reworked document adding and most of the project

local_rag.py

@@ -12,6 +12,23 @@ from langchain_ollama import ChatOllama
 from langchain_openai import ChatOpenAI
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 
+# Pipeline tuning: used when adding documents (rebuild index after changing).
+CHUNK_SIZE = 2000
+CHUNK_OVERLAP = 400
+
+# Retrieval / query tuning
+RETRIEVAL_K = 5
+
+# Appended to the embedding query for FAISS (does not affect the answer-generation prompt).
+QUERY_ADDITIONAL_INSTRUCTIONS = (
+    "Do not return a list of references but prioritize meaningful text from abstracts, results and discussion sections."
+)
+
+# Opening instructions for the final answer LLM call only. The rest (history, context, question)
+# is assembled in query_with_history.
+ANSWER_PROMPT = """You are an assistant for question-answering. Use the chat history (if any) and the retrieved context below to answer the current question.
+If you don't know the answer, say so. Keep the conversation coherent."""
+
 
 class LocalRAG:
     def __init__(
@@ -19,7 +36,7 @@ class LocalRAG:
         vectorstore_path="./vectorstore",
         llm_provider="ollama",
         ollama_model="gpt-oss:20b",
-        openai_model="gpt-5.2",
+        openai_model="gpt-5-mini",
         ollama_base_url="http://localhost:11434",
     ):
         """Initialize local RAG system. llm_provider: 'ollama' or 'openai'."""
@@ -32,11 +49,12 @@ class LocalRAG:
             model_name="sentence-transformers/all-MiniLM-L6-v2"
         )
 
-        # Text splitter
+        # Text splitter (used when adding documents; tune CHUNK_SIZE / CHUNK_OVERLAP above)
         self.text_splitter = RecursiveCharacterTextSplitter(
-            chunk_size=2000,
-            chunk_overlap=400
+            chunk_size=CHUNK_SIZE,
+            chunk_overlap=CHUNK_OVERLAP,
         )
+        print(f"Text splitter: chunk_size={CHUNK_SIZE}, chunk_overlap={CHUNK_OVERLAP}")
 
         # LLM (Ollama or OpenAI)
         if llm_provider == "openai":
@@ -186,15 +204,19 @@ class LocalRAG:
             for doc, score in docs_with_scores
         ]
 
-    def query(self, question, k=8):
+    def query(self, question, k=None):
         """Query the RAG system (no conversation history). Returns dict with 'answer' and 'retrieved'."""
+        if k is None:
+            k = RETRIEVAL_K
         return self.query_with_history(question, chat_history=[], k=k)
 
-    def query_with_history(self, question, chat_history=None, k=8):
+    def query_with_history(self, question, chat_history=None, k=None):
         """Query the RAG with conversation history: rephrase question using history for retrieval,
         then answer with full conversation + retrieved context in the prompt.
         Returns dict with 'answer' and 'retrieved' (list of chunks with content, source, page).
         """
+        if k is None:
+            k = RETRIEVAL_K
         if self.vectorstore is None:
             return {
                 "answer": "Error: No documents loaded. Please add documents first.",
@@ -203,9 +225,6 @@ class LocalRAG:
 
         history_str = self._format_history(chat_history)
         search_query = question
-        rag_query_instruction = (
-            "Do not return a list of references but prioritize meaningful text from abstracts, results and discussion sections."
-        )
 
         print(f"[RAG] User question: {question!r}")
 
@@ -224,7 +243,7 @@ Standalone question:"""
             search_query = (rephrase_response.content if hasattr(rephrase_response, "content") else str(rephrase_response)).strip() or question
             print(f"[RAG] Standalone search query (rephrased): {search_query!r}")
 
-        retrieval_query = f"{search_query}\n\n{rag_query_instruction}"
+        retrieval_query = f"{search_query}\n\n{QUERY_ADDITIONAL_INSTRUCTIONS}"
         print(f"[RAG] Search query: {search_query!r}")
         print(f"[RAG] Retrieval query sent to vector store: {retrieval_query!r}")
 
@@ -239,8 +258,9 @@ Standalone question:"""
 
         # 3) Answer using conversation history + retrieved context
         history_block = f"Chat history:\n{history_str}\n\n" if history_str else ""
-        answer_prompt = f"""You are an assistant for question-answering. Use the chat history (if any) and the retrieved context below to answer the current question.
-        If you don't know the answer, say so. Keep the conversation coherent.
+        answer_prompt = (
+            ANSWER_PROMPT
+            + f"""
 
 {history_block}Relevant context from documents:
 
@@ -249,6 +269,8 @@ Standalone question:"""
 Current question: {question}
 
 Answer:"""
+        )
+        print(f"[RAG] Composed answer prompt:\n{answer_prompt}")
         response = self.llm.invoke(answer_prompt)
         answer = response.content if hasattr(response, "content") else str(response)