Express YourSelf !

For AI application, we need automation of 

1. Data preparation
2. model tuning
3. Deployment
4. Maintenance and 
5. Monitoring

• Managing Dependency adds complexity. 

E2E workflow for LLM based application. 

MLOps framework

1. data ingestion

2. data validation

3. data transformation

4. model

5. model analysis

6. serving model

7. logging. 

LLM System Design

boarder design of E2E app including front end, back end, data engineering etc. 

Chain multiple LLMs together

* Grounding : provides additional information/fact with prompt to LLM. 

* Track History. how it works past. 

LLM App

User input->Preprocessing->grounding->prompt goes to LLM model->LLM Response->Grounding->Post processing + Responsible AI->Final output to user.

Model Customization

1. Data Prep

2. Model Tuning

3. Evaluate

It is iterative process

LLMOps Pipeline (Simplified)

1. Data Preparation and versioning (for training data)

2. Supervised tuning (pipeline) 

3. Artifact = config and workflow : are generated. 

- config = config for workflow

E.g. 

Which data set to use

- Workflow = steps 

4. Pipeline execution

5. deploy LLM 

6. Prompting and predictions

7. Responsible AI

Orchestration = 1 + 2 . Orchestration : What is first, then next step and further next step. sequence of step assurance. 

Automation = 4 + 5

Fine Tuning Data Model using Instructions (Hint)

1. rules

2. step by step

3. procedure

4. example

File formats

1. JSONL: JSON Line. Human readable. For small and medium size dataset. 

2. TFRecord 

3. Parquet for large and complex dataset. 

MLOps Workflow for LLM

1. Apache Airflow

2. KubeFlow

DSL = Domain Specific Language

Decorator 

@dls.component

@dls.pipeline

Next compiler will generate YAML file for pipeline

YAML file has

- components

- deploymentSpec

Pipeline can be run on

- K8s

- Vertex AI pipeline execute pipeline in serverless enviornment

PipelineJob takes inputs

1. Template Path: pipline.yaml

2. Display name

3. Parameters

4. Location: Data center

5. pipeline root: temp file location

Open Source Pipeline

https://us-kfp.pkg.dev/ml-pipeline/large-language-model-pipelines/tune-large-model/v2.0.0

Deployment

Batch and REST

1. Batch. E.g. customer review. Not real time. 

2. REST API e.g. chat. More like teal time library. 

* pprint is library to format 

LLM provides output and 'safetyAttributes'

- blocked

* We can find citation also from output of LLM

===========

vertexAI SDK

https://cloud.google.com/vertex-ai

BigQuery 

https://cloud.google.com/bigquery

sklearn

To decide data 80-20% for training and evaluation. 

Building AI/ML apps in Python with BigQuery DataFrames | Google Cloud Blog

===========

Examples: 

Istio, Kong, Envoy , Gluee , Trafeik, kgateway, Contour, NGINX, Kong Gateway and many more as per https://gateway-api.sigs.k8s.io/implementations/#gateway-controller-implementation-status

Protocols: gRPC, HTTP/2, and WebSockets

The structure of a Kubernetes Custom Resource Definition (CRD) or manifest file is referred to as an API. This is because it refers to the structure of the API in the Kubernetes control plane

Migration from ingress https://gateway-api.sigs.k8s.io/guides/migrating-from-ingress/#migrating-from-ingress

extension points

ingress has 2 extension points

1. annotations

2. resource end point

primary extension points in GW API:

1. External references

1.1 HTTP Route Filter

1.2 Backend Object Reference

1.3 Secret Object Reference

Here GW API reference 'external reference'

2. Custom implementations

e.g. The RegularExpression type of the 'HTTP Path Match'

3. Policies

A "Policy Attachment" is a specific type of metaresource

Here, Policy reference 'GW API'

• GW API is not API GW
• GAMMA (Gateway API for Mesh Management and Administration) initiative
• A 'waypoint proxy' is a proxy server deployed inside the mesh for E-W traffic.

