
pinecone_vector_store=PineconeVectorStore(embedding=huggigface_embeddings,index_name="pdf-query-index",namespace=namespace)
pinecone_vector_store.add_documents(final_documents)
return pinecone_vector_store
# def doc_loader(pdf_reader):
# # print('im from doc_loc fn')
# encode_kwargs = {'normalize_embeddings': True}
# huggigface_embeddings=HuggingFaceBgeEmbeddings(
# model_name='BAAI/bge-small-en-v1.5',
# # model_name='sentence-transformers/all-MiniLM-16-v2',
# model_kwargs={'device':'cpu'},
# encode_kwargs=encode_kwargs)
# loader=PyPDFLoader(pdf_reader)
# documents=loader.load_and_split()
# # print('iam after documents loader called')
# text_splitter=RecursiveCharacterTextSplitter(chunk_size=1000,chunk_overlap=200)
# final_documents=text_splitter.split_documents(documents)
# # print('iam after final_documents called',final_documents)
# astrasession = Cluster(
# cloud={"secure_connect_bundle": ASTRA_DB_SECURE_BUNDLE_PATH},
# auth_provider=PlainTextAuthProvider("token", ASTRA_DB_APPLICATION_TOKEN),
# ).connect()
# check_table_query = f"""
# SELECT table_name FROM system_schema.tables
# WHERE keyspace_name='{ASTRA_DB_KEYSPACE}' AND table_name='{ASTRA_DB_TABLE}';
# """
# try:
# result = astrasession.execute(check_table_query)
# if result.one():
# return_query=f""" select * from '{ASTRA_DB_KEYSPACE}'.'{ASTRA_DB_TABLE}'; """
# astra_vector_store=astrasession.execute(return_query)
# return astra_vector_store
# else:
# print(f"Table {ASTRA_DB_KEYSPACE}.{ASTRA_DB_TABLE} does not exist. Try to create table.")
# astra_vector_store=Cassandra(
# embedding=huggigface_embeddings,
# table_name='medical_bot_demo',
# session=astrasession,
# keyspace=ASTRA_DB_KEYSPACE
# )
# astra_vector_store.add_documents(final_documents)
# if astra_vector_store:
# print("Vector store created successfully")
# return astra_vector_store
# except Exception as e:
# print(f"Error checking/creating keyspace: {e}")
|