Express YourSelf !

Connect. Build. Contain. Agents in the AI Governance Era

noreply@blogger.com (Manish Panchmatia) — Mon, 14 Sep 2026 12:29:04 +0000

Reference https://www.meetup.com/collabnix/events/316301263/

1. Contain, Forecast, Adjudicate: Three Agent Controls No Protocol Gives You

https://www.nasiko.com/

2. Securing Your Agentic Stack (Workshop)

https://agentic.dockerworkshop.com/

https://agentic.dockerworkshop.com/#/labs/securing-the-agentic-stack-slides

https://agentic.dockerworkshop.com/#/labs/securing-the-agentic-stack

1. What it contains? What is software Artifact

SBOM

docker scout sbom --format spdx --output baseline.spdx.json catalog-service:baseline

2. From where it comes from?

Provenience

3. CI pipeline. Who approve image with vulnerabilities? Can I. verify attestation source

https://docs.docker.com/scout/deep-dive/advisory-db-sources/

match with SBOM

Now AIBOM term is emerging. https://www.ajeetraina.com/ai-bom-explained-why-your-sbom-stops-where-your-ai-system-starts

VEX: Vulnerability Exploitability eXchange

In Docker Desktop, we can filter vulnerabilities based on fixable or not

SLSA

Level 1 to 3

FIPS 140 For US

4. Can it be restricted? Sandbox

We need base image with near zero vulnerabilities.

All images shall be signed

Allow coding agent only what it needs.

"/rc" in Claude. Remote control. You will keep getting notifications in your mobile.

AI Agent

local sandbox and cloud sandbox. SBX is running on microVM. Agent can change kernel also. So SBX runs on microVM instead of container.

Inside mircoVM also we run Docker engine and docker daemon

Docker Hub have MCP policy, AI policy

Now we have SBX compose file with policy

MCP Toolkit

Hardened MCP servers

https://agentic.dockerworkshop.com/#/labs/securing-the-agentic-stack-slides/workshop-75

Docker hub

DHI Docker Hardening Images

Images and AI models also on

3. Docker sbx kits: you explorations to contain AI Agents begins here

AI Agent

https://docs.docker.com/ai/sandboxes/customize/

https://docs.docker.com/ai/sandboxes/customize/kits/

https://hub.docker.com/search?type=sbx_kit

Tools

1. MIXIN kit

It has enhanced capabilities

build agent from scratch

2. Sandbox Kit

-------

Kit has spec.yaml file

Files are payload. it can have docker compose file. certificate file etc. Some will go to sandbox and other files remain on laptop

start from Mixin kit, as Sandbox kit has many definition

Now let's have customize AI agent.

https://floci.io/ is like localstack. Cloud emulators

floci CLI is inside sandbox

1. create shell sendbox

2. run docker compose

same can be done with spec.yaml file

We have DHI for langchain also. It can be inside sandbox

4. Beyond the Agent: Building AI Systems You Can Trust

If it hallucinate then workflow has problem or model has problem?

5. The New Primitives of AI: YAML, OCI, and Agent Infrastructure

you write agent in your Jupiter Notebook

"It works on my notebook"

"docker agent"

oci artifacts

API Days India 2026 - Part 1

noreply@blogger.com (Manish Panchmatia) — Mon, 14 Sep 2026 12:20:48 +0000

I did not attend this event in-person. I gone through YouTube Playlist https://www.youtube.com/playlist?list=PLcWDDGrTp5AU It has 41 videos

In part 1, let me cover few of them

-------------------

1. Made in India. the founders behind API tools

specmatic
Beeceptor
keploy.io
postman
bruno
karate labs

------------------------

2. Restoring Trust in AI-Native development

Earlier we used to have Pre-commit hook before agent started coding.

Now, SDD = spec driven development

Vibe coding was based on prompt

now spec is new source code

Harness engineering

1. Guides gives feedback to agent

2. Sensors for self-correcting loop

3. Executable intent

4. Executable architecture

5. Continuous Governance

------------------------

3. Death of API Management

The speaker is founder of "bunny and cloud" a collaborative development tool for humans and AI

https://bunnyandcloud.com/

He explain reasons.

1. A New practices is emerging: Context engineering

A right context at right time for agent, so it can reason and act reliably.

2. Agents are taking all management attention

AI GWs and context contracts extend API Management into agent governance.

3. API Management does not get intent

But agent needs intent

We need to hard code and orchestrate the agents for different workflows. Agent does not think about workflow.

4. APIs are relegated to the execution layer

Reasoning layer by LLM (Probabilistic)

context layer by MCP and RAG

Execution layer (deterministic)

5. The GW shift

Kong is decoupling API GW and AI GW

Portkey AI GW pioneer is acquired by Palo Alto Networks

AI GW enforce policy to every call to LLM, MCP, RAG

6. The tokenomics is replacing APInomics

7. Context Management includes managing APIs

Microcontext. Not DB dump. Agent shall receive smallest truthful slice of bounded context.

8. From API endpoint Management to capabilities management

Agent Registries

Instead of DX, now we need AX (Agent eXperience)

Context Management is new API Management

pillar 1: Identity and intent context

pillar 2: Business and domain context

pillar 3: Knowledge and evidence context (RAG)

pillar 4: Execution and feedback context (MCP)

AI GW examples

1 Portkey AI GW

2 Kong

3 Truefoundry (someone added from the audience)

The attack surface is different for AI GW.

------------------

36. Skills and MCP

https://www.skills.sh/

API related classes / certifications

https://apimasters.io/

Kyverno

noreply@blogger.com (Manish Panchmatia) — Thu, 20 Aug 2026 07:34:51 +0000

Kyverno Policy

- 2 types: Policy and ClusterPolicy

- Multiple Rules

- Match / Exclude

-- Match resources

kind is mandatory. names, namespaces, operations, selector are optional.

Wildcards * supported in kinds, names, namespaces

All are AND condition.

Any means OR condition

We can mention based on who created

exclude:

any:
- clusterRoles:
- cluster-admin
- subjects:
- kind: User
name: John

match AND exclude

exclude must be a subset of match

- Action

1. Validate ( allow / deny )

2. Mutate

3. Generate new K8s object

4. Verify image (Cosign/Sigstore)

- Enforce / Audit

* It uses JAMESPath

- Filter JSON

# Returns a list of container objects that match the condition
{{ request.object.spec.containers[?starts_with(image, 'nginx')] }}

validate:

message: "Nginx images are not allowed!"
deny:
conditions:
all:
# Filter the list. Use length() to count.
# If count > 0, it means a violation exists -> Block.
- key: "{{ request.object.spec.containers[?starts_with(image, 'nginx')] | length(@) }}"
operator: GreaterThan
value: 0

- pipe

Used to extract a specific field from a complex object into a flat list.

# Input: List of container objects
# Output: ["nginx:latest", "redis:alpine", "busybox"]
key: "{{ request.object.spec.containers[].image }}"

kyverno jp query -i object.json 'spec.containers[].name'

Combo (Filter + Pipe): “Get the containerPort of the container named ‘app’”

request.object.spec.containers[?name == 'app'].ports[].containerPort

You want to find the names of all volumes that are of type emptyDir.

spec.volumes[?emptyDir != null].name

kyverno jp query -i object.json "spec.volumes[?emptyDir != null]"

- null handling

Risk: {{ request.object.metadata.labels.team }} (If null -> Error).

Safe: {{ request.object.metadata.labels.team || '' }} (If null -> treat as empty string).