1. GatewayClass 

- It is at cluster level. so no namespace

- Annotations at GatewayClassfor vendor specific

- It defines controller capabilities

2. Gateway

- Each Gateway defines one or more listeners, which are the ingress points to the cluster

- You can control which services can be connected to this listener (allowedRoutes) by way of their namespace — this defaults to the same namespace as the Gateway 

- Advanced featues like 

-- request mirroring, 

-- direct response injection, 

-- and fine-grained traffic metrics

-- Traffic spilt

- In Istio APIs, a Gateway configures an existing gateway Deployment/Service that has been deployed. In the Gateway APIs, the Gateway resource both configures and deploys a gateway

- one can attach HPA and PodDisuptionBudget to gateway deployment. 

3. HTTP Route: 

- any combinations of hostname, path, header values and query parameters.

- hostname (optional) at HTTP route shall match with hostname at Gateway->Listener->hostname

- A definition of the Gateway to use (in ParentRefs), is referenced by name and namespace

- The backendRefs that defines the service to route the request to for this match

- advanced pattern matching and filtering on arbitrary headers as well as paths.

- In the Istio VirtualService, all protocols are configured within a single resource. In the Gateway APIs, each protocol type has its own resource, such as HTTPRoute and TCPRoute.

- Route and Gateway can be in different namespace

* 4. TLS Route

5. GRPCRoute

* 6. TCPRoute

* not v1, GA

Details: https://gateway-api.sigs.k8s.io/reference/spec/

If you are using a service mesh, it would be highly desirable to use the same API resources to configure both ingress traffic routing and internal traffic, similar to the way Istio uses VirtualService to configure route rules for both. Fortunately, the Kubernetes Gateway API is working to add this support. Although not as mature as the Gateway API for ingress traffic, an effort known as the Gateway API for Mesh Management and Administration (GAMMA) initiative is underway to make this a reality and Istio intends to make Gateway API the default API for all of its traffic management in the future.

https://gateway-api.sigs.k8s.io/mesh/

Gateway controller is for North South traffic. mesh controller is for East West traffic

7. ReferenceGrant: for cross-namespace reference. 

LTM Large Teleco Model : SoftBank is pioneer. Here is WhitePaper by GSMA https://www.gsma.com/get-involved/gsma-foundry/gsma_resources/white-paper-large-telecom-models/

Llama Nemotron Reasoning Model. Open source by NVIDIA on HF

https://www.nvidia.com/en-in/ai-data-science/foundation-models/nemotron/

https://arxiv.org/pdf/2505.00949

AI Factory is a specialized, integrated infrastructure designed to manage the entire AI lifecycle, from data ingestion to model training and deployment for real-time inference

AI Grid is a network of small, highly specialized AI communities. The members of AI Grid share their research work within these communities, initiate collaborations and establish fruitful connections for the future. https://lightning.ai/

https://ai-ran.org/

Building Blocks of the NVIDIA AI Aerial Platform: 

1. NVIDIA Aerial CUDA-Accelerated RAN

2. NVIDIA Aerial AI Radio Frameworks

3. NVIDIA Aerial Omniverse Digital Twin

Reference

NVIDIA GTC25: Telecom Special Address

 8 Day Live Online Workshop

AI Bootcamp for Students

Make Your Child Future-Ready with AI

by Timesof Inida

https://www.notion.com/product Documentation

https://www.todoist.com/ To Do List

https://gamma.app/ For presentation 

https://openai.com/index/sora/ Cinematic Video 

https://www.midjourney.com/home Art Grade Visuals for story telling

https://ideogram.ai/t/explore Typography to image. Communicate in style

https://lovable.dev/ No code web apps

https://n8n.io/ Workflow automation tools

Few more tools

TachyonGPT accelerate the project planning process, potentially saving weeks of effort. This powerful AI assistant allows you to create a complex backlog structure for your project in very little time. Tachyon GPT gives you the power to improve existing work items or generate new work items based on brief titles or descriptions. https://marketplace.visualstudio.com/items?itemName=Neudesic.TachyonGPT

windserf editor and cascade. Agentic code IDE

Reference: https://economictimes.indiatimes.com/masterclass/ai-for-students

https://www.msn.com/en-in/money/news/chatgpt-to-google-gemini-top-5-ai-tools-to-enhance-productivity-mostly-free/ar-AA1GRlt1

