| .. | ||
| bin | ||
| personal_receipts/2017/de/public_transport | ||
| schema_registry | ||
| tests | ||
| .env.template | ||
| api.py | ||
| docker-compose.yml | ||
| Dockerfile | ||
| entrypoint.sh | ||
| level_2_pdf_vectorstore__dlt_contracts.py | ||
| poetry.lock | ||
| pyproject.toml | ||
| Readme.md | ||
PromethAI Memory Manager
Description
Initial code lets you do three operations:
- Add to memory
- Retrieve from memory
- Structure the data to schema and load to duckdb
#How to use
Installation
docker compose build promethai_mem
Run
docker compose up promethai_mem
Usage
The fast API endpoint accepts prompts and stores data with the help of the Memory Manager
The types of memory are: Episodic, Semantic, Buffer
Endpoint Overview The Memory API provides the following endpoints:
- /[memory_type]/add-memory (POST)
- /[memory_type]/fetch-memory (POST)
- /[memory_type]/delete-memory (POST)
- /available-buffer-actions (GET)
- /run-buffer (POST)
- /buffer/create-context (POST)
Here is a payload example:
{
"payload": {
"user_id": "681",
"session_id": "471",
"model_speed": "slow",
"prompt": "I want ",
"pdf_url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
"params": {
"version": "1.0",
"agreement_id": "AG123456",
"privacy_policy": "https://example.com/privacy",
"terms_of_service": "https://example.com/terms",
"format": "json",
"schema_version": "1.1",
"checksum": "a1b2c3d4e5f6",
"owner": "John Doe",
"license": "MIT",
"validity_start": "2023-08-01",
"validity_end": "2024-07-31"
}
}
}