anura-graph 0.2.0

Python client for the GraphMem knowledge graph API

anura-graph (Python)

Python client for the GraphMem knowledge graph API.

Installation

pip install anura-graph

Quick Start

from graphmem import GraphMem

mem = GraphMem(api_key="gm_your_key_here")

# Store knowledge
result = mem.remember("Alice works at Acme Corp as a software engineer")
print(f"Extracted {result.extracted_count} facts")

# Retrieve context
ctx = mem.get_context("What does Alice do?")
print(ctx)

# Search for an entity
result = mem.search("Alice")
print(result.edges)

All Methods

Core

Method	Description
remember(text)	Extract knowledge from text and store in the graph
get_context(query, options?)	Retrieve graph context for a query
search(entity)	Search for an entity and its 1-hop neighbors

Graph Management

Method	Description
get_graph()	Get the full graph (nodes, edges, communities)
ingest_triples(triples)	Ingest triples directly into the graph
delete_edge(id, blacklist?)	Delete an edge, optionally blacklisting it
update_edge_weight(id, weight?, increment?)	Update an edge's weight
delete_node(id)	Delete a node and all its connected edges
export_graph()	Export the entire graph as portable JSON
import_graph(data)	Import a graph export into the current project

Traces

Method	Description
list_traces(limit?, cursor?)	List query traces with pagination
get_trace(id)	Get details for a specific trace

Blacklist

Method	Description
list_blacklist(limit?, cursor?)	List blacklisted triples
add_to_blacklist(subject, predicate, object)	Add a triple to the blacklist
remove_from_blacklist(id)	Remove a triple from the blacklist

Pending Facts

Method	Description
list_pending(limit?, cursor?)	List pending facts
approve_fact(id)	Approve a pending fact
reject_fact(id, blacklist?)	Reject a pending fact
approve_all()	Approve all pending facts
reject_all()	Reject all pending facts

Projects

Method	Description
list_projects()	List all projects
create_project(name)	Create a new project
delete_project(id)	Delete a project
select_project(id)	Switch active project

Communities

Method	Description
list_communities()	List all detected communities
detect_communities()	Run community detection

Other

Method	Description
health()	Check server health
get_usage()	Get usage and tier info

Configuration

from graphmem import GraphMem, RetryConfig

mem = GraphMem(
    api_key="gm_your_key_here",
    base_url="https://graphmem.com",  # default
    retry=RetryConfig(
        max_retries=3,       # default
        base_delay=0.5,      # seconds, default
        max_delay=10.0,      # seconds, default
        retry_on=[429, 500, 502, 503, 504],  # default
    ),
    timeout=30.0,  # seconds, default
)

Rate Limit Info

After each request, rate limit info is available:

mem.remember("some fact")
print(mem.rate_limit.remaining)  # requests remaining
print(mem.rate_limit.limit)      # total allowed per window
print(mem.rate_limit.reset)      # unix timestamp when window resets

Error Handling

from graphmem import GraphMem, GraphMemError

mem = GraphMem(api_key="gm_your_key_here")

try:
    mem.remember("some text")
except GraphMemError as e:
    print(f"API error {e.status}: {e}")
    print(e.body)  # raw response body

Context Manager

The client can be used as a context manager to ensure the HTTP connection is properly closed:

with GraphMem(api_key="gm_your_key_here") as mem:
    mem.remember("Alice works at Acme")
    ctx = mem.get_context("Alice")

License

MIT