returning the query itsef, IDK why

model.py

@@ -37,12 +37,11 @@ class RAGModel:
 
         context = "_ " + "\n-".join(c for c in topk_items)
 
-        base_prompt = f"""Based on the follwing context items, please answer the query. 
-        Give time for yourself to read the context and then answer the query. 
+        base_prompt = f"""Give time for yourself to read the context and then answer the query. 
         Do not return thinking process, just return the answer.
         If you do not find the answer, or if the query is offesnsive or in any other way harmfull just return "I'm not aware of it"
         Now use the following context items to answer the user query.
-        {context}.
+        context: {context}.
         user query : {query} 
         """
 
@@ -56,7 +55,6 @@ class RAGModel:
     def answer_query(self, query: str, topk_items: list[str]):
 
         prompt = self.create_prompt(query, topk_items)
-        print(prompt)
         input_ids = self.tokenizer(prompt, return_tensors="pt").to(self.device)
         output = self.model.generate(**input_ids, max_new_tokens=512)
         text = self.tokenizer.decode(output[0])
@@ -67,12 +65,13 @@ class RAGModel:
 if __name__ == "__main__":
 
     configs = load_configs(config_file="rag.configs.yml")
-    query = "what is LLM"
-    # g = GoogleSearch(query)
-    # data = g.all_page_data
-    # d = Document(data, 512)
-    # s, u = SemanticSearch( "all-mpnet-base-v2", "mps")
-    # topk = s.semantic_search(query=query, k=32)
-    # r = RAGModel(configs)
-    # output = r.answer_query(query=query, topk_items=[""])
-    # print(output)
+    query = "what is computer vision"
+    g = GoogleSearch(query)
+    data = g.all_page_data
+    d = Document(data, 512)
+    doc_chunks = d.doc()
+    s = SemanticSearch(doc_chunks, "all-mpnet-base-v2", "mps")
+    topk, u = s.semantic_search(query=query, k=32)
+    r = RAGModel(configs)
+    output = r.answer_query(query=query, topk_items=topk)
+    print(output)

search.py

@@ -34,12 +34,11 @@ class GoogleSearch:
             for link in sublist
             if len(link) > 0
         ]
-        print(links)
+
         return links
 
     def read_url_page(self, url: str) -> str:
 
-        print(url)
         response = requests.get(url, headers=self.headers)
         response.raise_for_status()
         soup = BeautifulSoup(response.text, "html.parser")
@@ -136,7 +135,7 @@ class SemanticSearch:
         )
 
     def semantic_search(self, query: str, k: int = 10):
-        print("Searhing Top k in document...")
+        print("Searching Top k in document...")
         query_embeding = self.get_embeding(query)
         doc_embeding = self.get_embeding(self.doc_chunks)
         scores = util.dot_score(a=query_embeding, b=doc_embeding)[0]
@@ -147,20 +146,3 @@ class SemanticSearch:
     def get_embeding(self, text: Union[list[str], str]):
         en = self.st.encode(text)
         return en
-
-
-if __name__ == "__main__":
-
-    query = "what is LLM"
-    g = GoogleSearch(query)
-    data = g.all_page_data
-    # d = Document(data, 333)
-    # doc_chunks = d.doc()
-    # s = SemanticSearch(doc_chunks, "all-mpnet-base-v2", "mps")
-    # topk, u = s.semantic_search(query, k=64)
-    # print(len(topk))
-    # print(topk, u)
-
-    # g = GoogleSearch("what is LLM")
-    # d = Document(g.all_page_data)
-    # print(len(d.doc()[0]))