Update the docs for teams knowledge changes (#203)

Author: dirkbrnd

_snippets/team-reference.mdx

@@ -13,14 +13,20 @@
 | `description` | `Optional[str]` | `None` | A description of the team that is added to the start of the system message |
 | `instructions` | `Optional[Union[str, List[str], Callable]]` | `None` | List of instructions for the team |
 | `expected_output` | `Optional[str]` | `None` | Provide the expected output from the team |
+| `additional_context` | `Optional[str]` | `None` | Additional context added to the end of the system message |
 | `success_criteria` | `Optional[str]` | `None` | Define the success criteria for the team |
 | `markdown` | `bool` | `False` | If markdown=true, add instructions to format the output using markdown |
 | `add_datetime_to_instructions` | `bool` | `False` | If True, add the current datetime to the instructions to give the agent a sense of time |
+| `knowledge` | `Optional[AgentKnowledge]` | `None` | Add a knowledge base to the team |
+| `retriever` | `Optional[Callable[..., Optional[List[Dict]]]]` | `None` | Function to get references to add to the user_message |
+| `references_format` | `Literal["json", "yaml"]` | `"json"` | Format of the references |
 | `context` | `Optional[Dict[str, Any]]` | `None` | User provided context |
 | `add_context` | `bool` | `False` | If True, add the context to the user prompt |
 | `enable_agentic_context` | `bool` | `False` | If True, enable the team agent to update the team context and automatically send the team context to the members |
 | `share_member_interactions` | `bool` | `False` | If True, send all previous member interactions to members |
 | `read_team_history` | `bool` | `False` | If True, read the team history |
+| `search_knowledge` | `bool` | `True` | Add a tool that allows the Model to search the knowledge base |
+| `get_member_information_tool` | `bool` | `True` | Add a tool that allows the Model to get information about the members of the team |
 | `show_tool_calls` | `bool` | `False` | Show tool calls in team response |
 | `response_model` | `Optional[Type[BaseModel]]` | `None` | Response model for the team response |
 | `use_json_mode` | `bool` | `False` | If `response_model` is set, sets the response "mode" of the model, i.e. if the model should explicitly respond with a JSON object instead of a Pydantic model |

teams/introduction.mdx

@@ -128,6 +128,64 @@ team_with_memory.print_response("What are the key challenges in quantum computin
 team_with_memory.print_response("Elaborate on the second challenge you mentioned")
 ```
 
+## Team Knowledge
+
+Teams can use a knowledge base to store and retrieve information:
+
+```python
+from pathlib import Path
+
+from agno.agent import Agent
+from agno.embedder.openai import OpenAIEmbedder
+from agno.knowledge.url import UrlKnowledge
+from agno.models.openai import OpenAIChat
+from agno.team import Team
+from agno.tools.duckduckgo import DuckDuckGoTools
+from agno.vectordb.lancedb import LanceDb, SearchType
+
+# Setup paths
+cwd = Path(__file__).parent
+tmp_dir = cwd.joinpath("tmp")
+tmp_dir.mkdir(parents=True, exist_ok=True)
+
+# Initialize knowledge base
+agno_docs_knowledge = UrlKnowledge(
+    urls=["https://docs.agno.com/llms-full.txt"],
+    vector_db=LanceDb(
+        uri=str(tmp_dir.joinpath("lancedb")),
+        table_name="agno_docs",
+        search_type=SearchType.hybrid,
+        embedder=OpenAIEmbedder(id="text-embedding-3-small"),
+    ),
+)
+
+web_agent = Agent(
+    name="Web Search Agent",
+    role="Handle web search requests",
+    model=OpenAIChat(id="gpt-4o"),
+    tools=[DuckDuckGoTools()],
+    instructions=["Always include sources"],
+)
+
+team_with_knowledge = Team(
+    name="Team with Knowledge",
+    members=[web_agent],
+    model=OpenAIChat(id="gpt-4o"),
+    knowledge=agno_docs_knowledge,
+    show_members_responses=True,
+    markdown=True,
+)
+
+if __name__ == "__main__":
+    # Set to False after the knowledge base is loaded
+    load_knowledge = True
+    if load_knowledge:
+        agno_docs_knowledge.load()
+
+    team_with_knowledge.print_response("Tell me about the Agno framework", stream=True)
+```
+
+
 ## Running Teams
 
 Teams support both synchronous and asynchronous execution, with optional streaming: