agno-agi · uzaxirr · Jan 20, 2026 · Jan 20, 2026 · Jan 20, 2026 · Jan 20, 2026
diff --git a/cookbook/learning/support-agent.mdx b/cookbook/learning/support-agent.mdx
@@ -5,7 +5,7 @@

 ## Overview

 A customer support agent that combines all learning stores to provide faster resolutions over time. Uses namespace isolation for multi-tenant deployments where different organizations share the system but have separate knowledge.

 ## Code

@@ -100,14 +100,18 @@
 
 ```bash
 git clone https://github.com/agno-agi/agno.git
-cd agno/cookbook/08_learning
+cd agno
 
 # Setup (requires Docker for Postgres)
-./setup_venv.sh
+./cookbook/08_learning/setup_venv.sh
 ./cookbook/scripts/run_pgvector.sh
 
+# Activate the environment and set API key
+source .venvs/learning/bin/activate
+export OPENAI_API_KEY=***
+
 # Run
-python 07_patterns/support_agent.py
+python cookbook/08_learning/07_patterns/support_agent.py
 ```
 
 Full source: [agno/cookbook/08_learning/07_patterns/support_agent.py](https://github.com/agno-agi/agno/blob/main/cookbook/08_learning/07_patterns/support_agent.py)

diff --git a/cookbook/streamlit/agentic-rag.mdx b/cookbook/streamlit/agentic-rag.mdx
@@ -1,32 +1,23 @@
 ---
-title: Agentic RAG
+title: Knowledge Agent (Agentic RAG)
 description: Document Q&A with knowledge base, citations, and conversation memory.
 ---
 
 A sophisticated RAG (Retrieval Augmented Generation) system that leverages search of a knowledge base with LLMs to provide deep insights into the data.

 
 ## The agent can:
 - Process and understand documents from multiple sources (PDFs, websites, text files)
-- Build a searchable knowledge base using vector embeddings
+- Build a searchable knowledge base using vector embeddings with hybrid search
 - Maintain conversation context and memory across sessions
 - Provide relevant citations and sources for its responses
-- Generate summaries and extract key insights
-- Answer follow-up questions and clarifications
+- Handle uncertainty gracefully (ambiguous queries, partial matches, conflicting sources)
 
 ## The agent uses:
-- Vector similarity search for relevant document retrieval
-- Conversation memory for contextual responses
+- Hybrid search (semantic + keyword) for relevant document retrieval
+- Conversation memory for contextual responses (5 turns)
 - Citation tracking for source attribution
-- Dynamic knowledge base updates
-
-<video
-  autoPlay
-  muted
-  controls
-  className="w-full aspect-video"
-  src="/videos/agentic_rag.mp4"
-></video>
+- ReasoningTools for think/analyze capabilities
 
 ## Example queries to try:
 - "What are the key points from this document?"
@@ -35,11 +26,10 @@
 - "How does this relate to [topic X]?"
 - "What are the limitations or gaps in this analysis?"
 - "Can you explain [concept X] in more detail?"
-- "What other sources support or contradict these claims?"
 
 ## Code
 
-The complete code is available in the [Agno repository](https://github.com/agno-agi/agno).
+The complete code is available in the [Agno repository](https://github.com/agno-agi/agno/tree/main/cookbook/01_showcase/01_agents/knowledge_agent).
 
 ## Usage
 
@@ -60,7 +50,7 @@
 
   <Step title="Install dependencies">
     ```bash
-    uv pip install -r cookbook/02_examples/streamlit_apps/agentic_rag/requirements.txt
+    pip install agno openai psycopg[binary] pgvector
     ```
   </Step>
 
@@ -86,24 +76,29 @@
     ```
   </Step>
 
-
   <Step title="Set up API keys">
     ```bash
-    # Required
     export OPENAI_API_KEY=***
-    # Optional
-    export ANTHROPIC_API_KEY=***
-    export GOOGLE_API_KEY=***
+    ```
+  </Step>
 
+  <Step title="Load knowledge base">
+    ```bash
+    python cookbook/01_showcase/01_agents/knowledge_agent/scripts/load_knowledge.py
     ```
-    We recommend using gpt-5-mini for optimal performance.
   </Step>
 
