simplememory
This will be the memory of the agents and agency
To use this package:
Ensure that a .env exists with below parameters.
OPENAI_API_KEY=sk-"ADD YOUR API KEY HERE"
PINECONE_API_KEY = "ADD YOUR API KEY HERE"
PINECONE_INDEX="ADD YOUR INDEX NAME HERE"
If using entity memory or v1 of semantic memory, below parameters are needed
OPENAI_API_KEY = "ADD YOUR API KEY HERE"
NEO4J_URI = "ADD YOUR NEO4J URI HERE"
NEO4J_USERNAME = "ADD YOUR NEO4J USERNAME HERE"
NEO4J_PASSWORD = "ADD YOUR NEO4J PASSWORD"
How to add to semantic memory:
- use v1 of semantic memory which uses NEO4J
# Below version will be deprecated use v1
from memory.semantic_memory import SemanticMemory
if __name__=="__main__":
sc= SemanticMemory()
semantic_val,memory_item = sc.add_memory_item(mem_key="What is the capital of india?",mem_val="The capital of India is New Delhi"
print(semantic_val)
print(memory_item)
# V1 of semantic memory
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_openai import ChatOpenAI
from memory.v1.semantic_memory_v1 import SemanticMemory
if __name__ == "__main__":
llm = ChatOpenAI()
sm = SemanticMemory()
generation_prompt = ChatPromptTemplate.from_messages([
(
"system",
"You will answer based on a question asked.",
),
MessagesPlaceholder(variable_name="messages"), ])
generate = generation_prompt | ChatOpenAI()
while True:
user_input = input("User: ")
messages = generate.invoke({"messages": [user_input]})
sm.add_memory_item(mem_key=user_input,
mem_val=messages.content)
How to retrieve semantic memory:
- use V1 of sematic memory. It uses NEO4J.
# The below will be deprecated
from memory.semantic_memory import SemanticMemory
if __name__=="__main__":
sc= SemanticMemory()
result = sc.retrieve_memory_item(mem_key="what is the capital of India?")
print(result['matches'][0]['metadata']['key'])
print(result['matches'][0]['metadata']['value'])
print(result['matches'][0]['score'])
from memory.v1.semantic_memory_v1 import SemanticMemory
sm = SemanticMemory()
question = "What is blockchain?"
memory = sm.retrieve_memory_item(mem_key=question)
memory_key = memory[0]['name']
print(memory[0]['name'])
memory_value = sm.retrieve_memory_value(memory_key)
print(memory_value)
How to add entity memory:
from memory.entity_memory import EntityMemory
if __name__=="__main__":
sc= EntityMemory()
sc.add_memory_item(mem_key="What is the capital of India?",mem_val="The capital of India is New Delhi")
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
simplememory-0.0.3.tar.gz
(7.7 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file simplememory-0.0.3.tar.gz.
File metadata
- Download URL: simplememory-0.0.3.tar.gz
- Upload date:
- Size: 7.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/5.1.0 CPython/3.11.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5a67fc6d265441750b0569494bc53545d25957f17d8750c0de9316568562871f
|
|
| MD5 |
0d3459fb5e65e6e9c7bd4563a5595df3
|
|
| BLAKE2b-256 |
61a876cf0cbd2b095ec930400445ce54381e5c11d7a5c5ed2bcbe76848e95889
|
File details
Details for the file simplememory-0.0.3-py3-none-any.whl.
File metadata
- Download URL: simplememory-0.0.3-py3-none-any.whl
- Upload date:
- Size: 9.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/5.1.0 CPython/3.11.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
271325eacd3364ee6e5e6ed012b4ab2a0c5ba0e738746e8b2c77537a55097c22
|
|
| MD5 |
813c35bd90b73e6578ad875f0ded9b14
|
|
| BLAKE2b-256 |
6faaa087ee16c09d7af962d3922a481220b334c64d9819063464e9d0d519d7dc
|