Updated Agentic RAG math tutor

rag_tutorials/agentic_rag_math_agent/README.md

@@ -2,24 +2,19 @@
 
 This project implements an **Agentic-RAG architecture** to simulate a math professor that solves **JEE-level math questions** with step-by-step explanations. The system smartly routes queries between a vector database and web search, applies input/output guardrails, and incorporates human feedback for continuous learning.
 
----
-
 ## 📌 Features
 
 - ✅ **Input Guardrails** (DSPy): Accepts only academic math questions.
 - 📚 **Knowledge Base Search**: Uses **Qdrant Vector DB** with OpenAI Embeddings to match known questions.
 - 🌐 **Web Fallback**: Integrates **Tavily API** when no good match is found.
-- ✍️ **GPT-3.5 Turbo Explanations**: Generates step-by-step math solutions.
+- ✍️ **GPT-4.1 Explanations**: Generates step-by-step math solutions.
 - 🛡️ **Output Guardrails**: Filters for correctness and safety.
 - 👍 **Human-in-the-Loop Feedback**: Users rate answers (Yes/No), logged for future learning.
 - 📊 **Benchmarking**: Evaluated on **JEEBench** dataset with adjustable question limits.
 - 💻 **Streamlit UI**: Interactive dashboard with multiple tabs.
 
----
-
 ## 🚀 Architecture Flow
 
-![image](https://github.com/user-attachments/assets/9197a918-d14e-4759-9b28-8a90dadd1baf)
 
 ## 📚 Knowledge Base
 
@@ -27,36 +22,29 @@ This project implements an **Agentic-RAG architecture** to simulate a math profe
 - **Vector DB:** Qdrant (with OpenAI Embeddings)
 - **Storage:** Built with `llama-index` to persist embeddings and perform top-1 similarity search
 
----
-
 ## 🌐 Web Search
 
 - Uses **Tavily API** for fallback search when the KB doesn't contain a good match
-- Fetched content is piped into **GPT-3.5 Turbo** for clean explanation
+- Fetched content is piped into **GPT-4o** for clean explanation
 
----
 
 ## 🔐 Guardrails
 
 - **Input Guardrail (DSPy):** Accepts only math-related academic questions
 - **Output Guardrail (DSPy):** Blocks hallucinated or off-topic content
 
----
 
 ## 👨‍🏫 Human-in-the-Loop Feedback
 
 - Streamlit UI allows students to give 👍 / 👎 after seeing the answer
 - Feedback is logged to a local JSON file for future improvement
 
----
-
 ## 📊 Benchmarking
 
 - Evaluated on **50 random JEEBench Math Questions**
 - **Current Accuracy:** 66%
 - Benchmark results saved to: `benchmark/results.csv`
 