- The length function

Example: “A Pod must not have more than 3 containers.”

validate:
deny:
conditions:
all:
- key: "{{ request.object.spec.containers | length(@) }}"
operator: GreaterThan
value: 3

- if / else

- sum

- contain means exist : contains(request.object.metadata.labels, 'production')

advance mutate foreach

mutate:

foreach:
- list: "request.object.spec.containers"
patchStrategicMerge:
spec:
containers:
- name: "{{ element.name }}"
securityContext:
readOnlyRootFilesystem: true

* Aut-Gen: If rule for pod then automatically generate rules for Deployment, StatefulSet, DaemonSet, etc.

https://release-1-8-0.kyverno.io/docs/writing-policies/autogen/

Generate rule has synchronize flag

synchronize: true: Kyverno complete managed lifecycle

synchronize: false: Kyverno created for the first time then user can edit it manually without getting revert back like synchronize: true

* request.object is the incoming resource configuration (the new state) that is being submitted to Kubernetes API server

Documentation: https://kyverno.io/docs/policy-types/cluster-policy/variables/

# -------------------------------------------------------------

# ACTION: If Kyverno is dead, just let the request go through.

# -------------------------------------------------------------

failurePolicy: Ignore # or Fail

PolicyReport

PolicyReport stores the results of those rules.

The PolicyReport is essentially a “Health Check Report Card” for your Kubernetes resources.

Its main goal is Observability & Auditing.

It provides summary and then detail about all failures. For Example

apiVersion: wgpolicyk8s.io/v1alpha2
kind: PolicyReport
metadata:
name: polr-ns-default
namespace: default # It lives next to the Pod, not at the cluster level
labels:
app.kubernetes.io/managed-by: kyverno
summary:
pass: 0
fail: 1
warn: 0
error: 0
skip: 0
results:
- policy: require-labels # The name of the ClusterPolicy responsible
rule: check-for-team-label # The specific rule name
category: Best Practices
severity: medium
result: fail # The outcome (fail, pass, warn, error, skip)
message: "Validation error: label 'team' is required"
source: kyverno
resources: # The specific object that failed
- apiVersion: v1
kind: Pod
name: nginx
namespace: default
uid: a1b2c3d4-e5f6...

* Background scan never delete resource even with enforce mode

* For background scan following variable are not relevant

request.userInfo.*

request.operation

request.dryRun

serviceAccountName in admission context

Document: https://kyverno.io/docs/policy-reports/background/

* Cleanup policy delete pods

https://kyverno.io/docs/policy-types/cleanup-policy/

Kyverno CLI

* for given resource, policy is pass or fail

kyverno apply policy.yaml --resource pod.yaml

* test JAMESPath expression against JSON

kyverno jp query -i object.json 'metadata.labels'

* Check policy YAML is written correctly or not

kyverno validate policy.yaml

External Data Source

Purpose: It allows you to load data from outside into a variable before the rule logic (validate/mutate) runs.

In order to consume data from a ConfigMap in a rule, a context is required... The context data can then be referenced in the policy rule using JMESPath notation.

Kyverno supports 3 main data sources in context:

1. Kubernetes Resources (via API Call): Look up existing data in the cluster (e.g., ConfigMaps, Secrets, Services).

2. External APIs: Make an HTTP call to a service outside the cluster.

3. Image Registry: Fetch metadata about a container image (e.g., image size, architecture).

verifyImages:
- imageReferences:
- "ghcr.io/myorg/*"
attestors:
- entries:
- keys:
publicKeys: |-
-----BEGIN PUBLIC KEY-----
...
-----END PUBLIC KEY-----

https://main.kyverno.io/docs/policy-types/cluster-policy/external-data-sources/

Kyverno Mutate — JSON Patch

the standard patchStrategicMerge merges YAMLs together.

patchesJson6902 is a mutation method specific operations (RFC 6902 standard) to tell Kyverno exactly how to change the data.

Usage:

* Removing a field (impossible with standard merge).

* Adding an item to a specific position in a list (arrays).

* Replacing a value entirely without merging.

It follows the JSON Patch format:

* op: The action (add, remove, replace).

* path: The location of the field (e.g., /metadata/labels/mytag).

* value: The data to put there.

Example: “Add a sidecar container”

https://main.kyverno.io/docs/policy-types/cluster-policy/mutate/#rfc-6902-jsonpatch

TTL Default of Certification in Kyverno:

https://pkg.go.dev/github.com/kyverno/kyverno/pkg/tls

const (

CAValidityDuration = 365 * 24 * time.Hour // 365 days

TLSValidityDuration = 150 * 24 * time.Hour // 150 days

CertRenewalInterval = 12 * time.Hour // 12 hours

)

https://www.udemy.com/course/complete-certified-kyverno-associate-kca-exam-prep/

https://medium.com/@kienlt.qn/prepare-for-the-kyverno-certified-associate-kca-exam-c144906f9bc2

Concurrent Policies Generation Number Default!

PolicyException CRD

CEL

Epic history of LLM

noreply@blogger.com (Manish Panchmatia) — Sun, 05 Jul 2026 07:45:06 +0000

RNN. Seq to seq NLP tasks.

1. Many to one: Sentimental Analysis

2. One to Many: Image caption

3. Many to Many:

- Synch many to many: # input = # output. E.g. Part of speech tagging, Named Entity Recognition

- Asynch many to many: translation, text summarization, question and answer, chatboat, speech to text,

Seq2seq model is used for Many to Many

Stage 1: 2014 Encoder decoder network

Encoder and decoder are LSTM. RNN and GRU are other options.

It is good for small sentences. Not for 30+ words

BLEU score

Stage 2: 2015 Attention Mechanism

Encoder is same

Attention Mechanism: Attention layer at decoder finds out which hidden state is useful at each stage of decoder and generate context vector for that stage. So, Multiple context vectors based on encoder's (hidden state of LSTM = ctht vector) are available to decoder.

Training time is more.

2015 to 2017: May types of Attention Mechanisms were introduced.

Stage 3: 2017 Transformer

No LSTM

No RNN Cell

Self-attention was introduced

Both encoder and decoder uses attention

Transformer can process all words in parallel

1. Attention layer = Multi Head Attention

2. Normalization Layer

3. Dense Layer

4. Input embeddings

It needs hardware, time, and data

Stage 4: 2018 Jan Transfer Learning

Challenges

1 Single model cannot perform all tasks like sentimental, translation, summarization

2 lots of labeled data

Universal Language Model Fine-tuning ULMFiT proposed to use Language modelling as Pre-training. Language modelling is NLP task to predict next word. Advantages

1. Rich feature training

2. unsupervised task

model: AWD LSTM model

data set: wikipedia

finetuning changed output as classifier with many data set

Scratch 10000 data. Now fine tune 100 data still better result

- No transformer

Now in 2018, we have two technolgoies

1. architecture: transformer

2. training. Pretrain and transfer learning

Stage 5: 2018 Oct LLM

Transfer learning on transformer

1. Google : BERT (encoder only model)

2. OpenAI: GPT (decoder only model)

LM to LLM

1. data

2 hardware GPU clusters

3 time : days to weeks

4. cost = h/w + electricity + people + infra

5. energy consumption

---------------

GPT3 - > chatGPT

1. RLHF : Reinforcement Learning from Human Feedback

2. incorporate safety and ethical guidelines

3. improvement in contextual point

4. dialogue specific

5. continuous improvement based on user feedback

Reference https://www.youtube.com/watch?v=8fX3rOjTloc&list=PPSV

साधनमन्त्र

noreply@blogger.com (Manish Panchmatia) — Sun, 24 May 2026 09:31:23 +0000

इदानीं वयं समुहे साधनमन्त्रस्य जपं कुर्याम।

---------------------------------------------------------------------------------

अक्षरम् अहं - पुरुषोत्तमदासोऽस्मि ।

अक्षरसदृशः अहं - पुरुषोत्तमस्य दासः अस्मि ।।

---------------------------------------------------------------------------------

इदानीं वयं हस्तौ बध्वा गद्गद कण्ठेन प्रार्थनां कुर्याम।

---------------------------------------------------------------------------------

हे महाराजाः! हे स्वामिनः! हे प्रमुखस्वामिमहाराजाः!

