Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -3,6 +3,110 @@ import requests
|
|
| 3 |
import json
|
| 4 |
import os
|
| 5 |
import pandas as pd
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
# Assuming the environment variables are already set, we directly use them.
|
| 8 |
# However, in a Streamlit app, you might want to set them up within the script for demonstration purposes
|
|
@@ -84,3 +188,5 @@ if st.button("Query Vectara"):
|
|
| 84 |
st.write("No results found.")
|
| 85 |
|
| 86 |
# Note: The integration of the model for HHEM scores is omitted as it requires the specific model details and implementation.
|
|
|
|
|
|
|
|
|
| 3 |
import json
|
| 4 |
import os
|
| 5 |
import pandas as pd
|
| 6 |
+
from sentence_transformers import CrossEncoder
|
| 7 |
+
import numpy as np
|
| 8 |
+
|
| 9 |
+
# Initialize the HHEM model
|
| 10 |
+
model = CrossEncoder('vectara/hallucination_evaluation_model')
|
| 11 |
+
|
| 12 |
+
# Function to compute HHEM scores
|
| 13 |
+
def compute_hhem_scores(texts, summary):
|
| 14 |
+
pairs = [[text, summary] for text in texts]
|
| 15 |
+
scores = model.predict(pairs)
|
| 16 |
+
return scores
|
| 17 |
+
|
| 18 |
+
# Define the Vectara query function
|
| 19 |
+
def vectara_query(query: str, config: dict):
|
| 20 |
+
corpus_key = [{
|
| 21 |
+
"customerId": config["customer_id"],
|
| 22 |
+
"corpusId": config["corpus_id"],
|
| 23 |
+
"lexicalInterpolationConfig": {"lambda": config.get("lambda_val", 0.5)},
|
| 24 |
+
}]
|
| 25 |
+
data = {
|
| 26 |
+
"query": [{
|
| 27 |
+
"query": query,
|
| 28 |
+
"start": 0,
|
| 29 |
+
"numResults": config.get("top_k", 10),
|
| 30 |
+
"contextConfig": {
|
| 31 |
+
"sentencesBefore": 2,
|
| 32 |
+
"sentencesAfter": 2,
|
| 33 |
+
},
|
| 34 |
+
"corpusKey": corpus_key,
|
| 35 |
+
"summary": [{
|
| 36 |
+
"responseLang": "eng",
|
| 37 |
+
"maxSummarizedResults": 5,
|
| 38 |
+
}]
|
| 39 |
+
}]
|
| 40 |
+
}
|
| 41 |
+
|
| 42 |
+
headers = {
|
| 43 |
+
"x-api-key": config["api_key"],
|
| 44 |
+
"customer-id": config["customer_id"],
|
| 45 |
+
"Content-Type": "application/json",
|
| 46 |
+
}
|
| 47 |
+
response = requests.post(
|
| 48 |
+
headers=headers,
|
| 49 |
+
url="https://api.vectara.io/v1/query",
|
| 50 |
+
data=json.dumps(data),
|
| 51 |
+
)
|
| 52 |
+
if response.status_code != 200:
|
| 53 |
+
st.error(f"Query failed (code {response.status_code}, reason {response.reason}, details {response.text})")
|
| 54 |
+
return [], ""
|
| 55 |
+
|
| 56 |
+
result = response.json()
|
| 57 |
+
responses = result["responseSet"][0]["response"]
|
| 58 |
+
summary = result["responseSet"][0]["summary"][0]["text"]
|
| 59 |
+
|
| 60 |
+
res = [[r['text'], r['score']] for r in responses]
|
| 61 |
+
return res, summary
|
| 62 |
+
|
| 63 |
+
# Streamlit UI setup
|
| 64 |
+
st.title("Vectara Content Query Interface")
|
| 65 |
+
|
| 66 |
+
# User inputs
|
| 67 |
+
query = st.text_input("Enter your query here", "")
|
| 68 |
+
lambda_val = st.slider("Lambda Value", min_value=0.0, max_value=1.0, value=0.5)
|
| 69 |
+
top_k = st.number_input("Top K Results", min_value=1, max_value=50, value=10)
|
| 70 |
+
|
| 71 |
+
if st.button("Query Vectara"):
|
| 72 |
+
config = {
|
| 73 |
+
"api_key": os.environ.get("VECTARA_API_KEY", ""),
|
| 74 |
+
"customer_id": os.environ.get("VECTARA_CUSTOMER_ID", ""),
|
| 75 |
+
"corpus_id": os.environ.get("VECTARA_CORPUS_ID", ""),
|
| 76 |
+
"lambda_val": lambda_val,
|
| 77 |
+
"top_k": top_k,
|
| 78 |
+
}
|
| 79 |
+
|
| 80 |
+
results, summary = vectara_query(query, config)
|
| 81 |
+
|
| 82 |
+
if results:
|
| 83 |
+
st.subheader("Summary")
|
| 84 |
+
st.write(summary)
|
| 85 |
+
|
| 86 |
+
st.subheader("Top Results")
|
| 87 |
+
|
| 88 |
+
# Extract texts from results
|
| 89 |
+
texts = [r[0] for r in results[:5]]
|
| 90 |
+
|
| 91 |
+
# Compute HHEM scores
|
| 92 |
+
scores = compute_hhem_scores(texts, summary)
|
| 93 |
+
|
| 94 |
+
# Prepare and display the dataframe
|
| 95 |
+
df = pd.DataFrame({'Fact': texts, 'HHEM Score': scores})
|
| 96 |
+
st.dataframe(df)
|
| 97 |
+
else:
|
| 98 |
+
st.write("No results found.")
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
"""
|
| 105 |
+
import streamlit as st
|
| 106 |
+
import requests
|
| 107 |
+
import json
|
| 108 |
+
import os
|
| 109 |
+
import pandas as pd
|
| 110 |
|
| 111 |
# Assuming the environment variables are already set, we directly use them.
|
| 112 |
# However, in a Streamlit app, you might want to set them up within the script for demonstration purposes
|
|
|
|
| 188 |
st.write("No results found.")
|
| 189 |
|
| 190 |
# Note: The integration of the model for HHEM scores is omitted as it requires the specific model details and implementation.
|
| 191 |
+
|
| 192 |
+
"""
|