Skip to main content

NucliaDB Agentic API

The NucliaDB Agentic API package exposes NucliaDB-oriented agentic capabilities for Hyperforge, including ASK/search flows and MCP integrations.

Install

From the workspace root:

uv sync

Run

Start the service:

uv run nucliadb-agentic-api

Useful endpoints:

  • /health/ready
  • /health/alive
  • /metrics

Configuration

Runtime configuration is provided through environment variables consumed by Pydantic settings. Common settings include:

  • HTTP_HOST and HTTP_PORT
  • MEMORY_READER_NUCLIADB, MEMORY_WRITER_NUCLIADB, and MEMORY_SEARCH_NUCLIADB
  • MEMORY_APIKEY_NUCLIADB
  • VALKEY_URL
  • IDP_REGIONAL_GRPC
  • LOAD_MODULES

Development

Run the package tests from the workspace root:

make test

Objective

Enhance the RAG experience by offering RAO features directly in a KB.

How?

The same way we store search configs in the KB, we could store agentic configs, and when calling the /ask endpoint we can refer to a given agentic config.

Scope

The corresponding RAO workflow will be:

  • a Rephrase (optionally)
  • a SmartAgent
  • a Summarize

Possible sources for the SmartAgent:

  • The current KB (possibly several times with different filters)
  • Sync service (using connections defined in the current KB)
  • Google
  • Perplexity
  • MCP

Out of scope

  • Other KBs
  • SQL
  • Snowflake (?)
  • Sitefinity (?)

Config spec

{
  "rephrase": { // optional
    "ask_to": <filter_expression>, //optional
    "prompt": <string>, // optional
    "model": <model>, // optional
  },
  "smart_agent": {
    "mode": <reactive | plan_execute>,
    "extra_prompt": <string>, // optional
    "models": { // optional
      "context_validation": <model>, // optional
      "planner": <model>, // optional
      "executor": <model>, // optional
    },
    "sources": [<source list>]
  },
  "summarize": { // optional
    "user_prompt": <string>, // optional
    "system_prompt": <string>, // optional
    "conversational": <boolean>,
    "model": <model>, // optional
    // and citations must be forced to chunk-level
  }
}

And sources can be:

{
  "type": "nucliadb",
  "description": <string>,
  "filter_expression": <filter_expression>, //optional
}

{
  "type": "sync",
  "description": <string>,
  "connection": <connection_id>
}

{
  "type": "google",
  "description": <string>
}

{
  "type": "perplexity",
  "description": <string>
}

{
  "type": "mcp",
  "description": <string>,
  <...the MCP driver params>
}

Metadata

Release files for nucliadb-agentic-api 1.0.0.post240

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for nucliadb-agentic-api 1.0.0.post240
File Size Uploaded
nucliadb_agentic_api-1.0.0.post240.tar.gz 42.2 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for nucliadb-agentic-api 1.0.0.post240
File Interpreter ABI Platform
nucliadb_agentic_api-1.0.0.post240-py3-none-any.whl Python 3 none any Details

Total release size: 93.2 kB

Release files / nucliadb_agentic_api-1.0.0.post240.tar.gz

Download URL nucliadb_agentic_api-1.0.0.post240.tar.gz
Size 42.2 kB
Tags Source
SHA-256 checksum
How to use checksums
ed63dba26b11611d106e5805690de1ce8b4ac103c707dacfa8394daf8843b309
BLAKE2b-256 checksum
How to use checksums
90c9b47eb561f240274985e83aa8875a1b3f413b6798d01dfe0020af4d2c5204
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.13

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 19, 2026.

Transparency log

Release files / nucliadb_agentic_api-1.0.0.post240-py3-none-any.whl

Download URL nucliadb_agentic_api-1.0.0.post240-py3-none-any.whl
Size 51.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
418e53654144032ce49ba81eb0ad7606628ad8f40c1c95f9565a87aba5c8568e
BLAKE2b-256 checksum
How to use checksums
57fad18515f12f59c387d7fcc23fd53326aea168cba6750629bbd96ace3007b6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.13

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 19, 2026.

Transparency log
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page