Spaces:
Running
Running
File size: 1,684 Bytes
249fca7 23a84f2 85952ea d967c00 23a84f2 a3e054f 23a84f2 d967c00 23a84f2 1d2c336 23a84f2 1d2c336 85952ea 23a84f2 85952ea 23a84f2 d3e2171 1d2c336 23a84f2 |
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 |
from langchain_community.embeddings import HuggingFaceBgeEmbeddings
from langchain_community.vectorstores import Pinecone
from langchain_community.vectorstores.utils import DistanceStrategy
from langchain_openai import ChatOpenAI
from pinecone import Pinecone as PineconeClient
import streamlit as st
st.set_page_config(layout="wide", page_title="LegisQA")
CONGRESS_GOV_TYPE_MAP = {
"hconres": "house-concurrent-resolution",
"hjres": "house-joint-resolution",
"hr": "house-bill",
"hres": "house-resolution",
"s": "senate-bill",
"sconres": "senate-concurrent-resolution",
"sjres": "senate-joint-resolution",
"sres": "senate-resolution",
}
OPENAI_CHAT_MODELS = [
"gpt-3.5-turbo-0125",
"gpt-4-0125-preview",
]
def load_bge_embeddings():
model_name = "BAAI/bge-small-en-v1.5"
model_kwargs = {"device": "cpu"}
encode_kwargs = {"normalize_embeddings": True}
emb_fn = HuggingFaceBgeEmbeddings(
model_name=model_name,
model_kwargs=model_kwargs,
encode_kwargs=encode_kwargs,
query_instruction="Represent this question for searching relevant passages: ",
)
return emb_fn
def load_pinecone_vectorstore():
emb_fn = load_bge_embeddings()
pc = PineconeClient(api_key=st.secrets["pinecone_api_key"])
index = pc.Index(st.secrets["pinecone_index_name"])
vectorstore = Pinecone(
index=index,
embedding=emb_fn,
text_key="text",
distance_strategy=DistanceStrategy.COSINE,
)
return vectorstore
vectorstore = load_pinecone_vectorstore()
query = st.text_area("Enter query")
docs = vectorstore.similarity_search_with_score(query)
st.write(docs)
|