New Language Learning

Want to learn a new language this summer? Explore these expert-led platforms

Mobile app https://youtu.be/jyffkeM9GB0

Regional LLM

Sarvam AI launches Bulbul-v2, its voice model with support for 11 Indian languages

https://asr.iitm.ac.in/models/ 

BharatGen  https://bharatgen.tech/  Bharatgen: First Indigenous Language Ai Model Launched In India News In Hindi - Amar Ujala Hindi News Live - Bharatgen:भारत में लॉन्च हुआ पहला स्वदेशी भाषा Ai मॉडल, 22 भाषाओं में करेगा अनुवाद; दूर होंगी संवाद चुनौतियां and Google to collaborate with IIT Bombay’s BharatGen to build indigenous Indic language model

https://aikosha.indiaai.gov.in/home It looks like huggingface website for India

Models https://aikosha.indiaai.gov.in/home/models/all 

Datasets https://aikosha.indiaai.gov.in/home/datasets/all

https://aikosha.indiaai.gov.in/home/resources?from=resource-detail having some PDF books 

https://aikosha.indiaai.gov.in/home/toolkit having a list of popular AI related tools.

LLM

Inside The Brain Of An LLM: What Makes AI So Powerful?

Landscape

https://landscape.lfai.foundation/

https://landscape.pytorch.org/

Models for coding

1. Qwen2.5 Coder

2. Granite Code

3. CodeGemma

4. Deep Seek Coder V2

5. StarCoder 2

6. Code llama

7. Codestral 

Coding tool Google Opal is a new vibe coding app and here's how you can try it for free

Interviews

Pioneering Innovation in Cloud and AI Transformation Done By Chandrakanth Devarakadra Anantha

Innovation in Machine Learning & Engineering Leadership by Pratik Parekh

Amazing Innovation in Telecom Cloud: The Journey of Jayavelan Jayabalan

Handson

https://www.youtube.com/watch?v=RQFfK7xIL28

Keywords

• CAMARA APIs
• Open GW
• Network API
• NaaS

AI impacts API development

Usecase

1. anti fraud

2. location API : book cab for people not having smart phone

3. voice activated AI transaction. book a cab

4. geo fencing. warn people when other people comes close to them. logistic when truck reaches store, offloading

5. future Quality in demand

Challenges

1. monetizing

2. standardizing

3. presenting to non-telco audience

4. focus on right APIs: There are 15 fraud APIs, customer only wants to know is it fraud or not?

5. scale and coverage: approach operator and help them coming to eco system

6. data privacy and consent: no need for customer to provide consent for each new API. it is bad experience

7. education and certification about API. Let developer make new business models and business case. 

8. telco shall listen to industry need. how to solve challenges using advance connectivity and APIs. demand side focus. 

https://www.youtube.com/watch?v=Rg-TKpBuiPI

Popular APIs

• Messaging
• authentication
• Device location, 
• QoS, 
• fraud prevention, 
• identity verification
• age verification

https://youtu.be/XYAwAEM2QQU

https://cpaasaa.com/post-mwc-aduna-vonage-and-the-future-of-network-apis/

Network API centralizes complexity and distribute simplicity

https://www.youtube.com/watch?v=4C9zrRNoxas

Vonage and Infobip : service aggregation

https://www.youtube.com/watch?v=Jh8iUuNHFYw

Network APIs, allow operators to virtualize parts of their networks and provide tailored data and features to developers

Network API v/s Usecase

1. Verify Location: Navigation, geotagging and location-aware notifications, personalized marketing

2. Device Status: Optimize resource usage based on device health and network condition. Identify issue and proactive customer support

3. SIM Density: Ensure optimal user experience during peak hours, SON

4. SIM swap: Fraud Prevention

5. QoD

6. Device identification, device location, and phone number verification

7. Identity and consent management 

8. OTP validation

https://www.vonage.com/resources/articles/what-is-a-network-api/

Vonage Network Registry 

CSP can find who developer uses

Developer can decide which CSP to choose. 

