Adding Files

app.py

@@ -8,6 +8,7 @@ import gradio as gr
 import os
 
 # initialising the locally saved vectorstore from artifacts
+player_names = pd.read_csv("artifacts/data.csv", encoding = "latin-1")["Name"].to_list()
 model_name = "sentence-transformers/all-mpnet-base-v2"
 embeddings = HuggingFaceEmbeddings(model_name = model_name)
 vectorstore = FAISS.load_local("artifacts/FAISS-Vectorstore", embeddings)
@@ -16,27 +17,22 @@ vectorstore = FAISS.load_local("artifacts/FAISS-Vectorstore", embeddings)
 def generate_response(input_query):
     result = vectorstore.similarity_search_with_relevance_scores(input_query, k = 4)
     PROMPT_TEMPLATE = """
-    Consider yourself to be a football expert who has been given the task to answer a question
-    based on some of the content you are provided with along with their some relevance scores.
-    Please restrict your knowledge to only the given content and do not add up anything on your own.
-    Also make sure that if the top relevance score is less than 0.25, generate a response that you weren't able
-    to find anything relevant from the knowledge base.
+    Consider yourself to be a football expert who knows everything about 35 greatest football players of all time 
+    according to "The Guardian", the names of the 35 players are : {names}. 
+    Now you have been given the task to answer a question and have also been given some content which you can take help of
+    to generate a proper and much detailed response. You are completely free to elaborate and add more details if they are correct.
 
     Here's the question which you have been asked :
     {question}
 
     Here's the content you are provided with :
     {content}
-
-    Here's the maximum relevance score :
-    {score}
     """
 
     content = "\n-----\n".join([x[0].page_content for x in result])
-    score = max([x[1] for x in result])
 
     prompt = PromptTemplate.from_template(PROMPT_TEMPLATE)
-    prompt = prompt.format(question = input_query, content = content, score = score)
+    prompt = prompt.format(question = input_query, content = content, names = player_names)
 
     llm = OpenAI(api_key = os.getenv("OPENAI_API_KEY"), temperature = 0.95)
     response = llm.predict(prompt).strip()

faiss_setup.py

@@ -7,7 +7,7 @@ import pandas as pd
 from tqdm import tqdm
 
 # reading names of the players in the data and displaying few of them
-players = pd.read_csv("artifacts\data.csv", encoding = "latin-1")["Name"].to_list()
+players = pd.read_csv("artifacts/data.csv", encoding = "latin-1")["Name"].to_list()
 
 # extracting information about the players from their wikipedia pages
 content = ""