-  <Step title="Launch the app">
+  <Step title="Run examples">
     ```bash
-    streamlit run cookbook/02_examples/streamlit_apps/agentic_rag/app.py
+    # Basic Q&A
+    python cookbook/01_showcase/01_agents/knowledge_agent/examples/basic_query.py
+
+    # Multi-turn conversation
+    python cookbook/01_showcase/01_agents/knowledge_agent/examples/conversation.py
+
+    # Edge cases and uncertainty
+    python cookbook/01_showcase/01_agents/knowledge_agent/examples/edge_cases.py
     ```
-    Open localhost:8501 to start using the Agentic RAG.
   </Step>
 </Steps>
 

diff --git a/cookbook/streamlit/answer-engine.mdx b/cookbook/streamlit/answer-engine.mdx
@@ -8,8 +8,8 @@
 Sage:
 1. Uses real-time web search (DuckDuckGo) and deep contextual analysis (ExaTools) to provide comprehensive answers
 2. Intelligently selects tools based on query complexity
 3. Provides an interactive Streamlit UI with session management and chat history export
 4. Supports multiple LLM providers (OpenAI, Anthropic, Google, Groq)

 ## Key capabilities
 - Natural language query understanding and processing
@@ -18,20 +18,12 @@
 - Multiple LLM provider support
 - Session management using SQLite
 - Chat history export
 - Interactive Streamlit UI
 
-<video
-  autoPlay
-  muted
-  controls
-  className="w-full aspect-video"
-  src="/videos/answer-engine.mp4"
-></video>
-
 ## Simple queries to try
 - "Tell me about the tariffs the US is imposing in 2025"
 - "Which is a better reasoning model: o3-mini or DeepSeek R1?"
 - "Tell me about Agno"
 - "What are the latest trends in renewable energy?"

 ## Advanced analysis queries
@@ -42,7 +34,7 @@
 
 ## Code
 
-The complete code is available in the [Agno repository](https://github.com/agno-agi/agno).
+The complete code is available in the [Agno repository](https://github.com/agno-agi/agno/tree/main/cookbook/01_showcase/01_agents/research_agent).
 
 ## Usage
 
@@ -63,29 +55,31 @@
 
   <Step title="Install dependencies">
     ```bash
-    uv pip install -r cookbook/02_examples/streamlit_apps/answer_engine/requirements.txt
+    pip install agno openai parallel-web
     ```
   </Step>
 
   <Step title="Set up API keys">
     ```bash
-    # Required
     export OPENAI_API_KEY=***
-    export EXA_API_KEY=***
-
-    # Optional (for additional models)
-    export ANTHROPIC_API_KEY=***
-    export GOOGLE_API_KEY=***
-    export GROQ_API_KEY=***
+    export PARALLEL_API_KEY=***
     ```
-    We recommend using gpt-5-mini for optimal performance.
   </Step>
 
-  <Step title="Launch the app">
+  <Step title="Run examples">
     ```bash
-    streamlit run cookbook/02_examples/streamlit_apps/answer_engine/app.py
+    # Fast overview research (3-5 sources)
+    python cookbook/01_showcase/01_agents/research_agent/examples/quick_research.py
+
+    # Comprehensive investigation (10-15 sources)
+    python cookbook/01_showcase/01_agents/research_agent/examples/deep_research.py
+
+    # Comparison and decision support
+    python cookbook/01_showcase/01_agents/research_agent/examples/comparative.py
+
+    # Automated accuracy testing
+    python cookbook/01_showcase/01_agents/research_agent/examples/evaluate.py
     ```
-    Open localhost:8501 to start using Sage.
   </Step>
 </Steps>
 
@@ -94,7 +88,7 @@
 - OpenAI (o3-mini, gpt-5-mini)
 - Anthropic (claude-3-5-sonnet)
 - Google (gemini-2.0-flash-exp)
 - Groq (llama-3.3-70b-versatile)

 ## Agent Configuration
 The agent configuration is in `agents.py` and the prompts are in `prompts.py`:

diff --git a/cookbook/streamlit/overview.mdx b/cookbook/streamlit/overview.mdx
@@ -1,7 +1,7 @@
 ---
 title: Streamlit Apps
 sidebarTitle: Overview
 description: 3 production-ready applications with Streamlit UI for RAG, SQL, and search.
 ---

 Full-stack AI applications - not toy demos. Each app solves a real problem with proper architecture.
@@ -29,11 +29,9 @@
 python3 -m venv .venv
 source .venv/bin/activate
 
-# Install for specific app
-uv pip install -r cookbook/02_examples/streamlit_apps/agentic_rag/requirements.txt
+# Install agno
+pip install agno
 
