MemoryBlockCreateRequest
Properties
Name |
Type |
Description |
Notes |
|---|---|---|---|
name |
str |
Name of the memory block. |
|
content |
str |
Initial content of the memory block. |
[optional] |
system_prompt_amendment |
str |
System prompt amendment for agent mode that drives changes to the memory block. |
[optional] |
injection_mode |
str |
Where memory content is injected. ‘system_prompt’ (default) adds it to the LLM system prompt; ‘user_instruction’ prepends it to the user message; ‘agent_file’ makes it only available as AGENTS.md in agent mode; ‘agent_tool’ exposes content lazily via the read_memory_block / update_memory_block tools (no pre-injection). |
[optional] |
access_mode |
str |
Controls whether the LLM/agent can read the memory, write to it, or both. |
[optional] |
max_content_length |
int |
Maximum number of characters allowed in memory content. Set to 0 for unlimited. In LLM mode, new memories are appended and oldest content is trimmed when this limit is exceeded. |
[optional] [default to 10000] |
Example
from h2ogpte.rest_async.models.memory_block_create_request import MemoryBlockCreateRequest
# TODO update the JSON string below
json = "{}"
# create an instance of MemoryBlockCreateRequest from a JSON string
memory_block_create_request_instance = MemoryBlockCreateRequest.from_json(json)
# print the JSON string representation of the object
print(MemoryBlockCreateRequest.to_json())
# convert the object into a dict
memory_block_create_request_dict = memory_block_create_request_instance.to_dict()
# create an instance of MemoryBlockCreateRequest from a dict
memory_block_create_request_from_dict = MemoryBlockCreateRequest.from_dict(memory_block_create_request_dict)