Udai Solanki

Project Owner

NeuroKG – A Scalable Knowledge Graph Toolkit

Expert Rating

n/a

Type SingularityNET RFP
Funding Request $60,000 USD
RFP Guidelines Advanced knowledge graph tooling for AGI systems

Overview

NeuroKG seeks to create a modular and open-source toolkit that will improve every stage of the lifecycle of knowledge graphs (KGs) in relation to AGI systems. The toolkit will center on the following: Extraction>> pertains to the automated creation of KGs from unstructured data. Refinement>>focuses on duplication, disambiguation, and consistency checking. Assessment>> relates to benchmarking the quality of KGs and their reasoning abilities. Integration>> MORK graph database within the OpenCog Hyperon framework from MeTTa language offers complete proprietary integration. NeuroKG will enable the construction of highly resilient, agile, and expandable KGs in AGI systems.

Project Tags:
Community and Collaboration

RFP Guidelines

Advanced knowledge graph tooling for AGI systems

Complete & Awarded

Type SingularityNET RFP
Total RFP Funding $350,000 USD
Proposals 39
Awarded Projects 5

SingularityNET

Apr. 16, 2025

This RFP seeks the development of advanced tools and techniques for interfacing with, refining, and evaluating knowledge graphs that support reasoning in AGI systems. Projects may target any part of the graph lifecycle — from extraction to refinement to benchmarking — and should optionally support symbolic reasoning within the OpenCog Hyperon framework, including compatibility with the MeTTa language and MORK knowledge graph. Bids are expected to range from $10,000 - $200,000.

Proposal Description

Our Team

AIQUANT Technologies have 20+ team mebers who are expert in area of AI, Blockchain and quantum computing.

Udai Solanki - 25 Years Global Experience in Technology Leadership, AI/ML, KG, Blockchain, Cardano and Quantum Computing

Kausik Sarkar, 25 years experience in Solution Architecturing, Technical Desgin, AI/ML and KG implementation in large enterprises. Certified in KG.

Aditya Solanki - MeTTa, KG Developer

Company Name (if applicable)

AIQUANT Technologies

Project details

NeuroKG offers a complete modular toolkit for every stage of the knowledge graph (KG) lifecycle in AGI systems. It is built on advanced NLP, graph algorithms, and other open-source tools, NeuroKG will provide:

Automated Extraction: Complete entity and relation extraction pipelines for unstructured data sources such as text, PDFs, and the web.

Refinement and Curation: Sophisticated deduplication, entity resolution, ontology alignment, and consistency validation.

Benchmarking & QA: Comprehensive testbeds focused on predefined metrics with visualization dashboards for assessing completeness, accuracy, and reasoning performance.

Seamless AGI Integration: MeTTa scripts, MORK graph storage, and Hyperon reasoning modules integrate with out-of-the-box KG frameworks with no additional configuration needed.

Technical Description

Overview of Architecture

Microservices-Based Design: Extraction, Refinement, Evaluation, and Integration are all distinct phases organized as containerized services under Kubernetes (EKS/GKE).

Event-Driven Workflow: Data flows are managed by Apache Kafka, which webinars automation through new data triggers.

Storage Layer:

- Raw Data Store: An S3 compatible blob store for unstructured data inputs.

- Interim Graph Store: Early stage knowledge graph drafts stored in JanusGraph with a Cassandra backend.

- Final Persistent Store: Production knowledge graph MORK database used by AGI components.

API Gateway: RESTful and gRPC interfaces for orchestrating pipelines, monitoring, and Hyperon integration provide streamlined access.

Extraction Module

NLP Core: RoBERTA and T5 based transformers for domain-specific NER projects utilizing span-based models identifying multi and nested type entities.

Relation Extraction: Binary and multi-ary relations inference by multi-head attention classifiers.

Document Processing: Extracting texts from PDFs with Apache Tika and HTML scraping with Scrapy.

Ontology-Driven Mapping: Entity normalization with alignments and SPARQL templates in Protégé Against the target ontologies (OWL/RDF).

Batch & Streaming Modes: Bulk ingestion in addition to updates in real-time processed through Kafka topics.

Refinement & Curation Module

Entity Resolution:

- Vector Embeddings: Node embeddings from GraphSAGE for similarity clustering.

- Clustering Algorithms: Hierarchical climbers with a tunable threshold for duplicate merging.

Disambiguation: Canonical entities selected through Contextual BERT cross-encoder ranked disambiguation.

Consistency & Integrity Checks: Enforcement of domain constraints and detection of cycles or logical conflicts are handled by custom prolog-like rule engines through ECLiPSe or Datalog.

