adding augmented generation

app.py

@@ -16,7 +16,9 @@ Manually Downloaded as HTML files:
 
 ## Details
 
-1. Vector Store is built using FAISS prior to starting this app. Although the vector store size in KBs but the creation and loading of the store takes processing takes ~10GB RAM and lasts 5 mins. Hence **NOT BUILDING IT DURING RUNTIME OF APP**.
+1. Vector Store is built using FAISS prior to starting this app. Although the vector store size in KBs but
+    - the creation and loading of the store takes processing takes ~10GB RAM and lasts 5 mins. Hence **NOT BUILDING IT DURING RUNTIME OF APP**. 
+    - `multi_process=True` was not working with HF Space `free-tier`.
 
 '''
 

z_generate.py

@@ -26,5 +26,48 @@ class ServerlessInference:
     
     def perform_rag(self, query:str):
         # First perform text search 
-        relevant_docs = self.vs_text.similarity_search(query=query, k=5)
-        return relevant_docs[0].page_content
+        # Retrieval 
+        retrieved_docs = self.vs_text.similarity_search(query=query, k=5)
+        retrieved_docs_text = [doc.page_content for doc in retrieved_docs]  # We only need the text of the documents
+        context = "\nExtracted documents:\n"
+        context += "".join([f"Document {str(i)}:::\n" + doc for i, doc in enumerate(retrieved_docs_text)])
+
+        # Augmented Generation
+        messages:str  = [
+            {
+                "role": "system",
+                "content": """Using the information contained in the context,
+
+give a comprehensive answer to the question.
+
+Respond only to the question asked, response should be concise and relevant to the question.
+
+Provide the number of the source document when relevant.
+
+If the answer cannot be deduced from the context, do not give an answer.""",
+
+            },
+
+            {
+                "role": "user",
+                "content": """Context:
+
+{context}
+
+---
+
+Now here is the question you need to answer.
+
+Question: {question}""".format(context=context, question=query),
+
+            },
+        ]
+
+        completion = self.client.chat.completions.create(
+            model=self.model,
+            messages=messages, 
+            max_tokens=500
+        )
+
+        response_text = completion.choices[0].message.content
+        return response_text