changed rag method flags

README.md

@@ -151,8 +151,8 @@ nano .env  # or use your preferred editor
 
 **Required environment variables:**
 ```bash
-ANTHROPIC_API_KEY=sk-ant-xxxxxxxxxxxxx
-TAVILY_API_KEY=tvly-xxxxxxxxxxxxx
+GOOGLE_API_KEY=xxxxxxxxxxxxx      # Gemini API key
+TAVILY_API_KEY=tvly-xxxxxxxxxxxxx # Enable web search
 ```
 
 ### 5️⃣ Prepare Data
@@ -171,7 +171,6 @@ mkdir -p data/documents data/chroma_db
 python main.py
 ```
 
-The app will be available at: **http://127.0.0.1:7860**
 
 ### 7️⃣ Run Tests (Optional)
 ```bash
@@ -283,11 +282,12 @@ lsof -ti:7860 | xargs kill -9
 
 - [UV Documentation](https://github.com/astral-sh/uv)
 - [LangGraph Docs](https://langchain-ai.github.io/langgraph/)
-- [Anthropic API](https://docs.anthropic.com/)
+- [Gemini API](https://ai.google.dev/gemini-api/docs/api-key)
 - [Tavily API](https://docs.tavily.com/)
 - [ChromaDB Docs](https://docs.trychroma.com/)
 
-## 📚 Reference 
+## 📚 Reference (Used for demo as document in vector store)
+
 1. Wei, H., Sun, Y., & Li, Y. (2025). Deepseek-ocr: Contexts optical compression. arXiv preprint arXiv:2510.18234.
 2. Chen, X., Chu, F. J., Gleize, P., Liang, K. J., Sax, A., Tang, H., ... & SAM 3D Team. (2025). SAM 3D: 3Dfy Anything in Images. arXiv preprint arXiv:2511.16624.
 3. Carion, N., Gustafson, L., Hu, Y. T., Debnath, S., Hu, R., Suris, D., ... & Feichtenhofer, C. (2025). SAM 3: Segment Anything with Concepts. arXiv preprint arXiv:2511.16719.

agent/graph.py

@@ -40,8 +40,8 @@ def create_agent_graph(llm, vectordb, search_tools) -> StateGraph:
         "web_search_agent_node",
         tools_condition,
         {
-            "tools": "web_search_tool_node",  # Changed key from node name to "tools"
-            "__end__": "generate_node",  # Changed key from "generate_node" to "__end__"
+            "tools": "web_search_tool_node",  
+            "__end__": "generate_node",  
         }
     )
 

agent/nodes.py

@@ -20,7 +20,7 @@ def router_node(state: AgentState, llm):
 
 def routing_logic(state: AgentState) -> str:
     rag_method = state["rag_method"]
-    if rag_method == "RAG":
+    if rag_method == "VECTORDB":
         return "vectordb_node"
     elif rag_method == "WEBSEARCH":
         return "web_search_agent_node"

agent/prompts.py

@@ -15,18 +15,29 @@ def determine_rag_method_prompt() -> str:
 You are a query classification model. Given the user's query, you must classify the method to use
 as one and only one of the following options:
 
-1. **RAG**: The query asks about specific documents, papers, or systems like DeepAnalyze, AgentMem, SAM3, SAM 3, SAM3D, DeepSeek-OCR, or any technical architecture/implementation details from research papers.
-2. **WEBSEARCH**: The query asks for current events, latest news, real-time information after January 2024, or general factual knowledge not in specialized documents.
-3. **GENERAL**: The query is a simple calculation, definition, reasoning task, or common knowledge question that doesn't need external data.
+1. **VECTORDB**: 
+The query asks about specific documents, papers, or systems. 
+This includes technical architecture/implementation details from research papers for DeepAnalyze, AgentMem, SAM3, SAM 3, SAM3D, DeepSeek-OCR
+
+2. **WEBSEARCH**: 
+The query asks for current events, latest news, real-time information after January 2024, or general factual knowledge not in specialized documents.
+
+3. **GENERAL**: 
+The query is a simple calculation, definition, reasoning task, or common knowledge question that doesn't need external data.
 
 **Examples:**
-- "What is DeepAnalyze?" → RAG
-- "Explain SAM 3 architecture" → RAG  
+- "What is DeepAnalyze?" → VECTORDB
+- "Explain SAM 3 architecture" → VECTORDB  
 - "Latest AI news in 2025" → WEBSEARCH
 - "What is 15 times 7?" → GENERAL
 
-Respond STRICTLY with only one word: RAG, WEBSEARCH, or GENERAL. No punctuation or extra text.
+Respond STRICTLY with only one word: VECTORDB, WEBSEARCH, or GENERAL. No punctuation or extra text.
 """
-        
+# For dynamic RAG routing based on user query, each route decision need to clafify what 
+# information can be retrieved from which source.
+# If more than 2 vectorstores are used, the routing logic can to be updated accordingly.
+# Example: VECTORDB1, VECTORDB2, WEBSEARCH, GENERAL
+
+
 if __name__ == "__main__":
     pass

agent/state.py

@@ -14,16 +14,6 @@ class AgentState(TypedDict):
     rag_method: RAG_method
     context: Optional[str]
 
-    questionIsClear: bool
-    conversation_summary: str = ""
-
-
-# Implement later if needed, omit first
-class QueryAnalysis(BaseModel):
-    """Structured output for query analysis"""
-    is_clear: bool = Field(description="Indicates if the user's question is clear and answerable")
-    questions: List[str] = Field(description="List of rewritten, self-contained questions")
-    clarification_needed: str = Field(description="Explanation if the question is unclear")
 
 if __name__ == "__main__":
     pass

config.py

@@ -2,7 +2,7 @@ import os
 
 configs = {
     "DATA_PATH": "./docs/markdowns",
-    "PERSIST_PATH": "./chroma_data",
+    "PERSIST_PATH": "./chroma_data", # modify if want to create another vectorstore like chroma_data_2
     "EMBEDDING_MODEL_NAME": "sentence-transformers/all-mpnet-base-v2",
     "COLLECTION_NAME": "langchain_mpnet_collection",
     "LLM_MODEL_NAME": "gemini-2.0-flash",