Interactive Curation UI: Backend conflicts resolution and manual review using React front end with Cytoscape.js user feedback loops for iterative processes.

Evaluation & Benchmarking Module

Quality Metrics: For extraction tasks – precision, recall, F1; graph-centric metrics (connectivity, diameter, clustering coefficient).

Reasoning Benchmarks: AGI standardized reasoning tasks such as analogical mapping and pathfinding queries measured through Hyperon’s reasoning engine.

Automated Test Suite: Nightly builds run by PyTest-based frameworks including synthetic benchmarks and real-world application scenarios.

Visualization Dashboard: Trend analyzers from KPI, error distribution, and performance profiling with Grafana and Kibana integrations.

AGI Integration & API

MeTTa Bindings: MeTTa templates enabling automatic code generation for knowledge graph ingestion, query execution, and pattern reasoning.

MORK Connector: Rust-built gRPC connector enabling high-throughput low-latency operations on nodes and edges.

SDK & CLI: Contains Python SDK with the procedural tools such as load_graph(), query_pattern(), refine_entities() and also a CLI for batch operations.

Security & Access Control: Authorisation via OAuth2.0 / JWT, with role-based access control for scoped read/write permissions.

NeuroKG Benefits:

Improving the Quality of Symbolic Reasoning: Offering services that enhance the construction and application of KGs which are critical in the processes of symbolic reasoning in AGI systems.

Supporting OpenCog Hyperon: Guaranteeing MeTTa and MORK interoperability as a means to ensure integration into the current AGI architecture.

Advancing Open Source Collaboration: Adopting open-source policies to support collective public input and system transparency.

Tackling the Issues of Dynamic Knowledge: Engineering robust solutions for the changing environments where data is unpredictable and inherently complex.

Open Source Licensing

GNU GPL - GNU General Public License

Full solution will be made Open Source under the GNU GPL license.

Background & Experience

The AIQUANT Research and Development focused team has experience of many real life projects on AI and Blockchain like Cardano and working on building AI Foundational model as well doing advance research on Quantum Computing.

AIQUANT Technologies have 20+ team mebers who are expert in area of AI, Blockchain and quantum computing.

https://aiquant.ae/

Udai Solanki - 25 Years Global Experience in Technology Leadership, AI/ML, KG, Blockchain, Cardano and Quantum Computing

https://www.linkedin.com/in/solanki/

Kausik Sarkar, 25 years experience in Solution Architecturing, Technical Desgin, AI/ML and KG implementation in large enterprises. Certified in KG.

https://www.linkedin.com/in/kausik/

Aditya Solanki - MeTTa, KG Developer

https://www.linkedin.com/in/adityasoul/

Links and references

https://www.linkedin.com/in/solanki

https://www.linkedin.com/in/kausik/

https://www.linkedin.com/in/adityasoul/

https://aiquant.ae

Describe the particulars.

Cardano Summit 2024 Dubai

Activity Summary

Milestones

4

Total

Discussion

0

Total Comments

Reviews

0

Total Posted

Project Team

5

Total People

Total Milestones
4
Total Budget
$60,000_USD
Last Updated
27 May 2025

Milestone 1 - Setup Infrastructure & Initiating Basic Framework

Description

Execute the initial infrastructure consisting of Kubernetes Kafka and back-end storage systems. Set up the project skeleton along with CI/CD pipelines along with the first microservice interaction templates.

Deliverables

Active Kubernetes cluster and AWS login; Apache Kafka topics created; S3-compatible storage provisioned; primary Git repository and CI/CD jobs configured.

Budget

$10,000 USD

Success Criterion

All core components are installed and working; data flow in sample form is functioning between services; primary logs, data, and metrics are collected.

Milestone 2 - Extracting the data and Drafting The Initial Graph

Description

Create and deploy the document text extraction process using specialized NER and RE models. Connect the NLP engine to a JanusGraph database to automatically construct knowledge graphs.

Deliverables

Functional Transformer models; PDF/HTML content intake at the pipeline; initial graph building and exporting procedure; processed a batch of 10000 documents.

Budget

$15,000 USD

Success Criterion

Complete NER/RE with precision of at least 80% on the holdout set; RDF triples were derived from authentic documents; graph accessible through the REST API.

Milestone 3 - Refinement Graph and Human-in-the-Loop Interface

Description

Create UI for interactive quality control for graph editing and deploy deduplication entity linking consistency checking and rule-based graph quality control.

Deliverables

Entity resolution processes; datalog/prolog information processing rule construction engine; React-derived KG curation dashboard; change history tracking of KG modifications.

