Spaces:
Build error
Build error
File size: 3,154 Bytes
1540bd1 3384f62 1540bd1 736eba2 63e4b9a 736eba2 1540bd1 77554c7 1540bd1 0d130a7 d19a03c 8e4448b 1540bd1 3384f62 1540bd1 3384f62 1540bd1 89553ed 3384f62 89553ed 3384f62 1540bd1 d19a03c 0f6388d 1540bd1 3384f62 1540bd1 3384f62 1540bd1 |
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 |
from langchain.embeddings import HuggingFaceEmbeddings,HuggingFaceInstructEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.chat_models.openai import ChatOpenAI
from langchain import VectorDBQA
import pandas as pd
from variables import *
from langchain.chat_models import ChatOpenAI
from langchain.prompts.chat import (
ChatPromptTemplate,
SystemMessagePromptTemplate,
AIMessagePromptTemplate,
HumanMessagePromptTemplate,
)
from langchain.schema import (
AIMessage,
HumanMessage,
SystemMessage
)
from datetime import datetime as dt
system_template="""Use the following pieces of context to answer the users question.
If you don't know the answer, just say that you don't know, don't try to make up an answer.
ALWAYS return a "SOURCES" part in your answer.
The "SOURCES" part should be a reference to the source of the document from which you got your answer.
Example of your response should be:
```
The answer is foo
SOURCES: xyz
```
Begin!
----------------
{context}
"""
messages = [
SystemMessagePromptTemplate.from_template(system_template),
HumanMessagePromptTemplate.from_template("{question}")
]
prompt = ChatPromptTemplate.from_messages(messages)
current_time = dt.strftime(dt.today(),'%d_%m_%Y_%H_%M')
st.markdown("## Financial Tweets GPT Search")
twitter_link = """
[](https://twitter.com/nickmuchi)
"""
st.markdown(twitter_link)
bi_enc_dict = {'mpnet-base-v2':"sentence-transformers/all-mpnet-base-v2",
'instructor-base': 'hkunlp/instructor-base'}
search_input = st.text_input(
label='Enter Your Search Query',value= "What is the latest update on central banks?", key='search')
sbert_model_name = st.sidebar.selectbox("Embedding Model", options=list(bi_enc_dict.keys()), key='sbox')
tweets = st.session_state['tlist']
topic = st.session_state['topic']
user = st.session_state['user']
cr_time = st.session_state['time']
try:
if search_input:
model = bi_enc_dict[sbert_model_name]
with st.spinner(
text=f"Loading {model} embedding model and Generating Response..."
):
vectorstore = create_vectorstore(tweets,model,user,topic,cr_time)
tweets = embed_tweets(search_input,prompt,vectorstore)
references = [doc.page_content for doc in tweets['source_documents']]
answer = tweets['result']
##### Sematic Search #####
with st.expander(label='Query Result', expanded=True):
st.write(answer)
with st.expander(label='References from Corpus used to Generate Result'):
for ref in references:
st.write(ref)
else:
st.write('Please ensure you have entered the YouTube URL or uploaded the Earnings Call file')
except RuntimeError:
st.write('Please ensure you have entered the YouTube URL or uploaded the Earnings Call file')
|