-# Run
-streamlit run cookbook/02_examples/streamlit_apps/agentic_rag/app.py
+# Run an example
+python cookbook/01_showcase/01_agents/text_to_sql/examples/basic_queries.py
 ```
-
-Open `localhost:8501` to use the application.
diff --git a/cookbook/streamlit/text-to-sql.mdx b/cookbook/streamlit/text-to-sql.mdx
@@ -1,33 +1,26 @@
 ---
-title: SQL Agent
-description: Natural language to SQL with dynamic few-shot learning and Agentic RAG.
+title: Text to SQL Agent
+description: Natural language to SQL with dynamic few-shot learning and self-learning capabilities.
 ---
 
-A text-to-SQL system that:
+A text to SQL system that:
 1. Uses Agentic RAG to search for table metadata, sample queries and rules for writing better SQL queries.
 2. Uses dynamic few-shot examples and rules to improve query construction.
 3. Provides an interactive Streamlit UI for users to query the database.

 We'll use the F1 dataset as an example, but you can easily extend it to other datasets.
 
 ### Key capabilities
 - Natural language to SQL conversion
-- Retrieve table metadata, sample queries and rules using Agentic RAG
-- Better query construction with the help of dynamic few-shot examples and rules
-- Interactive Streamlit UI
-
-<video
-  autoPlay
-  muted
-  controls
-  className="w-full aspect-video"
-  src="/videos/sql_agent.mp4"
-></video>
+- Semantic model for table metadata guidance
+- Knowledge base with query patterns and data quality notes
+- Self-learning workflow (save validated queries for future use)
+- Agentic memory for user preferences across sessions
 
 ### Simple queries to try
 - "Who are the top 5 drivers with the most race wins?"
 - "Compare Mercedes vs Ferrari performance in constructors championships"
 - "Show me the progression of fastest lap times at Monza"
 - "Which drivers have won championships with multiple teams?"
 - "What tracks have hosted the most races?"
 - "Show me Lewis Hamilton's win percentage by season"
@@ -41,7 +34,7 @@
 
 ## Code
 
-The complete code is available in the [Agno repository](https://github.com/agno-agi/agno).
+The complete code is available in the [Agno repository](https://github.com/agno-agi/agno/tree/main/cookbook/01_showcase/01_agents/text_to_sql).
 
 ## Usage
 
@@ -55,14 +48,20 @@
 
   <Step title="Create virtual environment">
     ```bash
-    python3 -m venv .venv
-    source .venv/bin/activate
+    uv venv .venvs/text-to-sql --python 3.12
+    source .venvs/text-to-sql/bin/activate
     ```
   </Step>
 
   <Step title="Install dependencies">
     ```bash
-    uv pip install -r cookbook/02_examples/streamlit_apps/sql_agent/requirements.txt
+    uv pip install -r cookbook/01_showcase/01_agents/text_to_sql/requirements.txt
+    ```
+  </Step>
+
+  <Step title="Set up API keys">
+    ```bash
+    export OPENAI_API_KEY=***
     ```
   </Step>
 
@@ -88,42 +87,34 @@
     ```
   </Step>
 
-  <Step title="Load F1 data">
+  <Step title="Check setup">
     ```bash
-    python cookbook/02_examples/streamlit_apps/sql_agent/load_f1_data.py
+    python cookbook/01_showcase/01_agents/text_to_sql/scripts/check_setup.py
     ```
   </Step>
 
-  <Step title="Load knowledge base">
-    The knowledge base contains table metadata, rules and sample queries that help the Agent generate better responses.
-
+  <Step title="Load data and knowledge">
     ```bash
-    python cookbook/02_examples/streamlit_apps/sql_agent/load_knowledge.py
+    python cookbook/01_showcase/01_agents/text_to_sql/scripts/load_f1_data.py
+    python cookbook/01_showcase/01_agents/text_to_sql/scripts/load_knowledge.py
     ```
-
-    Pro tips for enhancing the knowledge base:
-    - Add `table_rules` and `column_rules` to guide the Agent on query formats
-    - Add sample queries to `cookbook/02_examples/apps/sql_agent/knowledge_base/sample_queries.sql`
   </Step>
 
-  <Step title="Set up API keys">
+  <Step title="Run examples">
     ```bash
-    # Required
-    export OPENAI_API_KEY=***
+    # Basic queries
+    python cookbook/01_showcase/01_agents/text_to_sql/examples/basic_queries.py
 
-    # Optional
-    export ANTHROPIC_API_KEY=***
-    export GOOGLE_API_KEY=***
-    export GROQ_API_KEY=***
-    ```
-    We recommend using gpt-5-mini for optimal performance.
-  </Step>
+    # Self-learning demonstration
+    python cookbook/01_showcase/01_agents/text_to_sql/examples/learning_loop.py
 
-  <Step title="Launch the app">
-    ```bash
-    streamlit run cookbook/02_examples/streamlit_apps/sql_agent/app.py
+    # Data quality edge cases
+    python cookbook/01_showcase/01_agents/text_to_sql/examples/edge_cases.py
+
+    # Evaluate accuracy
+    python cookbook/01_showcase/01_agents/text_to_sql/examples/evaluate.py
     ```
-    Open localhost:8501 to start using the SQL Agent.
+    These scripts will run example text-to-SQL queries and demonstrate the SQL Agent in your terminal.
   </Step>
 </Steps>