Budget

$15,000 USD

Success Criterion

Resolve minimum 90% duplicates in pilot data; logic constraints enforced; Active user testing for UI pertaining to entity disambiguation and feedback mechanisms.

Milestone 4 - Evaluation Suite & AGI Integration Tools

Description

Design evaluation metrics for Knowledge Graph (KG) quality and readiness for AGI. Complete the integrations of MeTTa and MORK. Make the SDK and CLI available to developers.

Deliverables

Documented metrics benchmark datasets MeTTa script generator MORK connector SDK and CLI.

Budget

$20,000 USD

Success Criterion

All active reasoning benchmarks meet operational status; Hyperon accesses NeuroKG through MORK; External collaborators evaluate developer’s toolkit.

Join the Discussion (0)

Expert Ratings

Reviews & Ratings

No Reviews Avaliable

Check back later by refreshing the page.

The weighted average of the 4 perspectives Overall

0.0
Each RFP defines a maximum allowed budget, but teams can differentiate their proposal by offering a solution with a lower budget or a wider scope.Value for money

0.0
This rating indicates compliance to 'Must haves' but also adaptation of 'Nice to haves' and Non-functional requirements defined in the RFP.Compliance with RFP requirements

0.0
RFPs will offer varying degrees of freedom. This rating indicates the quality of the team's specific solution ideas, the provided details, and the reviewer's confidence in the team's ability to execute.Solution details and team expertise

0.0

Review Headline

0 /50 chars

Review Summary

0 /5000 chars

The weighted average of the 4 perspectives Overall

0.0
Each RFP defines a maximum allowed budget, but teams can differentiate their proposal by offering a solution with a lower budget or a wider scope.Value for money

0.0
This rating indicates compliance to 'Must haves' but also adaptation of 'Nice to haves' and Non-functional requirements defined in the RFP.Compliance with RFP requirements

0.0
RFPs will offer varying degrees of freedom. This rating indicates the quality of the team's specific solution ideas, the provided details, and the reviewer's confidence in the team's ability to execute.Solution details and team expertise

0.0

Review Headline

0 /50 chars

0 /5000 chars

Warning: Adding final group rating for this project will prevent expert users from adding new or editing existing reviews

Reviews and Ratings in Deep Funding are structured in 4 categories. This will ensure that the reviewer takes all these perspectives into account in their assessment and it will make it easier to compare different projects on their strengths and weaknesses. Overall (Primary) This is an average of the 4 perspectives. At the start of this new process, we are assigning an equal weight to all categories, but over time we might change this and make some categories more important than others in the overall score. (This may even be done retroactively). Feasibility (secondary) This represents the user\'s assessment of whether the proposed project is theoretically possible and if it is deemed feasible. E.g. A proposal for nuclear fission might be theoretically possible, but it doesn’t look very feasible in the context of Deep Funding. Viability (secondary) This category is somewhat similar to Feasibility, but it interprets the feasibility against factors such as the size and experience of the team, the budget requested, and the estimated timelines. We could frame this as: “What is your level of confidence that this team will be able to complete this project and its milestones in a reasonable time, and successfully deploy it?” Examples:

A proposal that promises the development of a personal assistant that outperforms existing solutions might be feasible, but if there is no AI expertise in the team the viability rating might be low.
A proposal that promises a new Carbon Emission Compensation scheme might be technically feasible, but the viability could be estimated low due to challenges around market penetration and widespread adoption.

Desirability (secondary) Even if the project team succeeds in creating a product, there is the question of market fit. Is this a project that fulfills an actual need? Is there a lot of competition already? Are the USPs of the project sufficient to make a difference? Example:

Creating a translation service from, say Spanish to English might be possible, but it\'s questionable if such a service would be able to get a significant share of the market

Usefulness (secondary) This is a crucial category that aligns with the main goal of the Deep Funding program. The question to be asked here is: “To what extent will this proposal help to grow the Decentralized AI Platform?” For proposals that develop or utilize an AI service on the platform, the question could be “How many API calls do we expect it to generate” (and how important / high-valued are these calls?). For a marketing proposal, the question could be “How large and well-aligned is the target audience?” Another question is related to how the budget is spent. Are the funds mainly used for value creation for the platform or on other things? Examples:

A metaverse project that spends 95% of its budget on the development of the game and only 5 % on the development of an AI service for the platform might expect a low ‘usefulness’ rating here.

A marketing proposal that creates t-shirts for a local high school, would get a lower ‘usefulness’ rating than a marketing proposal that has a viable plan for targeting highly esteemed universities in a scaleable way.
An AI service that is fully dedicated to a single product, does not take advantage of the purpose of the platform. When the same service would be offered and useful for other parties, this should increase the ‘usefulness’ rating.