We are moving from Transactional world to conversational world. 

https://camaraproject.org/resources/

https://camaraproject.org/api-overview/

https://github.com/camaraproject

This article is my key take away points from PythonKrit workshop, at Samskrit Bharti Bangalore during March 2025

Dr. Amba Kulkarni explains how ASHTADHYAYI by sage PAANINI is similar to computer programming and compiler design 

https://sanskrit.uohyd.ac.in/faculty/amba/ and https://www.sanskritstudiespodcast.com/1759898/episodes/12324157-16-amba-kulkarni-sanskrit-and-computers

ASHTADHYAYI is also Algorithm and Data structure. Class/Object has data and function. Paanini's DHTAATU list has name of DHAATU and "इत् प्रत्यय". Here "इत् प्रत्यय" indicates, which operation to be performed. We know the challenges with multiple inheritance in Object Oriented Programming. Prof. Ashvini Bhave shows how TADDHITTA indicates single inheritance. 

Sage PAANINI introduced a new data structure SHIVA-SUTRA. He rearranged all character and did slicing then perform Boolean operation that input character belongs to given list or not, given input set of character is subset or not. 

Meta language itself is part of ASHTADHYAYI .

Three types of rules

1. regular rules

2. context free rules

3. context sensitive rules

We use regular expression * for beginning AADI , UPAADHAA for set of characters in middle with [] and $ for end of line (ANTHA). 

We know yacc and bison tools are for context free grammar. If we write all PAANINI rules as per syntax of yacc and bison then we can analyze the complexity of PAANINI's ASHTADHYAYI  grammar. There are few non-formal aspects in ASHTADHYAYI, as it was written to understand by human brain, not by computer. 

Sage PAANINI was about 1500 years ahead of time compare to today's computing power.

Rules are like event in programming. To understand grammar one of the rule shall be evaluated, it is like firing an event. 

ANUVRUTI is similar to factorization in Maths. 

Slides: https://web.stanford.edu/~kiparsky/Papers/paris.pdf and Stream rtsp://stream-serv.inrialpes.fr/Roc/Symposiums_2007/Sanskrit291007B_Gillon.rm by Paul Kiparsky

https://ashtadhyayi.com/

The entire data that powers https://ashtadhyayi.com  https://github.com/chaitanya-lakkundi/ashtadhyayi-com-data/

https://github.com/chaitanya-lakkundi/ashtadhyayi-commentaries/

https://drdhaval2785.github.io/siddhantakaumudi/

https://github.com/drdhaval2785/siddhantakaumudi

https://en.wikipedia.org/wiki/Mahabhashya

https://sanskrit.uohyd.ac.in/

Books

https://en.wikipedia.org/wiki/Algorithms_%2B_Data_Structures_%3D_Programs

https://www.sushmajee.com/reldictionary/literature/grammar/sanskrit-grammar.htm

Books: https://www.ebharatisampat.in/

https://www.amazon.com/Vaiyakaran-Siddhant-Kaumudi-Set-Volumes/dp/B00LND3A5U

Papers

https://www.jainfoundation.in/JAINLIBRARY/books/panini_and_euclid_reflections_on_indian_geometry_269453_hr6.pdf

https://sanskrit.inria.fr/Symposium/Program.html

https://upenn.academia.edu/Cardona

https://independent.academia.edu/SarojaBhate

YouTube / Videos: 

https://www.youtube.com/ashtadhyayi

https://www.youtube.com/playlist?list=PLxPxgIW05q49w0453x8iDZpfv0fNH8ujK

https://www.youtube.com/watch?v=gs0c4UXgM8M

https://www.youtube.com/@prasarbharatisanskrit

https://www.sanskritstudiespodcast.com/1759898

https://www.youtube.com/watch?v=7X5uqiODNPw&list=PLEKLkZ5fxeD0Xt4TKUwAkiRVw_AUV3y_X

https://www.youtube.com/watch?v=_OkzIE61EMg

https://www.youtube.com/watch?v=AGPfSgVqb78

https://www.youtube.com/watch?v=9tndwY-pJAk&list=PLeCoRXpRAy9iK1CTKseX_Vgg9-RcV-Uql

This article is my key take away points from PythonKrit workshop, at Samskrit Bharti Bangalore during March 2025.

