Multi-backend agents system for automated scripts and tasks
Project description
naming after the mathematician,
this repository served as an experimental features that enable AI model to be assitant of growing graph database knowledge. With the integration of model context protocol, to accessing external data source:
- dgraph
- neo4j
central file formating:
- apache graphar
Balakrishnan: MCP for Graph Database
enable ai integration with workflow via graph database language
Table of Contents
- Overview
- Features
- Technologies Used
- Installation
- Usage
- Data Collection & Customization
- Contributing
- License
- Contact
Features
- enable centralized repository of knowledge base
- using ai agent by function tools, to not only answer question but to help execute works
- initalized to expand our tech for developing, and learning new technology surrounding graph database
Installation
-
Clone the Repository:
git clone https://stage-gitlab.com/anusar.vinlay/balakrishnan.git cd Balakrishnan uv venv
-
Activate the virtual environment
source venv/bin/activate # On Windows: venv\Scripts\activate
Usage
[test:]..... Using the new A2A protocol from google
sequenceDiagram
participant Client as A2A Client
participant Server as A2A Server
participant Agent as LangGraph Agent
participant API as Frankfurter API
Client->>Server: Send task with currency query
Server->>Agent: Forward query to currency agent
alt Complete Information
Agent->>API: Call get_exchange_rate tool
API->>Agent: Return exchange rate data
Agent->>Server: Process data & return result
Server->>Client: Respond with currency information
else Incomplete Information
Agent->>Server: Request additional input
Server->>Client: Set state to "input-required"
Client->>Server: Send additional information
Server->>Agent: Forward additional info
Agent->>API: Call get_exchange_rate tool
API->>Agent: Return exchange rate data
Agent->>Server: Process data & return result
Server->>Client: Respond with currency information
end
alt With Streaming
Note over Client,Server: Real-time status updates
Server->>Client: "Looking up exchange rates..."
Server->>Client: "Processing exchange rates..."
Server->>Client: Final result
end
Technologies Used
- api-gateway : apache apisix
- model context protocol
- integrating with -> https://google.github.io/A2A/#/topics/a2a_and_mcp.md
Graph Database:
- dgraph (protocol-based distributed system)
- neo4j (open-standard graph database)
- tigergraph (olap analytic-commercial options)
- hugegraph (opensource db under apache)
- nebulagraph (modular, scalable, microservice-architecture)
[ BalaKrishnan ]:
├───api
│ └───graphql
├───data
│ ├───dgraph
│ │ ├───p
│ │ ├───t
│ │ ├───w
│ │ └───zw
│ └───neo4j
│ ├───databases
│ │ ├───neo4j
│ │ │ └───schema
│ │ │ └───index
│ │ │ └───token-lookup-1.0
│ │ │ ├───1
│ │ │ └───2
│ │ └───system
│ │ └───schema
│ │ └───index
│ │ ├───range-1.0
│ │ │ ├───11
│ │ │ ├───3
│ │ │ ├───5
│ │ │ ├───7
│ │ │ └───9
│ │ └───token-lookup-1.0
│ │ ├───1
│ │ └───2
│ └───transactions
│ ├───neo4j
│ └───system
├───database
│ ├───dgraph
│ │ └───.devcontainer
│ ├───hugegraph
│ │ └───.devcontainer
│ ├───nebula
│ │ └───.devcontainer
│ ├───neo4j
│ │ └───.devcontainer
│ └───tigergraph
│ └───.devcontainer
├───docs
│ ├───img
│ ├───libraries
│ ├───spec
│ └───update
├───lang
└───terraform
License
MIT License
Contribution
- MLOps (stage-gitlab.wingbank.com):
- anusar vinlay [main contributor]
with support and technical collaboration with MLOps teams
Contact
telephone: (+855) 015522542
gmail: anusar@big-dixta.tech
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file balakrishnan-0.1.0.tar.gz.
File metadata
- Download URL: balakrishnan-0.1.0.tar.gz
- Upload date:
- Size: 3.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4633b3a28d445b8231cf431773d6a04dc8e743d339144da5c43863677805a33f
|
|
| MD5 |
f45fb3ca2f98994b660d1b73298df7dc
|
|
| BLAKE2b-256 |
a4b680c16b5924800677e7c77501e4b9398ee785ab4b2a06dbf1202afdf9fd6a
|
File details
Details for the file balakrishnan-0.1.0-py3-none-any.whl.
File metadata
- Download URL: balakrishnan-0.1.0-py3-none-any.whl
- Upload date:
- Size: 3.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
406a6b9679b8ddbee77d5a0325e25a49c786011257dac99dcc4c433d66be6dd3
|
|
| MD5 |
2d9b341af6b7116676d6f1b13127d48e
|
|
| BLAKE2b-256 |
aab0414cf57488107d862a7f16a365e4807272c7de156d69a5290686dbb95826
|