added modules file

modules/knowledge_graph.py

@@ -0,0 +1,21 @@
+import numpy as np
+from sentence_transformers import SentenceTransformer
+import faiss
+import pandas as pd
+
+def search_kg(query, index_path, dataset_path, top_k=5):
+    index = faiss.read_index(index_path)
+    df = pd.read_json(dataset_path, lines=True)
+
+    model = SentenceTransformer('all-MiniLM-L6-v2')
+    query_embedding = model.encode([query], convert_to_tensor=True).cpu().numpy()
+    distances, indices = index.search(query_embedding, top_k)
+
+    results = []
+    for i in range(top_k):
+        idx = indices[0][i]
+        if 0 <= idx < len(df):
+            headline = df.iloc[idx]['headline']
+            description = df.iloc[idx]['short_description']
+            results.append(f"{headline}. {description}")
+    return " ".join(results)

modules/online_search.py

@@ -0,0 +1,46 @@
+from openai import OpenAI
+
+def search_online(query, api_key, base_url, model):
+    messages = [
+        {
+            "role": "system",
+            "content": (
+                "You are an artificial intelligence assistant and you need to "
+                "engage in a helpful, detailed, polite conversation with a user."
+            ),
+        },
+        {"role": "user", "content": query},
+    ]
+    
+    client = OpenAI(api_key=api_key, base_url=base_url)
+    response = client.chat.completions.create(
+        model=model,
+        messages=messages,
+    )
+
+    # print(type(response))
+    # print(response)
+    # print(vars(response)) 
+    result = process_result(response)
+    return result
+
+def process_result(response):
+    # Create a dictionary to hold all the individual pieces of information
+    response_dict = {
+        # 'finish_reason': response.choices[0].finish_reason,
+        # 'index': response.choices[0].index,
+        'message_content': response.choices[0].message.content,
+        # 'delta_role': response.choices[0].delta['role'] if response.choices[0].delta else None,
+        # 'delta_content': response.choices[0].delta['content'] if response.choices[0].delta else None,
+        # 'created': response.created,
+        # 'object': response.object,
+        # 'usage_completions_tokens': response.usage.completion_tokens,
+        'citations': response.citations  # Assuming `citations` is part of the response object
+    }
+
+    return response_dict
+
+
+
+# result = search_online("", "", "", "")
+# print(result)

modules/validation.py

@@ -0,0 +1,6 @@
+from transformers import pipeline
+
+def calculate_truthfulness_score(info, context):
+    classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
+    result = classifier(info, [context], multi_label=False)
+    return result['scores'][0]