`dbx-tools-graphiti`

Run Graphiti's REST and MCP applications together in one FastAPI process. The package composes the upstream routers, service initialization, MCP tools, and MCP session manager without copying their implementations.

Both upstream packages resolve from the same Graphiti commit:

graph-service from server/
mcp-server from mcp_server/

Run

UVICORN_HOST=0.0.0.0 \
UVICORN_PORT=8000 \
uv run uvicorn dbx_tools.graphiti.main:app

From the repository root, the local launcher starts the FalkorDB CLI first, waits for its loopback TCP listener, and then starts Uvicorn:

DATABRICKS_CONFIG_PROFILE=<profile> \
MODEL_NAME=databricks-gpt-5-nano \
bash scripts/run-graphiti-python.sh

The combined application exposes:

FastAPI documentation at /docs
OpenAPI at /openapi.json
REST health and Graphiti routes, including /healthcheck, /search, and ingestion endpoints
Streamable HTTP MCP at /mcp/

Configure Graphiti through the environment and YAML settings supported by the two upstream applications.

Databricks Model Resolution

The process creates one generated auth client and one generated model client at startup. It resolves the fuzzy chat model, ranks embedding endpoints by the configured name, embedding class, and dimensions, then resolves both endpoint routes. REST and MCP reuse the same Graphiti model clients, while the auth client injects refreshed Databricks headers into every model request.

Composition Boundary

dbx_tools.graphiti.main owns only the combined FastAPI lifespan and route mounting. It initializes the upstream REST application through initialize_graphiti(), initializes the existing MCP services without invoking their CLI parser, and runs the mounted MCP session manager in the parent lifespan. Shared Graphiti environment options are parsed through the generated graphiti_options_from_environment() binding and mapped into both upstream settings objects before initialization.

Metadata

Release files for dbx-tools-graphiti 0.9.47

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

Source distribution (sdist)

Source distribution for dbx-tools-graphiti 0.9.47
File	Size	Uploaded
dbx_tools_graphiti-0.9.47.tar.gz	462.2 kB	Oct 6, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for dbx-tools-graphiti 0.9.47
File	Interpreter	ABI	Platform	Reset
dbx_tools_graphiti-0.9.47-py3-none-any.whl 469.5 kB Oct 6, 2026	Python 3	none	any	Details

Total release size: 931.6 kB

Release files / dbx_tools_graphiti-0.9.47.tar.gz

Download URL	dbx_tools_graphiti-0.9.47.tar.gz
Size	462.2 kB
Tags	Source
SHA-256 checksum How to use checksums	`da3051d2759c53331eb7bb6990f0b99d0fd98e8a7093ff46baf3c739fdf9a704`
BLAKE2b-256 checksum How to use checksums	`4327a3d44417eef641ce29cf068ef7c89f43ae2ef32ea6c005c8cda7491cf820`
Upload date	Oct 6, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

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.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/reggie-db/dbx-tools
Publishing commit: github.com/reggie-db/dbx-tools/tree/1155b52adeec5328ba288b8a78ba502dd3c4d7ef

Workflow

Publishing configuration: github.com/reggie-db/dbx-tools/blob/1155b52adeec5328ba288b8a78ba502dd3c4d7ef/.github/workflows/release.yml
Publishing logs: github.com/reggie-db/dbx-tools/actions/runs/37515018863/attempts/1

Artifact

Subject: dbx_tools_graphiti-0.9.47.tar.gz
SHA-256 checksum: da3051d2759c53331eb7bb6990f0b99d0fd98e8a7093ff46baf3c739fdf9a704 Verifying attestations

Release files / dbx_tools_graphiti-0.9.47-py3-none-any.whl

Download URL	dbx_tools_graphiti-0.9.47-py3-none-any.whl
Size	469.5 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`dfd6608f239b09dee9915f8f08db9d240f5c7486f4211a3e468c34a8d9acca00`
BLAKE2b-256 checksum How to use checksums	`8ab9685641b730f4c823d79868e3073b516bd7e83d0fc5991f21f478a806a487`
Upload date	Oct 6, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/reggie-db/dbx-tools
Publishing commit: github.com/reggie-db/dbx-tools/tree/1155b52adeec5328ba288b8a78ba502dd3c4d7ef

Workflow

Publishing configuration: github.com/reggie-db/dbx-tools/blob/1155b52adeec5328ba288b8a78ba502dd3c4d7ef/.github/workflows/release.yml
Publishing logs: github.com/reggie-db/dbx-tools/actions/runs/37515018863/attempts/1

Artifact

Subject: dbx_tools_graphiti-0.9.47-py3-none-any.whl
SHA-256 checksum: dfd6608f239b09dee9915f8f08db9d240f5c7486f4211a3e468c34a8d9acca00 Verifying attestations