|
import gradio as gr |
|
|
|
|
|
|
|
import chromadb |
|
client = chromadb.PersistentClient(path="chroma.db") |
|
|
|
db = client.get_collection(name="banks") |
|
|
|
|
|
|
|
|
|
def greet(issue): |
|
global db |
|
docs = db.query(query_texts=issue, n_results=5) |
|
return docs |
|
|
|
|
|
|
|
iface = gr.Interface(fn=greet, inputs="text", outputs="text", title="NLP Leads Generation", description=""" |
|
Data Scientist: Kevin Wong |
|
Using Sentence Embedding to inject Public ML Banks Text Dataset @ https://github.com/kevinwkc/analytics/blob/master/ai/vectorDB.py""", |
|
article=""" |
|
put in the issue regarding service, sales, point of failure, product, trend to find out what customer talking about |
|
|
|
Client Experience |
|
---------- |
|
- having bad client experience |
|
- having credit card problem |
|
- late payment fee |
|
- credit score dropping |
|
|
|
Marketing Leads |
|
---------- |
|
- low interest credit card |
|
|
|
Sentiments |
|
--------- |
|
- upset customer |
|
|
|
""") |
|
iface.launch() |