----
 
 ## 🚀 Demo 
 
@@ -65,8 +53,6 @@ To run the app with Streamlit:
 ```bash
 streamlit run app/streamlit.py
 
-----
-
 
 
 

rag_tutorials/agentic_rag_math_agent/logs/feedback_log.json

@@ -63,5 +63,10 @@
     "question": "Let  \ud835\udc53 ( \ud835\udc65 ) = \ud835\udc65 3 \u2212 3 \ud835\udc65 + 1 f(x)=x  3  \u22123x+1. The number of real solutions of the equation \ud835\udc53 ( \ud835\udc53 ( \ud835\udc65 ) ) = 0 f(f(x))=0 is:  Options: (A) 3 (B) 5 (C) 7 (D) 9",
     "answer": "To find the number of real solutions of the equation \ud835\udc53(\ud835\udc53(\ud835\udc65)) = 0, we first need to understand what the function \ud835\udc53(\ud835\udc65) = \ud835\udc65\u00b3 - 3\ud835\udc65 + 1 represents.\n\nThe function \ud835\udc53(\ud835\udc65) = \ud835\udc65\u00b3 - 3\ud835\udc65 + 1 is a cubic function, which means it has at most 3 real roots. To find the real roots of \ud835\udc53(\ud835\udc65), we set \ud835\udc53(\ud835\udc65) = 0 and solve for \ud835\udc65:\n\n\ud835\udc65\u00b3 - 3\ud835\udc65 + 1 = 0\n\nThis equation may have 1, 2, or 3 real roots. Let's assume it has 3 real roots for now.\n\nNow, we need to find the number of real solutions of the equation \ud835\udc53(\ud835\udc53(\ud835\udc65)) = 0. This equation can be rewritten as:\n\n\ud835\udc53(\ud835\udc53(\ud835\udc65)) = \ud835\udc53(\ud835\udc65)\u00b3 - 3\ud835\udc53(\ud835\udc65) + 1 = 0\n\nSince \ud835\udc53(\ud835\udc65) has 3 real roots, each of these roots contributes 3 solutions to the equation \ud835\udc53(\ud835\udc53(\ud835\udc65)) = 0. Therefore, the total number of real solutions of \ud835\udc53(\ud835\udc53(\ud835\udc65)) = 0 is 3 * 3 = 9.\n\nTherefore, the correct answer is (D) 9, as stated in the web content provided.",
     "feedback": "positive"
+  },
+  {
+    "question": "Let  \ud835\udc53 ( \ud835\udc65 ) = ln \u2061 ( sin \u2061 \ud835\udc65 ) + ln \u2061 ( tan \u2061 \ud835\udc65 ) f(x)=ln(sinx)+ln(tanx). Find the domain of the function  \ud835\udc53 ( \ud835\udc65 ) f(x) in the interval  ( 0 , \ud835\udf0b ) (0,\u03c0).",
+    "answer": "To find the domain of the function \\( f(x) = \\ln(\\sin x) + \\ln(\\tan x) \\) in the interval \\( (0, \\pi) \\), we need to determine where both \\(\\ln(\\sin x)\\) and \\(\\ln(\\tan x)\\) are defined.\n\n### Step-by-Step Explanation:\n\n1. **Understanding the Natural Logarithm:**\n   - The natural logarithm function \\(\\ln(y)\\) is defined only for \\(y > 0\\).\n\n2. **Analyzing \\(\\ln(\\sin x)\\):**\n   - \\(\\sin x > 0\\) in the interval \\( (0, \\pi) \\).\n   - Therefore, \\(\\ln(\\sin x)\\) is defined for all \\(x\\) in \\( (0, \\pi) \\).\n\n3. **Analyzing \\(\\ln(\\tan x)\\):**\n   - \\(\\tan x = \\frac{\\sin x}{\\cos x}\\).\n   - For \\(\\ln(\\tan x)\\) to be defined, \\(\\tan x > 0\\), which means \\(\\sin x > 0\\) and \\(\\cos x > 0\\).\n   - \\(\\cos x > 0\\) in the interval \\( (0, \\frac{\\pi}{2}) \\).\n   - \\(\\tan x\\) is undefined at \\(x = \\frac{\\pi}{2}\\) because \\(\\cos x = 0\\) there.\n\n4. **Combining the Conditions:**\n   - Both \\(\\ln(\\sin x)\\) and \\(\\ln(\\tan x)\\) are defined when \\(x\\) is in \\( (0, \\frac{\\pi}{2}) \\) and \\( (\\frac{\\pi}{2}, \\pi) \\).\n   - At \\(x = \\frac{\\pi}{2}\\), \\(\\tan x\\) is undefined, so \\(x = \\frac{\\pi}{2}\\) is excluded from the domain.\n\n5. **Conclusion:**\n   - The domain of \\( f(x) = \\ln(\\sin x) + \\ln(\\tan x) \\) in the interval \\( (0, \\pi) \\) is \\( (0, \\frac{\\pi}{2}) \\cup (\\frac{\\pi}{2}, \\pi) \\).\n\nThis step-by-step analysis confirms that the domain of the function \\( f(x) \\) is indeed \\( (0, \\frac{\\pi}{2}) \\cup (\\frac{\\pi}{2}, \\pi) \\), excluding \\(x = \\frac{\\pi}{2}\\) where \\(\\tan x\\) is undefined.",
+    "feedback": "positive"
   }
 ]

rag_tutorials/agentic_rag_math_agent/rag/guardrails.py

@@ -8,7 +8,7 @@ OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
 print("🔐 Loaded OPENAI_API_KEY:", "✅ Found" if OPENAI_API_KEY else "❌ Missing")
 
 # Configure LM
-lm = dspy.LM(model="gpt-3.5-turbo", api_key=OPENAI_API_KEY)
+lm = dspy.LM(model="gpt-4o", api_key=OPENAI_API_KEY)
 dspy.configure(lm=lm)
 
 # ✅ Signature for Input Guard

rag_tutorials/agentic_rag_math_agent/rag/query_router.py

@@ -6,7 +6,7 @@ sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
 
 import os
 import requests
-import openai  # ✅ now using the real OpenAI SDK
+import openai  
 import json
 import inspect
 from llama_index.core import StorageContext,load_index_from_storage
@@ -78,7 +78,7 @@ Web Content:
 Now write a clear, accurate, and step-by-step explanation of the student's question.
 Only include valid math steps — do not guess or make up answers.
 """
-    llm = OpenAI(api_key=OPENAI_API_KEY, model="gpt-3.5-turbo")
+    llm = OpenAI(api_key=OPENAI_API_KEY, model="gpt-4o")
     response = llm.complete(prompt)
     return response.text
 
@@ -118,7 +118,7 @@ Do not change the final answer. You are only allowed to explain what is already
 Use the KB content as your only source. Do not guess or recalculate.
 """
 
-            llm = OpenAI(api_key=OPENAI_API_KEY, model="gpt-3.5-turbo")
+            llm = OpenAI(api_key=OPENAI_API_KEY, model="gpt-4o")
             answer = llm.complete(prompt).text
             from_kb = True
         else:

starter_ai_agents/agentic_rag_math_agent/storage/docstore.json

@@ -1 +0,0 @@
-{}

starter_ai_agents/agentic_rag_math_agent/storage/graph_store.json

@@ -1 +0,0 @@
-{"graph_dict": {}}

starter_ai_agents/agentic_rag_math_agent/storage/image__vector_store.json

@@ -1 +0,0 @@
-{"embedding_dict": {}, "text_id_to_ref_doc_id": {}, "metadata_dict": {}}

starter_ai_agents/agentic_rag_math_agent/storage/index_store.json

@@ -1 +0,0 @@
-{"index_store/data": {"b8b2a959-cac2-4df4-808b-9edf8eda98ff": {"__type__": "vector_store", "__data__": "{\"index_id\": \"b8b2a959-cac2-4df4-808b-9edf8eda98ff\", \"summary\": null, \"nodes_dict\": {}, \"doc_id_dict\": {}, \"embeddings_dict\": {}}"}}}