हे महन्तस्वामिमहाराजाः!

सर्वेभ्य: सत्सङ्गस्य यथार्थं सुखं प्राप्येत।

तदर्थम् सर्वेषां सर्वासाम् उपाधीनां निवारणं कुर्वन्तु।।

अन्तःशत्रुत:, अहं-ममत्वरूपिनी मायातः, तथा च कुसङ्गत:, रक्षां कुर्वन्तु।

भवत्सु तथा च भवतां भक्तेषु अखण्डः दिव्यभावः वर्तेत।

सर्वेषां दासानुदासाः भवेम।।

सर्वत्र सर्वकाले गुणानाम् एव दर्शनं भवेत् , ऐक्यं वर्धयितुं च बलं लभ्येत।

अक्षरपुरुषोत्तमसिद्धान्तः अस्माकं जीवेषु दृढो भवेत् , तस्य च प्रवर्तनं क्रियेत।

अस्मिन्नेव जन्मनि एकान्तिकधर्मं सिद्धं कृत्वा , अक्षरधामं प्राप्नुयाम, एवं आशीर्वादान् ददतु।

---------------------------------------------------------------------------------

अस्याः प्रार्थनायाः परिपूर्तये, तथा च परम पूज्य महन्तस्वामिमहाराजानां स्वास्थ्यः अखण्डं निरामयं भूयात्।

सकले विश्वे ऐक्यं शान्तिश्च प्रवर्तेयाताम्।

सर्वे तनो मनो धनैः सर्व प्रकारेण सुखिनः भवेयुः।

सर्वेषां च शुभ सङ्कल्पाः सिद्धाः भवेयुः।

तदर्थम् इदानीं वयं स्वामिनारायण महामन्त्रस्य जापेन प्रार्थनां करिष्यामः।

जयतु स्वामिनारायणः।

https://www.youtube.com/live/cRrnM9tMIg0?si=6_Kyn3b-wNcye9IK&t=2067

DSPy

noreply@blogger.com (Manish Panchmatia) — Wed, 18 Mar 2026 06:58:00 +0000

DSPy = Declarative Self-improving Python.

Components

1. language model — LLM that will answer our questions,

2. signature —a declaration of the program’s input and output (what task we want to solve),

- 1. inline

- 2. class

dspy.InputField()

List[Literal['', '', '']] = dspy.OutputField()

3. module — the prompting technique (how we want to solve the task).

- Building blocks

- different prompting strategies,

- 1. dspy.Predict

- 2. dspy.ChainOfThought

- 3. dspy.ReAct (to add tools = function calling

4. Optimiser

- 1. Automatic few-shot learning (e.g. BootstrapFewShot or BootstrapFewShotWithRandomSearch)

- 2. Automatic instructions optimisation (e.g. MIPROv2)

- 3. Automatic fine-tuning (e.g, BootstrapFinetune)

Other points

dspy.inspect_history for logs
Caching

# 1. updating config

dspy.configure_cache(enable_memory_cache=False, enable_disk_cache=False)

# 2. not using cache for specific module

math = dspy.Predict("question -> answer: float", cache = False)

dspy.configure(adapter=dspy.JSONAdapter())

DSPy is integrated with MLFlow (an observability tool)

Reference

Article

https://miptgirl.medium.com/programming-not-prompting-a-hands-on-guide-to-dspy-04ea2d966e6d

https://github.com/miptgirl/miptgirl_medium/blob/main/dspy_example/nps_topic_modelling.ipynb

https://www.dbreunig.com/2025/06/10/let-the-model-write-the-prompt.html

https://thedataquarry.com/blog/learning-dspy-1-the-power-of-good-abstractions/

https://thedataquarry.com/blog/learning-dspy-2-understanding-the-internals/

https://thedataquarry.com/blog/learning-dspy-3-working-with-optimizers/

https://thenewstack.io/goodbye-manual-prompting-hello-programming-with-dspy/

https://dzone.com/static/csrfAttackDetected.html

Paper

https://arxiv.org/abs/2310.03714

Website

https://dspy.ai/

https://dspy.ai/tutorials/games/

Course

https://www.deeplearning.ai/short-courses/dspy-build-optimize-agentic-apps/

Github

https://github.com/stanfordnlp/dspy

Hashicorp User Group Bangalore Meetup #1 : Powering the Multi-Cloud Era

noreply@blogger.com (Manish Panchmatia) — Sat, 07 Mar 2026 15:08:00 +0000

Alternatives for IDP

(1) https://github.com/JanssenProject/jans https://github.com/JanssenProject/jans/tree/main/jans-keycloak-link https://imshakil.medium.com/janssen-mod-auth-openidc-module-to-test-openid-connect-single-sign-on-s… It is by Glu

(2) Vault it self support OIDC https://developer.hashicorp.com/vault/docs/secrets/identity/oidc-provider https://brian-candler.medium.com/using-vault-as-an-openid-connect-identity-provider-ee0aaef2bba2

SQL++ is for JSON data. https://www.couchbase.com/sqlplusplus/

https://techmilap.com/ is free website for hosting event

Vault can provide dynamic temporary secrets to access data for each identity used by consumer. so later on, we can audit, who has accessed data. In our case, pods use ServiceAccount (SA). here we get dynamic secret per serviceaccount. So we cannot audit which pod accessed the data. we can only audit, data is accessed by which ServiceAccount. This dynamic secret has short life so one cannot use it again. SA we can use it as many time as we want.

Vault secure data in-transit with TLS and other encryption method that is called "encryption as a service"

In terraform, state file is the most confidential.

Nomad is alternative of K8s. It can manage VM also using QEMU driver. Consul is used for networking and service. Fabio is for ingress and load balancing in Nomad.

Event: Hashicorp User Group Bangalore Meetup #1 : Powering the Multi-Cloud Era, Sun, Nov 2, 2025, 10:00 AM | Meetup

Identity Provider

noreply@blogger.com (Manish Panchmatia) — Sat, 07 Mar 2026 15:04:00 +0000

https://github.com/pando85/kaniop Kaniop is a Kubernetes operator for managing Kanidm.

https://kanidm.com/ Kanidm is a modern, secure identity management system that provides authentication and authorization services with support for POSIX accounts, OAuth2, and more. It is simple and written in rust

IDP

(1)

https://github.com/JanssenProject/jans

https://github.com/JanssenProject/jans/tree/main/jans-keycloak-link

https://imshakil.medium.com/janssen-mod-auth-openidc-module-to-test-openid-connect-single-sign-on-s…

It is by Glu

-------------

Why Choose Keycloak?. Understanding the Need for an Identity… | by J3 | Jungletronics | Medium