XML to Mindmap generation : https://sambhasha.ksu.ac.in/CompLing/tarkasangraha/live/

We can have special tag like

<PAA-LAXANAM>

<PAA-UDAA>

<PAA-VAKYAM>

Other Tools

https://sambhasha.ksu.ac.in/projects/

Aksharamukha

https://www.aksharamukha.com/

https://github.com/chaitanya-lakkundi/aksharamukha

Vaijayantīkośa Knowledge-Net https://sambhasha.ksu.ac.in/CompLing/VK_ACL.pdf

A directory of Indic (Indian) language computing projects and resources https://indic.page/

https://sambhasha.ksu.ac.in/CompLing/chandas/chandas.html 

https://www.gitasupersite.iitk.ac.in/conceptmaps Good resource for Neo4J graph DB

https://sanskritlibrary.org/downloads.html 

https://sanskritlibrary.org/projects.html 

https://sanskritlibrary.org/tools.html 

Krudanta Rupa: https://github.com/chaitanya-lakkundi/kridanta-rupa-android/blob/master/kridanta_rupa_samgraha.pdf

Aadi Shankaracharya : https://www.sankara.iitk.ac.in/ and https://www.advaita-vedanta.org/texts/index.html

https://www.gitasupersite.iitk.ac.in/

GitHub

https://github.com/chaitanya-lakkundi/

https://github.com/drdhaval2785

Useful Sanskrit Alphabet https://github.com/chaitanya-lakkundi/varnamala/blob/main/varnamala.py

https://github.com/drdhaval2785/SanskritVerb/

https://github.com/drdhaval2785/SanskritSubanta

For Kids

https://bala.sambhasha.ksu.ac.in/

https://www.samskritpromotion.in/samskrit-toys

Scholars

https://sanskrit.uohyd.ac.in/faculty/amba/ and https://www.sanskritstudiespodcast.com/1759898/episodes/12324157-16-amba-kulkarni-sanskrit-and-computers

https://web.stanford.edu/~kiparsky/ and https://en.wikipedia.org/wiki/Paul_Kiparsky

                  List Tuple Dictionary

Ordered?         Yes Yes No

Mutable?         Yes No Yes

Different Data Types? Yes Yes Yes

Can be indexed?         Yes Yes Yes by keys

Syntax                 [] () {}

Duplicate elements? Yes Yes Yes, but key must be unique

• Both List and tuple supports: Slicing and skipping index
• Tuple is immutable, so faster

The speaker explains his solution about adding AI for observability. Where observability includes logs, traces and matrices. 

Features

It does not embed log message. most sophisticated GenAI also takes maximum 2 millions token. Logs generates it in 2 seconds. So solution need to feed right data to AI. It understands form log, which field shall be feed as initial value and then instruct to feed more data. 

It creates visualization dashboard based on question

It has level 0 (manual observability) to level 4 (full observability)

It uses AWS Bedrock to solve privacy issue and compliance. 

In future solution : GenAI 

- will understand deployment

- will understand changes between deployments and its impact : cost, error increase or decrease. 

- can go to Github repo to know changes that happen

- can fix the code

- then write test (UT) so it cannot happen again

So it makes much stable environment. It can make autonomous cluster configuration

At present, the solution has

- ability to analyze exception. Root cause analysis of exception. not 100% accurate all the time. It gives list of actions, that are taken to understand & troubleshoot problem. The solution can auto run RCA for each alert. 

As we know GenAI has 3 models

1. generic questions

2. RAG

3. Agent

Yes, the solution will make openAI calls. every openAI call costs money. Now cost is reducing. 

Future we may have trend of : BoY RAG

Ref: https://www.youtube.com/watch?v=IIz8Xpyebug

Final thoughts

The choice between DeepSeek R1, Llama 3.2, and OpenAI o1 depends on specific project requirements:

• Choose DeepSeek R1 for budget-friendly deployments with strong reasoning capabilities.
• Opt for Llama 3.2 if multimodal functionality or edge optimisation is critical.
• Select OpenAI o1 for unparalleled reasoning performance in STEM fields despite its higher cost.

