|
import gradio as gr |
|
|
|
|
|
|
|
''' |
|
https://huggingface.co/spaces/kevinhug/clientX |
|
|
|
https://dash.elfsight.com |
|
''' |
|
counter=""" |
|
<script src="https://static.elfsight.com/platform/platform.js" data-use-service-core defer></script> |
|
<div class="elfsight-app-5f3e8eb9-9103-490e-9999-e20aa4157dc7" data-elfsight-app-lazy></div> |
|
""" |
|
|
|
''' |
|
SIMILAR VECTOR DB SEARCH |
|
''' |
|
import chromadb |
|
client = chromadb.PersistentClient(path="chroma.db") |
|
|
|
db = client.get_collection(name="banks") |
|
|
|
def similar(issue): |
|
global db |
|
docs = db.query(query_texts=issue, n_results=5) |
|
return docs |
|
|
|
''' |
|
FINE TUNE LLM LIKE SCORE |
|
''' |
|
from fastai.vision.all import * |
|
learn = load_learner('banks_txt_like.pkl') |
|
def like(issue): |
|
pred,idx,probs = learn.predict(issue) |
|
return pred |
|
''' |
|
https://www.gradio.app/docs/interface |
|
''' |
|
|
|
|
|
|
|
|
|
with gr.Blocks() as demo: |
|
gr.Markdown("""Enhancing Customer Engagement and Operational Efficiency with NLP |
|
========= |
|
LLM |
|
Semantic Similarity Document Search (SSDS) |
|
|
|
Data Scientist: Kevin Wong, [email protected], 416-903-7937 |
|
|
|
Open source ml bank dataset |
|
https://www.kaggle.com/datasets/trainingdatapro/20000-customers-reviews-on-banks/?select=Banks.csv |
|
""") |
|
with gr.Tab("Semantic Similarity Document Search (SSDS)"): |
|
in_similar = gr.Textbox(placeholder="having credit card problem") |
|
out_similar = gr.JSON() |
|
|
|
btn_similar = gr.Button("Find Similar Verbatim") |
|
btn_similar.click(fn=similar, inputs=in_similar, outputs=out_similar) |
|
|
|
gr.Markdown(""" |
|
Description: |
|
======= |
|
In today's dynamic financial landscape, the Semantic Similarity Document Search (SSDS) capability is a practical innovation to improve client experience, marketing leads, and sentiment analysis. As a Data Scientist with a decades in the financial industry, I see the value of SSDS in action. |
|
|
|
Client Experience: |
|
------ |
|
When a client faces a bad experience, SSDS helps us swiftly locate relevant documents to understand and address their concerns, be it credit card issues, late payment fees, or credit score drops. |
|
|
|
### issue: |
|
- having bad client experience |
|
- having credit card problem |
|
- late payment fee |
|
- credit score dropping |
|
|
|
Marketing Leads: |
|
------ |
|
To enhance marketing strategies, SSDS identifies market trends and consumer preferences, such as the demand for low-interest credit cards. It's a treasure trove for refining our product offerings. |
|
|
|
### issue: |
|
- low interest credit card |
|
|
|
Sentiments: |
|
------ |
|
SSDS tracks customer sentiment, empowering us to swiftly respond to upset customers. It ensures we address their issues promptly, enhancing trust and loyalty. |
|
With no need for jargon, SSDS delivers tangible value to our fintech operations. It's about staying agile, informed, and customer-centric in a rapidly changing financial world. |
|
|
|
### issue: |
|
- upset customer |
|
|
|
Using Sentence Embedding to inject Public ML Banks Text Dataset @ https://github.com/kevinwkc/analytics/blob/master/ai/vectorDB.py |
|
""") |
|
|
|
with gr.Tab("Fine Tune LLM") |
|
in_like = gr.Textbox(placeholder="having credit card problem") |
|
out_like = gr.Textbox(placeholder="like score") |
|
|
|
btn_like = gr.Button("Find Like Score") |
|
btn_like.click(fn=like, inputs=in_like, outputs=out_like) |
|
|
|
|
|
with gr.Accordion("Future Improvement"): |
|
gr.Markdown(""" |
|
tuning the distance for use case |
|
""") |
|
|
|
demo.launch() |
|
|
|
|