Ory

Quickstart | Ory

Ory Kratos Helm Chart | k8s

GitHub - ory/k8s: Kubernetes Helm Charts for the ORY ecosystem. · GitHub

Ory Hydra: OAuth 2.0 and OpenID Connect server | Ory

GitHub - ory/kratos: Headless cloud-native authentication and identity management written in Go. Scales to a billion+ users. Replace Homegrown, Auth0, Okta, Firebase with better UX and DX. Passkeys, Social Sign In, OIDC, Magic Link, Multi-Factor Auth, SMS, SAML, TOTP, and more. Runs everywhere, runs best on Ory Network. · GitHub

GitHub - ory/hydra: Internet-scale OpenID Certified™ OpenID Connect and OAuth2.1 provider that integrates with your user management through headless APIs. Solve OIDC/OAuth2 user cases over night. Consume as a service on Ory Network or self-host. Trusted by OpenAI and many others for scale and security. Written in Go. · GitHub

The Top 7 Ory Kratos Alternatives

The Paper That Changed Everything: Attention is All You Need

noreply@blogger.com (Manish Panchmatia) — Sat, 07 Mar 2026 13:31:00 +0000

Here are few links

The Paper

https://arxiv.org/pdf/1706.03762.pdf

------------------------

Medium

https://medium.com/@SimplifyingFutureTech/understanding-attention-is-all-you-need-750713a1631b

https://medium.com/codex/attention-is-all-you-need-explained-ebdb02c7f4d4

-------------

PoloClub

https://poloclub.github.io/transformer-explainer/

https://arxiv.org/abs/2408.04619

https://www.youtube.com/watch?v=ECR4oAwocjs

-----------

Last Few videos of https://www.youtube.com/watch?v=2dH_qjc9mFg&list=PLKnIA16_RmvYuZauWaPlRTC54KxSNLtNn

https://hasgeek.com/fifthelephant/paper-reading-meet-up-december-2023/

https://www.linkedin.com/pulse/decoding-attention-all-you-need-how-transformers-ai-yuri-sylse/

--------------

Embedding is representation of text in multi dimensional space

Diffusion model add noise and then remove it. It is for multimodal.

Multi head = syntax + semantics + position. It improves expressiveness and captures richer patterns.

Attention is about which embedding to look at. It does not change embedding.

Few other miscellaneous link from event https://luma.com/d0yhf0ib

1. IronClaw

https://github.com/nearai/ironclaw

https://www.ironclaw.com/

IronClaw is the secure, open-source alternative to OpenClaw that runs in encrypted enclaves on NEAR AI Cloud. TEE (Trusted Execution Environment)

VoIP in Agentic AI era

noreply@blogger.com (Manish Panchmatia) — Sun, 22 Feb 2026 13:20:00 +0000

Once upon a time signaling stack is separated from voice as packet switched SS7 network, with its own protocol stack. SS7 over TCP/IP stack is SIGTRAN. VoIP signaling plane has protocols like H.323 (by ITU), SIP (by IETF) and MEGACO. SIP became most popular. VoIP data plane is RTP. Now in era of Agentic AI, we have business solutions for different verticals to integrate voice with STT, LLM, TTS etc. Here are few resource URLs

All Relevant technologies

https://www.voip-info.org/

https://telecom.altanai.com/

Signalwire

https://www.linkedin.com/posts/briankwest_github-signalwire-demosveronica-this-activity-7430982255675678720-jsTH/

https://developer.signalwire.com/sdks/agents-sdk/

https://github.com/signalwire-demos

https://signalwire.com/

https://postpromptviewer.signalwire.io/

FreeSWITCH

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

https://signalwire.com/freeswitch

https://github.com/signalwire/freeswitch

https://developer.signalwire.com/freeswitch/FreeSWITCH-Explained/

https://github.com/amigniter/mod_audio_stream

https://github.com/sptmru/freeswitch_mod_audio_stream

https://medium.com/@srivastava.vikash/day-9-real-time-voice-ai-starts-here-streaming-audio-from-freeswitch-a45d69547164

https://www.cyberpunk.tools/jekyll/update/2025/11/18/add-ai-voice-agent-to-freeswitch.html

Asterisk

https://www.asterisk.org/

https://en.wikipedia.org/wiki/Asterisk_(PBX)

https://github.com/asterisk/asterisk

Plivo

https://www.plivo.com/

https://github.com/plivo

JsSIP

https://jssip.net/

https://github.com/versatica/JsSIP

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

Security

https://www.frafos.com/

OverSIP

https://oversip.versatica.com/

https://github.com/versatica/OverSIP

https://rubygems.org/gems/oversip/versions/2.0.1?locale=en

https://www.voip-info.org/oversip/

OfficeSIP

https://officesip-server.software.informer.com/

https://telecom.altanai.com/2014/10/13/sip-server-officesip/

https://sourceforge.net/projects/officesip/

https://github.com/vf1/sipserver

FlexiSIP

https://github.com/BelledonneCommunications/flexisip

https://www.linphone.org/en/flexisip-sip-server/

https://www.linhome.org/software-products/flexisip/

https://wiki.linphone.org/xwiki/wiki/public/view/Flexisip/

Tools

https://postpromptviewer.signalwire.io/

https://github.com/briankwest/libnemo_normalize

https://github.com/signalwire-demos/utils

https://github.com/xiph/rnnoise

FreePBX

https://www.hostinger.com/in/tutorials/freepbx-tutorial

https://www.freepbx.org/

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

https://github.com/freepbx

Others

https://medium.com/@dwilkie_34546/implementing-ai-powered-voice-at-somleng-a-technical-deep-dive-93edbb920e02

https://stringee.com/en/

https://www.kamailio.org/w/

https://github.com/resiprocate/resiprocate/wiki

https://www.kaplansoft.com/teksip/

https://deepgram.com/

https://github.com/dograh-hq/dograh Voice AI agent

Transformers & Large Language Models - 1 of 9

noreply@blogger.com (Manish Panchmatia) — Tue, 10 Feb 2026 12:23:00 +0000

• Background on NLP and tasks

NLP Tasks

1. Classification

- Sentimental analysis :

* Examples: Amazon reviews, IMDB critiques, Twitter.

* Many to one RNN example.

Input: sequence of data

Output: scaler.

- Intent detection

- Language detection

* One to many RNN example.

Example: Image Captioning and Topic modeling

Input: single or scaler

output: sequence of data

2. "Multi"-Classification

* Synchronous Many to many RNN example.

Example: Part of speech tagging and Named entity recognition (NER): Dataset = annotated Reuters newspaper (CONLL-2003, CONLL+)

Input: sequence of data

output: sequence of data

- Dependency parsing

- Constituency parsing

3. Generation

* Asynchronous Many to many RNN example.

Example : Machine translation: Dataset = WMT'14 Translation quality unit is , Question answering, Summarization, Speech to text

Input: sequence of data

output: sequence of data

Length is not equal. No one to one mapping.

This RNN example is now done with transformer, LLM.

- Text generation

History of LLM

1980 RNN

1997 LSTM (Theoretical Foundation)

2013 Word2Vec

2014 Sequence to Sequence Learning with NN

2015: "Neural machine translation by jointly learning to align and translate" It introduced attention mechanism. Here sequential nature of processing at encoder and decoder.

2017: Transformer. Parallel processing. "Attention is all you need". Encoder and decoder both have self attention.

2018: Transfer learning. "Universal language model fine tuning (ULMFit) for text classification"

- Introduced language modelling

- Now common model for all usecases

- No need of supervised data

- It is about predicating next word.

