updated local deepseek rag app

rag_tutorials/deepseek_local_rag_agent/README.md

@@ -6,7 +6,7 @@ A powerful reasoning agent that combines local Deepseek models with RAG capabili
 
 - **Dual Operation Modes**
   - Local Chat Mode: Direct interaction with Deepseek locally
-  - RAG Mode: Enhanced reasoning with document context and web search integration - llama3.1:8b
+  - RAG Mode: Enhanced reasoning with document context and web search integration - llama3.2
 
 - **Document Processing** (RAG Mode)
   - PDF document upload and processing
@@ -15,7 +15,6 @@ A powerful reasoning agent that combines local Deepseek models with RAG capabili
   - Vector storage in Qdrant cloud
 
 - **Intelligent Querying** (RAG Mode)
-  - Query rewriting using Gemini
   - RAG-based document retrieval
   - Similarity search with threshold filtering
   - Automatic fallback to web search
@@ -50,14 +49,10 @@ ollama pull deepseek-r1:7b
 
 ollama pull snowflake-arctic-embed
 ollama run llama3.2
+ollama pull llama3.2
 ```
 
-### 2. Google API Key (for RAG Mode)
-1. Go to [Google AI Studio](https://aistudio.google.com/apikey)
-2. Sign up or log in to your account
-3. Create a new API key
-
-### 3. Qdrant Cloud Setup (for RAG Mode)
+### 2. Qdrant Cloud Setup (for RAG Mode)
 1. Visit [Qdrant Cloud](https://cloud.qdrant.io/)
 2. Create an account or sign in
 3. Create a new cluster
@@ -65,7 +60,7 @@ ollama run llama3.2
    - Qdrant API Key: Found in API Keys section
    - Qdrant URL: Your cluster URL (format: `https://xxx-xxx.cloud.qdrant.io`)
 
-### 4. Exa AI API Key (Optional)
+### 3. Exa AI API Key (Optional)
 1. Visit [Exa AI](https://exa.ai)
 2. Sign up for an account
 3. Generate an API key for web search capabilities

rag_tutorials/deepseek_local_rag_agent/deepseek_rag_agent.py

@@ -3,10 +3,8 @@ import tempfile
 from datetime import datetime
 from typing import List
 import streamlit as st
-import google.generativeai as genai
 import bs4
 from agno.agent import Agent
-from agno.models.google import Gemini
 from agno.models.ollama import Ollama
 from langchain_community.document_loaders import PyPDFLoader, WebBaseLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
@@ -18,8 +16,14 @@ from agno.tools.exa import ExaTools
 from agno.embedder.ollama import OllamaEmbedder
 
 
-class OllamaEmbedderr(Embeddings):
+class OllamaEmbedder(Embeddings):
     def __init__(self, model_name="snowflake-arctic-embed"):
+        """
+        Initialize the OllamaEmbedderr with a specific model.
+
+        Args:
+            model_name (str): The name of the model to use for embedding.
+        """
         self.embedder = OllamaEmbedder(id=model_name, dimensions=1024)
 
     def embed_documents(self, texts: List[str]) -> List[List[float]]:
@@ -139,8 +143,13 @@ if st.session_state.use_web_search:
 
 
 # Utility Functions
-def init_qdrant():
-    """Initialize Qdrant client with configured settings."""
+def init_qdrant() -> QdrantClient | None:
+    """Initialize Qdrant client with configured settings.
+
+    Returns:
+        QdrantClient: The initialized Qdrant client if successful.
+        None: If the initialization fails.
+    """
     if not all([st.session_state.qdrant_api_key, st.session_state.qdrant_url]):
         return None
     try:
@@ -234,7 +243,7 @@ def create_vector_store(client, texts):
         vector_store = QdrantVectorStore(
             client=client,
             collection_name=COLLECTION_NAME,
-            embedding=OllamaEmbedderr()
+            embedding=OllamaEmbedder()
         )
         
         # Add documents