Spaces:
Sleeping
Sleeping
File size: 2,982 Bytes
94b1e32 |
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 |
import re
import pandas as pd
from modules.scraper import get_raw_data, get_raw_data_sheets
from modules.embedding_storage import process_safety_with_chroma
from modules.qa_chatbot import create_chatbot, ask_question
def extract_column_name(query_template):
"""
Extract the column name from the query template enclosed in curly braces.
"""
match = re.search(r"\{(.*?)\}", query_template)
if not match:
raise ValueError("No placeholder found in the query template. Ensure the query contains a placeholder like {column_name}.")
return match.group(1)
def process_query_and_update_csv(file_path, query_template):
"""
Processes the queries based on the specified column, updates the CSV file,
and adds an 'Answer' column with responses.
"""
column_name = extract_column_name(query_template)
df = pd.read_csv(file_path)
if column_name not in df.columns:
raise ValueError(f"The specified column '{column_name}' is missing in the provided CSV file.")
if "Answer" not in df.columns:
df["Answer"] = ""
for index, row in df.iterrows():
value = row[column_name]
query = query_template.replace(f"{{{column_name}}}", str(value))
# Process the query using provided functions
raw_data = get_raw_data(file_path, query)
vector_store = process_safety_with_chroma(raw_data)
qa_system = create_chatbot(vector_store)
prompt = f"Give me the exact answer for this below query '{query}' in a structured format with a link from the content provided only."
answer = ask_question(qa_system, prompt)
df.at[index, "Answer"] = answer
df.to_csv(file_path, index=False)
return df
def process_query_and_update_sheets(file_path, df, query_template):
"""
Processes the queries based on the specified column, updates the CSV file,
and adds an 'Answer' column with responses.
"""
column_name = extract_column_name(query_template)
# df = pd.read_csv(file_path)
if column_name not in df.columns:
raise ValueError(f"The specified column '{column_name}' is missing in the provided CSV file.")
if "Answer" not in df.columns:
df["Answer"] = ""
for index, row in df.iterrows():
value = row[column_name]
query = query_template.replace(f"{{{column_name}}}", str(value))
# print( "Value : ", value, "Query : ", query)
# Process the query using provided functions
raw_data = get_raw_data_sheets(query)
vector_store = process_safety_with_chroma(raw_data)
qa_system = create_chatbot(vector_store)
prompt = f"Give me the exact answer for this below query '{query}' in a structured format with a link from the content provided only."
answer = ask_question(qa_system, prompt)
df.at[index, "Answer"] = answer
print("ddddddd")
print(df)
# df.to_csv(file_path, index=False)
return df
|