Transformer Language Model

1. BERT by Google (encoder only model)

2. GPT by OpenAI (decoder only model). Then GPT2, GPT3 etc.

2020s LLM

• Tokenization

1. Arbitrary (n/a)

2. Word (multiple tokens with similar meanings need same embedding, so Word variations not handled)

3. sub-word : focus on common root. Increase sequence length. Tokenization more complex

4. character level: can correct mis-spelled word & CasINg. Sequence length is much longer. No OOV

• Embeddings

Word (Token) Representation by vector

OHE = One Hot Encoding

cosine similarity

• Word2vec, RNN, LSTM

1. Word2Vec

It is ANN with proxy-task

1. CBOW: Continuous Bag of Words. You predict the target word

2. Skip-gram : You take the target word and predict words around it

Word order does not matter

Embeddings is not context aware

Dimension size example 768

Special token to indicate "end of sequence"

2. RNN Recurrent Neural Network

Connection forms a temporal sequence

H = Hidden state = A = Activation Vector = Context Vector.

RNN is used for all 3 NLP tasks

1. Classification

2. "Multi"-Classification

3. Generation

RNN is keep forgetting the past. This phenomena is called "vanishing gradient"

Word order matters in RNN

3. LSTM = Long short-term memory

1. hidden state

2. cell state

• Attention mechanism

Attention tries to have a direct link between next word that we are predicting and something from the past.

"self-attention" is main principle of "Attention is all you need" 2017 paper

"self-attention" = Instead of sequential, let direct connection with all part of text at once.

Concept of Query, Key and Value

We compare Q to K. How they are similar and then take corresponding value

Softmax converts unnormalized network output into probability for different class such that value is [0,1] and sum is 1.

Formula – Given a query Q, we want to know which key K the query should pay "attention" to with respect to the associated value V.

attention = softmax ( Q * K ^ T / Sqrt (dimension of K) ) * V

There are three attention layers

1. Attention layer at encoder to compute embeddings from input

2. Decoder-decoder attention OR self-attention layer in decoder, It is is masked, because it only look at those token that are translated. It determines: what other token of output sentence is useful to predict next token.

3. cross-attention layer : expressed as function of what is seen in input. Last part of encoder. it is fetch to decoder.

We have direct link to all token. So order words does not matter. (unlike RNN). So we have Position Encoding: to inform position of word in sequence.

BOS Token: Beginning of Sequence.

EOS Token: End of Sequence

• Transformer architecture

Self-attention is achieved by transformer = encoder and decoder

1. Encoder computes meaningful embedding from input text. We have N such encoders. Input layer generates position aware embedding matrix with size d = model size and length = length of input sequence = n

Encoder projects input sequence on 3 spaces Wk, Wq and Wv. so model learns.

attention = softmax ( Q * K ^ T / Sqrt (dimension of K) ) * V

Projecting on Wq gives a matrix where each row represents a given query Q. So we get matrix Wo that is project back to original dimension of embedding.

K^T is each column represents key of each token.

When we multiple K^T and Wq, Each row represents projection of query over each key and then get probability distribution.

Now multiple with matrix V

This is self-attention mechanism. means compute representation of each token as function of other tokens. it is done by attention layer.

Multi-Head Attention (MHA) means this computation is done in different way. So model can learn

- different representation

- different projections

so all token of input text attend each other.

It is masked self-attention layer.

A Multi-Head Attention (MHA) layer performs attention computations across multiple heads, then projects the result in the output space.

Variations of MHA

* Grouped-Query Attention (GQA) and

* Multi-Query Attention (MQA)

that reduce computational overhead by sharing keys and values across attention heads.

Head is term given to project matrix that we used to obtain Q, K, V. With more heads, model learns different projection. It is like multiple filters in convolution layer in computer vision.

h = number of heads

For having h number of heads, the output of attention is h such matrices. Here, because of gradient decent every time we get different result. Each objective function with degree of freedom. We concatenate output of all headers with respect to columns.

2. FFNN (Feed Forward Neural Network) : so model learn another kind of projection

so we get rich representation of input token

In LLM, hidden layer has higher dimension. So model has enough degree of freedom to learn useful representation.

3. output is for decoder

It takes Q from output.

K, V from encoder.

we have N decoders.

New Terms

Perplexity is an evaluation matrix for machine translation. It quantifies how 'surprised' the model is to see some words together. Lower is better.
OOV = out of vocabulary
RNN is keep forgetting the past. This phenomena is called "vanishing gradient"
Label Smoothing Purpose
- prevent overfitting
- introduce noise
- let model be little unsure about prediction.
It improves accuracy and BLEU score of translation.
RLHF : Reinforcement learning from human feedback

References

https://cme295.stanford.edu/

Syllabus : https://cme295.stanford.edu/syllabus/

CheatSheet

https://cme295.stanford.edu/cheatsheet/

https://github.com/afshinea/stanford-cme-295-transformers-large-language-models/tree/main/en

https://www.youtube.com/watch?v=Ub3GoFaUcds

https://www.youtube.com/watch?v=8fX3rOjTloc

https://www.youtube.com/playlist?list=PLoROMvodv4rOCXd21gf0CF4xr35yINeOy

Text Book Super Study Guides

------------------------------------------------------

Sequence to Sequence model has

1. Encoder, Decoder

2. Attention Mechanism

3. Transformer architecture

4. Fine tuning of Transformer Architecture

Usecases

1. Language, sentence has words in sequecne

2. Time series data

3. Biology: Genes, DNA

------------------------------------------------------

Some more relevant stuff:

Each layer has

1. Attention and

2. Fast Forward

Between two layers we have high dimension 'hidden state vector' in activation space.

LLM encodes concepts as distributed patterns accross layers = Superposition.

Antropic has series of papers on superposition and monosemanticity

https://www.youtube.com/watch?v=F2jd5WuT-zg

https://www.neuronpedia.org

https://huggingface.co/collections/dlouapre/sparse-auto-encoders-saes-for-mechanistic-interpretability

https://huggingface.co/spaces/dlouapre/eiffel-tower-llama

------------------------------------------------------------

https://www.linkedin.com/pulse/decoding-attention-all-you-need-how-transformers-ai-yuri-sylse/

https://poloclub.github.io/transformer-explainer/

BAPS IT Convention

noreply@blogger.com (Manish Panchmatia) — Sun, 25 Jan 2026 15:37:00 +0000

On January 18, 2026 BAPS Banglore temple hosted IT convention event from morning to evening. More than 375 participants.

Here are few take away points

1. "Changing Trends of AI in technologies" by Prof. Rahul De

Prof. Rahul De' is founder and CEO of https://www.memoricai.in/ He provided nice academic insight, history of AI, present state and future. AI is about inference and inference is predications, classification and generative output

Human brain has 80 to 86 billion neurons (cells).

Evolution of AI

1. ANI : Artificial Narrow Intelligence

2. GNI : General Narrow Intelligence

3. ANI : Super Narrow Intelligence

In 1966 a professor Joseph Weizenbaum at MIT developed first chatbot by name ELIZA. It acts like a Rogerian psychotherapist. People like it so much. Later on, we had to convince, that it is not a real person. It is just a computer program that simulates human conversation, through pattern matching and keyword substitution.

Late in 1980 John Searle did "Chinese Room Experiment". Here, a non-Chinese speaker in a room, just manipulate Chinese symbols manually and produce fluent responses without understanding the language. It proves that just through syntax (rule-following) alone, computer cannot achieve semantics (genuine understanding or consciousness).

Probably that is why today, GenAI has caveats like hallucinations, jail breaking, bias, privacy violations and unfair responses. In the context of bias, he mentioned about recent movie "Human in the loop" Available on Netflix. "An indigenous woman works as an AI data-labeler after returning to her village with her children, but soon questions the human bias in machine learning."

