Skip to main content

Python client for the Recallio API

Project description

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)

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)

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")

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

recallio-1.2.5.tar.gz (4.9 kB view details)

Uploaded Source

Built Distribution

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

recallio-1.2.5-py3-none-any.whl (5.8 kB view details)

Uploaded Python 3

File details

Details for the file recallio-1.2.5.tar.gz.

File metadata

  • Download URL: recallio-1.2.5.tar.gz
  • Upload date:
  • Size: 4.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.5

File hashes

Hashes for recallio-1.2.5.tar.gz
Algorithm Hash digest
SHA256 ea028537b1c8093af59460e0eef85bc9daaa44bcc1cbc5830c23971425b12fdb
MD5 be3e9ebe6be060daf56d54aa1e01bac0
BLAKE2b-256 87812fd64f6dc5fabae7ba51214c172d04a5178520260ed677d5dc6e8c39ca57

See more details on using hashes here.

File details

Details for the file recallio-1.2.5-py3-none-any.whl.

File metadata

  • Download URL: recallio-1.2.5-py3-none-any.whl
  • Upload date:
  • Size: 5.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.5

File hashes

Hashes for recallio-1.2.5-py3-none-any.whl
Algorithm Hash digest
SHA256 2a3c5f10427c4f4fe52bc214fe41e0f8880307b80aaf95f75aa73137bead7b2e
MD5 a0632b374bdf50b6f8fc1e202f7b0619
BLAKE2b-256 f25b7e75ae4d58a50d872f30743d544939ec75208bda875aac8812aa3c18a07e

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