Merge branch 'main' of https://github.com/phidatahq/agno-docs

Author: dirkbrnd

_snippets/memory-redis-reference.mdx

@@ -0,0 +1,9 @@
+### Parameters
+
+| Parameter | Type | Description | Default |
+|-----------|------|-------------|---------|
+| `prefix` | `str` | Prefix for Redis keys to namespace the memories | `"agno_memory"` |
+| `host` | `str` | Redis host address | `"localhost"` |
+| `port` | `int` | Redis port number | `6379` |
+| `db` | `int` | Redis database number | `0` |
+| `password` | `Optional[str]` | Redis password if authentication is required | `None` |

examples/concepts/memory/mem-redis-memory.mdx

@@ -0,0 +1,101 @@
+---
+title: Redis Memory Storage
+---
+
+## Code
+
+```python cookbook/agent_concepts/memory/redis_memory.py
+"""
+This example shows how to use the Memory class with Redis storage.
+"""
+
+from agno.agent.agent import Agent
+from agno.memory.v2.db.redis import RedisMemoryDb
+from agno.memory.v2.memory import Memory
+from agno.models.openai import OpenAIChat
+from agno.storage.redis import RedisStorage
+
+# Create Redis memory database
+memory_db = RedisMemoryDb(
+    prefix="agno_memory",  # Prefix for Redis keys to namespace the memories
+    host="localhost",      # Redis host address
+    port=6379,             # Redis port number
+)
+
+# Create memory instance with Redis backend
+memory = Memory(db=memory_db)
+
+# This will clear any existing memories
+memory.clear()
+
+# Session and user identifiers
+session_id = "redis_memories"
+user_id = "redis_user"
+
+# Create agent with memory and Redis storage
+agent = Agent(
+    model=OpenAIChat(id="gpt-4o-mini"),
+    memory=memory,
+    storage=RedisStorage(prefix="agno_test", host="localhost", port=6379),
+    enable_user_memories=True,
+    enable_session_summaries=True,
+)
+
+# First interaction - introducing personal information
+agent.print_response(
+    "My name is John Doe and I like to hike in the mountains on weekends.",
+    stream=True,
+    user_id=user_id,
+    session_id=session_id,
+)
+
+# Second interaction - testing if memory was stored
+agent.print_response(
+    "What are my hobbies?", 
+    stream=True, 
+    user_id=user_id, 
+    session_id=session_id
+)
+
+# Display the memories stored in Redis
+memories = memory.get_user_memories(user_id=user_id)
+print("Memories stored in Redis:")
+for i, m in enumerate(memories):
+    print(f"{i}: {m.memory}")
+```
+
+## Usage
+
+<Steps>
+  <Snippet file="create-venv-step.mdx" />
+
+  <Step title="Set environment variables">
+    ```bash
+    export OPENAI_API_KEY=xxx
+    ```
+  </Step>
+
+  <Step title="Install libraries">
+    ```bash
+    pip install -U agno openai redis
+    ```
+  </Step>
+
+  <Step title="Run Redis">
+    ```bash
+    docker run --name my-redis -p 6379:6379 -d redis
+    ```
+  </Step>
+
+  <Step title="Run Example">
+    <CodeGroup>
+    ```bash Mac/Linux
+    python cookbook/agent_concepts/memory/redis_memory.py
+    ```
+
+    ```bash Windows
+    python cookbook/agent_concepts/memory/redis_memory.py
+    ```
+    </CodeGroup>
+  </Step>
+</Steps>

faq/When-to-use-a-Workflow-vs-a-Team-in-Agno.mdx

@@ -0,0 +1,40 @@
+---
+title: When to use a Workflow vs a Team in Agno
+sidebarTitle: When to use a Workflow vs a Team in Agno
+---
+
+Agno offers two powerful ways to build multi-agent systems: **Workflows** and **Teams**. Each is suited for different kinds of use-cases.
+
+---
+
+## Use a Workflow when:
+
+You want to execute a fixed series of steps with a predictable outcome.
+
+Workflows are ideal for:
+
+- Step-by-step agent executions
+- Data extraction or transformation
+- Tasks that don’t need reasoning or decision-making
+
+[Learn more about Workflows](https://docs.agno.com/workflows/introduction)
+
+---
+
+## Use an Agent Team when:
+
+Your task requires reasoning, collaboration, or multi-tool decision-making.
+
+Agent Teams are best for:
+
+- Research and planning
+- Tasks where agents divide responsibilities
+
+[Learn more about Agent Teams](https://docs.agno.com/teams/introduction)
+
+---
+
+## 💡 Pro Tip
+
+> Think of **Workflows** as assembly lines for known tasks,
+> and **Agent Teams** as collaborative task forces for solving open-ended problems.

memory/storage.mdx

@@ -10,9 +10,10 @@ Agno's memory system provides persistent storage options to ensure memories are
 
 The Memory class supports different backend storage options through a pluggable database interface. Currently, Agno provides:
 
-1. [SQLite Storage](/reference/memory/sqlite)
-2. [PostgreSQL Storage](/reference/memory/postgres)
-3. [MongoDB Storage](/reference/memory/mongodb)
+1. [SQLite Storage](/reference/memory/storage/sqlite.mdx)
+2. [PostgreSQL Storage](/reference/memory/storage/postgres.mdx)
+3. [MongoDB Storage](/reference/memory/storage/mongo.mdx)
+4. [Redis Storage](/reference/memory/storage/redis.mdx)
 
 ## Setting Up Storage
 

mint.json

@@ -530,6 +530,7 @@
             "examples/concepts/memory/10-multi-user-multi-session-chat",
             "examples/concepts/memory/mem-mongodb-memory",
             "examples/concepts/memory/mem-postgres-memory",
+            "examples/concepts/memory/mem-redis-memory",
             "examples/concepts/memory/mem0-memory"
           ]
         },
@@ -1107,7 +1108,8 @@
               "pages": [
                 "reference/memory/storage/mongo",
                 "reference/memory/storage/postgres",
-                "reference/memory/storage/sqlite"
+                "reference/memory/storage/sqlite",
+                "reference/memory/storage/redis"
               ]
             }
           ]
@@ -1168,7 +1170,8 @@
         "faq/connecting-to-tableplus",
         "faq/could-not-connect-to-docker",
         "faq/openai_key_request_for_other_models",
-        "faq/structured-outputs"
+        "faq/structured-outputs",
+        "faq/When-to-use-a-Workflow-vs-a-Team-in-Agno"
       ]
     },
     {

reference/memory/storage/redis.mdx

@@ -0,0 +1,7 @@
+---
+title: RedisMemoryDb
+---
+
+RedisMemoryDb is a class that implements the MemoryDb interface using Redis as the backend storage system. It provides persistent storage for agent memories with support for JSONB data types, timestamps, and efficient querying.
+
+<Snippet file="memory-redis-reference.mdx" />