He shared some statistics

- 2.5 billion prompts are handled by ChatGPT alone in a year.
- 2.4 million models are present at hugging face
- 50 billion USD are spent for AI in year 2025.
- 95% firms fail in GenAI adoption.
- We achieved 15% improvement by GenAI

The above numbers raised serious questions that does spending behind GenAI is worth?

He mentioned few books and categorised all AI adopters in four groups. Boomers (books by Ray Kurzweil), Doomers , Skeptics and Critics "Empire of AI: Dreams and Nightmares in Sam Altman's OpenAI"

2. panel discussion on "Ways to overcome Challenges in IT"

One of the discussion point was about reducing 95% failure rate in 2026

We need:

- Automated task workflow
- Cross functional aggregation across various departments
- Collaboration between AI and human
- Orchestration for AI in day-today work

How can you fail? Your effort (to adapt AI, to retain job etc) can fail. In fact the definition for failure came after industry revolution. During the last century, "Productivity" was more in focus due to industry revolution.

Other points:

Former OpenAI co-founder Ilya Sutskever has indicated that simply scaling up to 1 trillion parameters model will not improve AI capability further.

May be, personalised AI will be next thing

We are humans so

- we are always optimistic, we have hope.
- We have ability to adapt.
- We are creator of AI so we are smarter than AI

We shall remove the fear that we need to learn everything. Yes, we shall learn something new everyday and take its now on NotebookLM. Internet is flooded with many buzzword about AI. We need to separate signal from noise.

Now learning is not same as degree earning.

Now, we need to be aware about all domain. That knowledge shall not be gain by asking ChatGPT.

Few points were discussed about parenting: We shall have 30 min of productive arguments with kids. We will learn AI from the end-user. We shall enable parental control for Internet, OTT. While using AI, be skeptic. You are interacting with product. So product has market, company / organisation behind it, that want to earn profit. AI product is not your friend. More we use LLM, that much brain is unused and lost.

We need to learn basic values like

- Humans are not means
- Respect life in people

About firing due to AI.

* If software engineers consider themselves as coder then AI will replace them. They shall consider themselves as problem solver.
* On lighter notes: Pujya Aksharatit Swami mentioned that we SADHUs are easier to get replace. Chat with AI is available round the clock.
* On lighter notes: Pujya Aksharatit Swami mentioned

येषाम् न विद्या न तपः न दानम् न ज्ञानम् न शीलम् न गुणः न धर्मः ।।

ते मृत्यु-लोके भुवि भार-भूता मनुष्यरूपेण मृगाः चरन्ति ।

It means: Those who possess no knowledge (Vidya), no penance (Tapa), no charity (Dana), no wisdom (Jnana), no good character (Sheela), no virtues (Guna), and no righteousness (Dharma), are a burden to the earth. Although they look like humans, they roam the earth like animals in human form.

Now this sloka is applicable for knowledge of AI also :-)

During the panel discussion, the floor is open for everyone to ask question via WhatsApp group, that was flooded with many questions.

3. Networking

The audience was divided into many groups. The participants had a round of introductions within group. There was engaging quiz, where all groups participated and the group leader responded to questions on behalf of group.

We had delicious vegetarian, SAATTVIK food. Now some key take away points from post lunch sessions.

4. Work-Life Integration & Wellbeing

“In God we trust. All others must bring data.” - W. Edwards Deming

Here are some shocking data points

83% of Indian IT professional are burnout
73% of European IT professional are burnout
72% are working beyond limit

The data source is ISACA (Information Systems Audit and Control Association)

5 pillars of work life integration

1. Know your why?

What is purpose? It brings impact, mastery and autonomy.

Our health and family should tune to work.

2. Design your system

Define boundaries so you can protect capacity

Bring rhythms by frequent breaks.

3. Recovery and build resilience practices

3.1 Mindful ness and reflection. Moment to moment non-reactive, non-judgmental awareness is mindful ness.

3.2 physical movement

3.3 social connections

4. Align your environment

5. Seek help early

Something about sleep

- Sleep is non-negotiable.

- Sleep hygiene and nutrition

- Stop all screens 60 to 90 min before going to bed. It is digital sunset.

- use eye mask while sleeping.

Next topic was NSANE

Nutrition

Screen Time

Automatic health. He mentioned about book : "Atomic Habit"

Notice Signal

Engage with real people

Remember 3 truths

1. Mind = body. Means if body is unhealthy, means mind is unhealthy. Body can be healthy by making healthy mind

2. Work family balance is important

3. It is still not too late.

Ask your wife, what she expect about husband?

- Rich husband?

- Healthy husband?

- Rich but unhealthy husband?

- burn out person as husband?

3. Personal/Spiritual Fire Chat with Pujya Santo

Along with other relevant questions and guidance by Pujya SAINTs, again IT layoff was discussed. The apparent reason is AI for layoff. The real reason can be poor performance of employee. Extra hiring happens during COVID phase, so now layoff is inevitable. जातस्य हि ध्रुवो मृत्युः Same way, if you have job, you may get fire. If not today then in future, at age of 62 years. Even after 10 years, the present software application has no values. This is also as per SANKHYA philosophy. It inspires us to make better documentation of product.

Summary

1. Be happy

2. Worship God.

બી.એ.પી.એસ. પ્રકાશ એપ

પ્રકાશ વિશેષ :

બેંગલુરુમાં આઇ.ટી. પ્રોફેશનલ્સ માટે યોજાયો વિશેષ સમારોહ

વધુ માહિતી માટે નીચેની લિંક પર ક્લિક કરો.

https://bapsprakash.in/deeplink?data=QsfHnR6PaUp%2FlihVajHZKg%3D%3D%3AWm7u3d6zy%2FylpRGzMz6xFENQBWhBhVioEwCNJCh3MI8%3D

Disclaimer: The author had put best effort to capture all the points, as per his understanding. It may or may not reflect exact intention of the speaker. So any corrections are welcome. This article is not verbatim

MCP and Security OAuth2.0

noreply@blogger.com (Manish Panchmatia) — Mon, 15 Dec 2025 06:32:00 +0000

This video is about MCP, ACP and A2A but later 11+ more protocols were found

MCP : Design goal is not Agent to Agent communication. But now it is happening.

- MCP is also wroking on Agent registry.

- It is different from A2A (1) No async message. (2) No renegotation.

- It is most adopted protocol.

- MCP has conquer world like React.js

These protocols are about : Discover, communicate, authenticate. over Internet

1. Inter-Agent protocol

1.1. Robot-Agent: CrowdES, SPPs (Saptial Population Protocol)

1.2. Human Computer: LOKA, PXP

1.3. System-Agent: Agent Protocol, LMOS (Large Model Operating System)

2. Context Oriented

2.1 MCP

Few Protocols

Agents.JSON: File has API documentation for Agent. It is in OpenAPI format
ANP: Agent Network Protocl. DID Distributed Identity (Blockchain-based)
AITP: Blockchain. interaction cost.
ACP (Agent Connect Protocol) by Cisco. Like A2A except it describe how to host and launch agent
ACP (Agent Communication Protocol) by IBM. like MCP. It has registry = distributed Database of all agents. It is fork of MCP
Agora: Natural language protocol. protocol upgrade itself.

