Skip to main content

LangChain integration for Mengram — AI memory with semantic, episodic, and procedural memory types.

Project description

langchain-mengram

LangChain integration for Mengram — AI memory with semantic, episodic, and procedural memory types.

Installation

pip install langchain-mengram

Quick start

from langchain_mengram import MengramRetriever

retriever = MengramRetriever(
    api_key="om-...",
    user_id="user-123",
)

docs = retriever.invoke("deployment issues")
for doc in docs:
    print(doc.metadata["memory_type"], doc.page_content)

What it does

MengramRetriever searches across all three Mengram memory types and returns LangChain Document objects:

  • Semantic — facts, entities, and knowledge graph relationships
  • Episodic — events, experiences, and their outcomes
  • Procedural — workflows, step-by-step procedures, and learned routines

Each document includes metadata["memory_type"] so you can filter or prioritize by type.

Use in a chain

from langchain_mengram import MengramRetriever
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_core.output_parsers import StrOutputParser

retriever = MengramRetriever(api_key="om-...", user_id="user-123")
llm = ChatOpenAI(model="gpt-4o-mini")

prompt = ChatPromptTemplate.from_messages([
    ("system", "Use the following memory context to answer:\n\n{context}"),
    ("human", "{question}"),
])

chain = (
    {"context": retriever | format_docs, "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)

chain.invoke("What deployment steps did we follow last time?")

Parameters

Parameter Type Default Description
api_key str required Mengram API key (starts with om-)
user_id str "default" User to search memories for
api_url str "https://mengram.io" Mengram API base URL
top_k int 5 Max results per memory type
memory_types list ["semantic", "episodic", "procedural"] Which types to search

Links

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

langchain_mengram-0.3.0.tar.gz (5.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

langchain_mengram-0.3.0-py3-none-any.whl (6.6 kB view details)

Uploaded Python 3

File details

Details for the file langchain_mengram-0.3.0.tar.gz.

File metadata

  • Download URL: langchain_mengram-0.3.0.tar.gz
  • Upload date:
  • Size: 5.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.7

File hashes

Hashes for langchain_mengram-0.3.0.tar.gz
Algorithm Hash digest
SHA256 c640e0034dfe38463d8adcdc53f72fa319d1f4e2b7fc215e97df00d49828ed13
MD5 ad7f40227bf9aeadf90ccec84c0455ff
BLAKE2b-256 9b0f09c895f9192bad97b38a867e1a52b420c372d02f14c0eb1d4a545953d120

See more details on using hashes here.

File details

Details for the file langchain_mengram-0.3.0-py3-none-any.whl.

File metadata

File hashes

Hashes for langchain_mengram-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 91a55af3a9f48e2736e4793b9b8678c0366b8e0c3bcb78950582634532de7472
MD5 0594803647dac85064f9277ca9eeeeb0
BLAKE2b-256 457f151f85ac08e7b0062a156596f3f894a58a32259caafdcb96969d04c0f28a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page