Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -17,12 +17,12 @@ import os
|
|
17 |
import boto3
|
18 |
|
19 |
# AWS access credentials
|
20 |
-
access_key = os.getenv("
|
21 |
-
secret_key =
|
22 |
|
23 |
# S3 bucket details
|
24 |
-
bucket_name = os.getenv("
|
25 |
-
prefix = os.getenv("
|
26 |
|
27 |
HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
|
28 |
|
@@ -59,18 +59,22 @@ def compute_cosine_similarity_scores(query, retrieved_docs):
|
|
59 |
readable_scores = [{"doc": doc, "score": float(score)} for doc, score in zip(retrieved_docs, cosine_scores.flatten())]
|
60 |
return readable_scores
|
61 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
def answer_query_with_similarity(query):
|
63 |
try:
|
64 |
# Fetch files from S3
|
65 |
-
|
66 |
-
objects = s3.list_objects_v2(Bucket=bucket_name, Prefix=prefix)
|
67 |
-
|
68 |
-
file_contents = []
|
69 |
-
for obj in objects.get('Contents', []):
|
70 |
-
if not obj['Key'].endswith('/'): # Skip directories
|
71 |
-
response = s3.get_object(Bucket=bucket_name, Key=obj['Key'])
|
72 |
-
file_content = response['Body'].read()
|
73 |
-
file_contents.append(file_content)
|
74 |
|
75 |
all_text = process_files(file_contents)
|
76 |
|
|
|
17 |
import boto3
|
18 |
|
19 |
# AWS access credentials
|
20 |
+
access_key = os.getenv("ACCESS_KEY")
|
21 |
+
secret_key = os.getenv("SECRET_KEY")
|
22 |
|
23 |
# S3 bucket details
|
24 |
+
bucket_name = os.getenv("BUCKET_NAME")
|
25 |
+
prefix = os.getenv("PREFIX")
|
26 |
|
27 |
HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
|
28 |
|
|
|
59 |
readable_scores = [{"doc": doc, "score": float(score)} for doc, score in zip(retrieved_docs, cosine_scores.flatten())]
|
60 |
return readable_scores
|
61 |
|
62 |
+
def fetch_files_from_s3():
|
63 |
+
s3 = boto3.client('s3', aws_access_key_id=access_key, aws_secret_access_key=secret_key)
|
64 |
+
objects = s3.list_objects_v2(Bucket=bucket_name, Prefix=prefix)
|
65 |
+
|
66 |
+
file_contents = []
|
67 |
+
for obj in objects.get('Contents', []):
|
68 |
+
if not obj['Key'].endswith('/'): # Skip directories
|
69 |
+
response = s3.get_object(Bucket=bucket_name, Key=obj['Key'])
|
70 |
+
file_content = response['Body'].read()
|
71 |
+
file_contents.append(file_content)
|
72 |
+
return file_contents
|
73 |
+
|
74 |
def answer_query_with_similarity(query):
|
75 |
try:
|
76 |
# Fetch files from S3
|
77 |
+
file_contents = fetch_files_from_s3()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
78 |
|
79 |
all_text = process_files(file_contents)
|
80 |
|