All protocols lack

1. Regsitry

2. Authorizatoin

3. Reputation

https://www.youtube.com/watch?v=kqB_xML1SfA

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

OAuth is bunch of specs

OAuth2.0 = RFC6749 (2012) + RFC6750

OAuth2.1 = Authorization code + PKCE, Client credentials (may not useful), token in HTTP header, token in POST form body. Refer MCP Github issue 830

OpenID Connect is to identify user. It provides ID token

RFC 9728 : single URL for MCP server. It points to file that define meta data of server. it has auth server meta data as per RFC 8414.

RFC 7591 : Dynamic client registration to get client ID and Client secret.

aaronpk.com/mcp

oauth.wtf

oauth.net

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

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

Keycloak and SPIRE

CNCF IAM Whitepaper. Yet to be published

5 principals

1. mTLS

2. OAuth2 token exchange RFC 8693

3. OIDC client authentication with SPIFEE SVID

4. OAuth2 token validation

5. PDP based Authorization decision.

PDP, PAP, PIP, PEP

PAP (Policy Administration Point): The user interface/management layer where policies (rules) are created, stored, and managed centrally.
PDP (Policy Decision Point): The "brain" that evaluates a user's request against policies from the PAP, using attributes from PIP, to return an "Allow" or "Deny" decision.
PIP (Policy Information Point): Fetches necessary attributes (like user roles, data from databases/LDAP) needed by the PDP to make a decision.
PEP (Policy Enforcement Point): Sits in front of the protected resource, intercepts requests, sends them to the PDP for a decision, and enforces that decision.

1. A user requests a resource (e.g., "view my profile").

2. The PEP intercepts the request and the OAuth access token.

3. The PEP sends the request details (user context from token, resource, action) to the PDP.

4. The PDP queries the PIP (e.g., a database) for attributes like user's department.

5. The PDP evaluates policies (managed by PAP) and returns "Permit/Deny" to the PEP.

6. The PEP allows or blocks the user's request based on the decision.

https://www.youtube.com/watch?v=S6qF0N5D1tM

Sanskrit speech at closing ceremony of spoken Sanskrit workshop

noreply@blogger.com (Manish Panchmatia) — Sat, 06 Sep 2025 19:07:00 +0000

10 days Spoken Sanskrit workshops (Sanskrit Sambhaasan Shibir) held from July14 2025 to July 23 2025 at BEML Balaji Temple and at Skylark Arcadia Bangalore, by Samskrita Bharati Marathahalli bhaga, Bangalore, India.

Spoken Sanskrit workshops - closing ceremony on 26th July 2025.

Sanskrit speech by chief guest Shri Manish Panchmatia

Greetings!

A warm welcome to everyone present—teachers, volunteers from Samskrita Bharati, students, and all those passionate about Sanskrit. After bowing down to each of you, I am honored to begin my speech.

First, let me ask: “How was the Spoken Sanskrit Workshop?” Was it “Good”? “Very good”? I’m certain it was a positive experience. Whenever Samskrita Bharati organizes a workshop, the teachers impart their knowledge with dedication, don’t they? Over the past ten days, each one of you demonstrated incredible determination to learn Sanskrit. No matter what, you attended all the classes and gave your best effort. Kudos to you all for your commitment and enthusiasm. You sang songs in Sanskrit, offered prayers, performed dramas, and narrated stories—all in Sanskrit. I am truly impressed by your efforts and progress.

Do you know the outcome of all this effort? Today, at the closing ceremony of our Spoken Sanskrit Workshop, English is not needed at all. At the beginning, everyone thought that English would be a common language among us. We come from various backgrounds—Gujarati, Kannada, Telugu, Tamil—but we are all Indians. And what is the mother tongue of Indians? Sanskrit. Indeed, Sanskrit is not only the mother tongue of Indians but also the language of the gods. Now, after this workshop, you have the ability to converse in Sanskrit, tell stories in Sanskrit, and truly appreciate the beauty of the language. So you all are also God only. Right?

As you may know, NASA called Sanskrit the most suitable language for computers. I won’t repeat those facts, but I do want to share a story about Sanskrit’s vast vocabulary. Just now, we sang about great poets—Vyasa, Bhasa, Kalidasa, Banabhatta—yet there is another renowned poet: Dandi, who composed “Dasakumaracharitam,” the story of ten princes. One prince, wounded in the lower lip, could not pronounce certain sounds: "pa," "fa," "ba," "bha," and "ma." Dandi skillfully chose synonymous words without those sounds for all of that prince’s dialogue. This was possible only because Sanskrit’s vocabulary is so rich.

Sanskrit grammar is exceptionally precise; in fact, the very meaning of the word “Sanskrit” is “well-formed” or “perfect.” Sanskrit has maintained its grammar rules since Vedic times—pronunciation, grammar, language rules—all unchanged. Even though new inventions like mobile phones have appeared, in Sanskrit, we create new words effortlessly. “Mobile phones” in Sanskrit is “Jangam Door-Vani”—a moving telephone. Artificial intelligence becomes “Krutrim Buddhi.” Thanks to Sanskrit’s structure, new words can always be formed. This habit of following rules brings discipline to our lives.

We all are Indians. Sanskrit is deeply imprinted in our consciousness. Just as our childhood photos make us happy, speaking Sanskrit awakens ancient impressions within us—it fills the soul with joy. Throughout these ten days, you learned Sanskrit joyfully, supported by equally joyful teachers.

How do we gain these benefits? By giving your 100% effort to learning Sanskrit. What does 100% effort mean? Here is another story from the Mahabharata. Karna is renowned as the greatest giver. Once, Arjuna asked Krishna, "Why is Karna more famous for charity than my brother Yudhishthira?" Krishna replied, “Let’s see for ourselves.” Disguised as BRAHMINs, Arjuna and Krishna visited Yudhishthira and requested sandalwood for a yagna. Yudhishthir responded, "OK". Then, what did Yudhishthir do? He searched. Remember the story of the crow. The crow was searching for water. Here Yudhishthir is searching for sandalwood. He looked here . He looked there. Right side. Left side. Front side. Back side. He looked for Sandalwood everywhere. The sandalwood is nowhere. Then he went outside. Looked at the garden. He searched everywhere. The sandalwood is nowhere. He returned back and told BRAHMIN: "Sorry sir. The sandalwood is nowhere. I will surely make a little more effort to arrange for sandalwood. Please come tomorrow. I will give." BHRAMIN said, "OK". Then, they visited Karna with the same request. Karna eagerly searched, and when he could not find sandalwood, he noticed his door was made of sandalwood. Without hesitation, he dismantled it and gave it to them. True charity is giving with 100% effort. It is the same with learning Sanskrit—when you give your wholehearted effort, you will gain both knowledge and discipline.

Further, speaking Sanskrit even helps with breathing exercises—“ma” and “ha” are frequently used, which naturally leads to “pranayama.”

This spoken Sanskrit workshop is just the beginning. Explore further—enroll in correspondence Sanskrit learning courses, Gita Sopanam etc. There are many Sanskrit books here, for sale. Buy them, read them and then, become Sanskrit teachers yourselves! Spread and promote Sanskrit to others just as your teachers did for you. You all know Swami Vivekananda. Right? "Yes". On 4th July, it was his death anniversary. On the last day of life, he taught Sanskrit to the students. You all know that? It is in his biography. Let us honor this legacy by teaching and learning Sanskrit.

Having spoken much about Sanskrit, let me turn briefly to our IT professionals. When we hear the word “language,” we often think of C, C++, Java, Python, NodeJS, ReactJS, and so on. Recently, I attended a "PyKrit" (Python + Sanskrit) workshop at Aksharam, Samskrita Bharati’s center. This workshop was not for IT people. It was for Sanskrit scholars. I saw Sanskrit scholars name Python functions in Sanskrit, such as “YANA SANDHI” (a grammar topic). We truly can create software for Sanskrit grammar, using modern programming languages like Python, and even coding in Sanskrit.