Refernce: 

https://www.msn.com/en-in/money/technology/here-are-the-best-ai-language-models-you-can-use-right-now/ar-AA1xVZ7k

Deepseek R1 vs Llama 3.2 vs ChatGPT o1: Which AI model wins?

DeepSeek-R1, BLOOM and Falcon AI: Exploring lesser-known open source LLMs

GitHub - deepseek-ai/awesome-deepseek-integration

(1) Use DeepSeek-R1 in Microsoft Word Locally. No Monthly Fees. - YouTube

SA is at cluster level. 

So Nepheo could not use SA

Every CSP has workload identity

spiffe is standard: 

- spiffe id. It is URL. 

- spiffe verifiable documents (SVIDs): cert or toekn

- The spiffe workload API. 

spire: spiffe Runtime Environment. 

- A toolchain of API for establising trust based on spifee

- provides out of the box attestation plugins

Expiry is short. can be 4 hours. So no need of revocation

* spire agent can be colocated. it is dameonset in K8s. 

=========

Nephio

ss7, sigtra, ngin, CN model (e.g. ORAN)

DISH is on AWS

CP based requirement for identity

Nephio SIG security wiki page has all details

Porch : Package Orchestration KPT

KPT does in place substitution 

5G requirements / usecases

IMS, SMO , IMS

LF article about Nephio spifee implementation at LF wiki

Catalog packages at GitOps

Each cluster shall have its own repo

Identity federation is based on cert chain. 

R3 Oct 23 of Nephio. 

It is proposed solution. It will be upstream. 

Workload identity solution shall not be native to specific cloud provider. 

Identity federation across CSPs. 

Google, E//, RedHat are in Nephio

SPIRE's alternative may be due to speicfic attestion plugin

What protocol between SPIRE Agent and SPIRE server? Bootstrap trust. it is pre-provision aspect. REST API and TLS. x.509 cert will be pulled. protocol is spire specific

Today's attestation is based on SA, pod labels, namespace. 

CA, Cert Manager can be used. 

Telecom Networks are complex due to multi layer, multi vendor

N/w Management -> SDN -> Intent Based Networking (programable and declarative) -> Cloud Native Networking

Earlier Monolithic NMS with FCAPS

Now : CICD, Microservice, K8s. 

NSP (N/s Service Platform) is for IP and optical domain

It has API (OpenAPI Spec). 

Model-driven mediation

Framework has orchestration 

Contributed by Nokia: Kubenet, gNMIc, SDCIO

1. Unified Artifactory Manager Component

It uses Kubespray

UAM creates CRs. CRs are consumed by deployer. Deployer is short lived job. 

2. Telemetry: 

A: internal NSP components

B: External system

Four Core Principle

1. Model driven

2. Vendor & Mediation Agnostic

3. Horizontal scale

4. Resilent

Six Layers

6. Analytics and optimization layer

5. o/p / storage layer : Kafka

3.and 4 make it model driven

4. Normalization Layer

3. Mapping layer

2. Collector layer (SNMP, gNMI) 

1. N/w layer

Architecture

UAM, Restconf GW

source : from network using SNMP, gNMI

Sink: influxDB, Prm, VErtica, Kafka, PostgreSQL, File

Source and Sink are connected using NATS. NATS also connected with multiple transform worker using transformer CR from UAM

gNMIc

1. single mode

2. CLI mode (auto complete option)

3. cluster mode (more replica. one is leader). 

Kubenet and SDCIO

declarative model and event driven reconciliation. It is more n/w automation using K8s. Gitops principle. 

Arch:

SDCIO Schema Driven Configuration. 

IPAM etc are CRD to build abstract network configuration. 

Config CR and ConfigSet CR, RunningConfig, UnmanagedConfig. It has different backend own etcd. 

YANG by schema server. 

==========================

BNG, CUPS specific implementation 

Kubenet Nephio are solving same problem? May be overlap. 

APIs for sink? customer provides sink. 

Kubenet is automation. more than NMS

Slide 21: Cisco Prime