Prompts
We prompt Agents using description
and instructions
and a number of other settings. These settings are used to build the system prompt that is sent to the language model.
Understanding how these prompts are created will help you build better Agents.
The 2 key parameters are:
- Description: A description that guides the overall behaviour of the agent.
- Instructions: A list of precise, task-specific instructions on how to achieve its goal.
Description and instructions only provide a formatting benefit, we do not alter or abstract any information and you can always use system_prompt
to provide your own system prompt.
System message
The system message is created using description
, instructions
and a number of other settings. The description
is added to the start of the system message and instructions
are added as a list after ## Instructions
. For example:
Will translate to (set debug_mode=True
to view the logs):
Set the system message directly
You can manually set the system message using the system_prompt
parameter.
User message
The input message
sent to the Agent.run()
or Agent.print_response()
functions is used as the user message.
User message when enable_rag=True
If the Agent is provided knowledge
, and the enable_rag=True
, the user message is set to:
Default system message
The Agent creates a default system message that can be customized using the following parameters:
Parameter | Type | Default | Description |
---|---|---|---|
description | str | None | A description of the Agent that is added to the start of the system message. |
task | str | None | Describe the task the agent should achieve. |
instructions | List[str] | None | List of instructions added to the system prompt in <instructions> tags. Default instructions are also created depending on values for markdown , output_model etc. |
additional_context | str | None | Additional context added to the end of the system message. |
expected_output | str | None | Provide the expected output from the Agent. This is added to the end of the system message. |
extra_instructions | List[str] | None | List of extra instructions added to the default system prompt. Use these when you want to add some extra instructions at the end of the default instructions. |
prevent_hallucinations | bool | False | If True, add instructions to return “I don’t know” when the agent does not know the answer. |
prevent_prompt_injection | bool | False | If True, add instructions to prevent prompt injection attacks. |
limit_tool_access | bool | False | If True, add instructions for limiting tool access to the default system prompt if tools are provided |
markdown | bool | False | Add an instruction to format the output using markdown. |
add_datetime_to_instructions | bool | False | If True, add the current datetime to the prompt to give the agent a sense of time. This allows for relative times like “tomorrow” to be used in the prompt |
system_prompt | str | None | System prompt: provide the system prompt as a string |
system_prompt_template | PromptTemplate | None | Provide the system prompt as a PromptTemplate. |
use_default_system_message | bool | True | If True, build a default system message using agent settings and use that. |
system_message_role | str | system | Role for the system message. |
Disable the default system message by setting use_default_system_message=False
.
Default user message
The Agent creates a default user message, which is either the input message or a message with the context
if enable_rag=True
. The default user message can be customized using:
Parameter | Type | Default | Description |
---|---|---|---|
enable_rag | bool | False | Enable RAG by adding references from the knowledge base to the prompt. |
add_rag_instructions | bool | False | If True, adds instructions for using the RAG to the system prompt (if knowledge is also provided). For example: add an instruction to prefer information from the knowledge base over its training data. |
add_history_to_messages | bool | False | If true, adds the chat history to the messages sent to the Model. |
num_history_responses | int | 3 | Number of historical responses to add to the messages. |
user_prompt | Union[List, Dict, str] | None | Provide the user prompt as a string. Note: this will ignore the message sent to the run function. |
user_prompt_template | PromptTemplate | None | Provide the user prompt as a PromptTemplate. |
use_default_user_message | bool | True | If True, build a default user prompt using references and chat history. |
user_message_role | str | user | Role for the user message. |
Disable the default user message by setting use_default_user_message=False
.
Was this page helpful?