Recallio Python Client

Recallio – AI-Powered Contextual Memory & Knowledge-Graph API

Store, index, and retrieve application “memories” with built-in fact extraction, dynamic summaries, reranked recall, and a full knowledge-graph layer.

🔧 Core Capabilities

• Embeddings-backed Storage: Fast semantic write & recall.

• LLM-Driven Insights: Fact extraction, reranking, summarization.

• Full Lifecycle Management: Write, recall, delete, export.

• Knowledge Graph: Entities, relationships, and powerful graph queries.

• OpenAPI-First: Auto-generated Swagger docs and client libs.

Lightweight Python wrapper for the Recallio API.

Installation

pip install recallio

Quick start

from recallio import RecallioClient

client = RecallioClient(api_key="YOUR_RECALLIO_API_KEY")

Memory API

Write memory

from recallio import MemoryWriteRequest

req = MemoryWriteRequest(
    userId="user_123",
    projectId="project_abc",
    content="The user prefers dark mode and wants notifications disabled on weekends",
    consentFlag=True,
)
client.write_memory(req)

You can also pass a JSON object or array for content:

req_json = MemoryWriteRequest(
    userId="user_123",
    projectId="project_abc",
    content=[{"role": "assistant", "content": "What is your name ?"},{"role": "user", "content": "My name is Guillaume"}],
    consentFlag=True,
)
client.write_memory(req_json)

Note: when content is not a string, it must be either a dict like { "role": "assistant", "content": "..." } or a list of such dicts. The client validates and automatically JSON-serializes this format before sending.

Ingest document

from recallio import DocumentIngestRequest

ingest_req = DocumentIngestRequest(
    file_path="/path/to/file.pdf",
    userId="user_123",
    projectId="project_abc",
    consentFlag=True,
)
client.ingest_document(ingest_req)

Recall memories

from recallio import MemoryRecallRequest

recall_req = MemoryRecallRequest(
    projectId="project_abc",
    userId="user_123",
    query="dark mode",
    scope="user",
    reRank=True,
)
results = client.recall_memory(recall_req)
for m in results:
    print(m.content, m.similarityScore)

Recall summary

from recallio import RecallSummaryRequest

summary_req = RecallSummaryRequest(
    projectId="project_abc",
    userId="user_123",
    scope="user",
)
summary = client.recall_summary(summary_req)
print(summary.content)

Recall topics

from recallio import RecallTopicsRequest

topics_req = RecallTopicsRequest(userId="user_123")
topics = client.recall_topics(topics_req)
print(topics.topics)

Delete memories

from recallio import MemoryDeleteRequest

delete_req = MemoryDeleteRequest(scope="user", userId="user_123")
client.delete_memory(delete_req)

Export memories

from recallio import MemoryExportRequest

export_req = MemoryExportRequest(type="fact", format="json", userId="user_123")
json_data = client.export_memory(export_req)

Graph Memory API

Add data to the graph

from recallio import GraphAddRequest

graph_req = GraphAddRequest(
    data="John works at OpenAI in San Francisco",
    user_id="user_123",
    project_id="project_abc",
)
response = client.add_graph_memory(graph_req)
print(response.added_entities)

Search the graph

from recallio import GraphSearchRequest

search_req = GraphSearchRequest(query="Where does John work?", user_id="user_123")
graph_results = client.search_graph_memory(search_req)
for r in graph_results:
    print(r.source, r.relationship, r.destination)

Get all relationships

relationships = client.get_graph_relationships(user_id="user_123")

Delete all graph data

client.delete_all_graph_memory(user_id="user_123")