Lastly, my wish: While we use AI/GenAI tools like ChatGPT, we mostly interact in English. Wouldn’t it be wonderful to have a large language model (LLM) in Sanskrit? Imagine asking questions in Sanskrit and receiving answers, back in Sanskrit, from AI tools, such as ChatGPT. That is my hope for the future.

Best wishes to everyone, and thank you all.

LLMOps

noreply@blogger.com (Manish Panchmatia) — Mon, 11 Aug 2025 03:52:00 +0000

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

===========

K8s GW API

noreply@blogger.com (Manish Panchmatia) — Fri, 01 Aug 2025 14:17:00 +0000

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. It can be (1) per namespace level destination services (2) few service(s) within a namespace as destination (3) destination services from multiple namespaces.

3.1 Traffic Policy

* It has transformation field to manipulate header and payload for request and response both. It is based on inja language

https://github.com/pantor/inja

https://kgateway.dev/docs/main/traffic-management/transformations/templating-language/

* It has ai field for prompt enrichment.

ai:

promptEnrichment:

prepend:

- role: SYSTEM

content: "Parse the unstructured text into CSV format."

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, HTTP method and query parameters.

Paths (e.g., /headers, /status/*)
Headers (e.g., User-Agent: Mobile)
Query Parameters (e.g., ?version=beta)
Methods (e.g., GET, POST)

You can also define multiple matching criteria and even combine them with an AND or OR operator.

- 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.

1. RequestRedirect : E.g. Redirect HTTP traffic to HTTPS

2. URLRewrite

3. <Request|Response>HeaderModifier

4. RequestMirror

5. CORS

6. ExtensionRef for custom filter. E.g. DirectResponse

filters:

- type: ExtensionRef

extensionRef:

name: direct-response

group: gateway.kgateway.dev

kind: DirectResponse

- 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.

- Traffic splitting is done by specifying multiple backendRef, with weight

- timeout, retry, sessionPersistence Session persistence, (= sticky sessions or strong session affinity), ensures that a client's requests are consistently routed to the same backend instance for the duration of a session. based on cookie or a header

- Route and Gateway can be in different namespace. If Gateway is defined with

allowedRoutes:

namespaces:

from: Same

then Route and Gateway shall be in same namespace. We can have group of namespaces with label selector and specify those namespace using label at Gatway resource.

allowedRoutes:

namespaces:

from: Selector

selector:

matchLabels:

self-serve-ingress: "true"

* 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.

8. Inference Extension

K8s offers following mechanisms to optimize GPU usage,

- time slicing,

- Multi-Instance GPU (MIG) partitioning,

- virtual GPUs, and

- NVIDIA MPS

for concurrent processing.

Effective GPU utilization means

- hardware allocation;

- how inference requests are routed across model-serving instances.

- how inference requests are load-balanced across model-serving instances.

Simple load-balancing strategies often fall short in handling AI workloads effectively, leading to suboptimal GPU usage and increased latency.

Inference requests V/s traditional web traffic

- It often takes much longer to process, sometimes several seconds (or even minutes!) rather than milliseconds,

- It has significantly larger payloads (ie, with RAG, multi-turn chats, etc). So a single request can consume an entire GPU, So making scheduling decisions far more impactful than those for standard API workloads. So, these requests need to queue up while others are being processed.

AI Models are stateful

- They maintain in-memory caches, such as KV storage for prompt tokens,

- They load fine tuned adapters like LoRA to customize response for specific user/organisation.

So routing decisions are based on

- current state (in-memory caches, adapters)

- available memory, and

- request queue depth.

So Inference aware routing through

8.1 Inference Model

- maps user facing model name to backend model

- traffic splitting between fine-tuned adapaters

- Priority based on real time interaction OR best-effort batch job

8.2 Inference Pool

- It is for platform operators managing model-serving infrastructure.

- a group of model-serving instances

- specialized backend service for AI workloads.

- It manages

-- inference-aware endpoint selection,

-- intelligent routing decisions based on real-time metrics such as

--- request queue depth and

--- GPU memory availability.

* Inference Pool is mapped with HTTP Route->backendRefs

* Inference Model has poolRef to link with Inference Pool

* Inference Pool has extensionRef (EPP = Endpoint picker) . If name for Inference Pool is xyz then extensionRef is "xyz-endpoint-picker" It is similar to K8s service, as it also has selector and target port

9. DirectResponse

10. Backend

For external endpoint

Ref: https://tetrate.io/blog/kubernetes-envoy-gateway-extensions

Low Cost Cloud

noreply@blogger.com (Manish Panchmatia) — Sat, 26 Jul 2025 09:36:00 +0000

NVIDIA GTC25: Telecom Special Address

noreply@blogger.com (Manish Panchmatia) — Tue, 01 Jul 2025 05:23:00 +0000

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

AI Bootcamp for students

noreply@blogger.com (Manish Panchmatia) — Fri, 20 Jun 2025 03:03:00 +0000

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

Regional LLM, SLM, TinyLM Language Learning

noreply@blogger.com (Manish Panchmatia) — Wed, 28 May 2025 05:58:00 +0000

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

AIKosha

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.

Kannada Models

nomic-embed-text-v2-moe

snowflake-arctic-embed2

OpenAIs text-embedding-3-large

Vovage

Cohere

intfloat/multilingual-e5-large-instruct

paraphrase-multilingual

BGE-M3 is based on the XLM-RoBERTa

NVIDIA

https://build.nvidia.com/openai/whisper-large-v3

https://blogs.nvidia.com/blog/india-ai-mission-infrastructure-models/

Sarvam.ai,

Gnani.ai,

BharatGen,

and CoRover.ai

are building frontier multilingual models using NVIDIA Nemotron and NeMo

Sarvam.ai is open-sourcing its Sarvam-3 series across 22 Indic languages (3B to 100B parameters).

BharatGen launched a 17B-parameter mixture-of-experts model for public services, agriculture, and security.

→ CoRover.ai handles 10,000 concurrent users for Indian Railways with 5,000+ daily ticket bookings

→ Gnani.ai processes 10M+ calls daily across telecom, banking, and hospitality — 15x reduction in inference costs

→ NPCI is exploring AI for India's UPI payments (something I use every single day at Rameshwaram Cafe and everywhere else in Bengaluru!)

→ Commotion (backed by Tata Communications) built an AI OS for enterprise workflow automation

TinyML

one possible hardware https://store-usa.arduino.cc/products/arduino-tiny-machine-learning-kit

Topics: https://github.com/tinyMLx/courseware/tree/master/edX

Courses: https://tinyml.seas.harvard.edu/courses/

Workshop videos and slides: https://tinyml.seas.harvard.edu/SciTinyML-24/

Article: https://hdsr.mitpress.mit.edu/pub/0gbwdele/release/5

embedUR https://www.embedur.ai/

Old PC: https://www.msn.com/en-in/money/news/someone-used-a-1997-processor-and-proved-you-only-need-128-mb-ram-to-run-a-modern-ai-model/ar-AA1O513S

LLM on mobile

Google launches app to let anyone run AI models on their phone without internet

How to Install and Run AI Models Locally on Your iPhone

Google for Education

Google introduces Gemini tool for students and educators: How this AI tool will transform classroom teaching

URL for AI/GenAI

noreply@blogger.com (Manish Panchmatia) — Tue, 20 May 2025 13:50:00 +0000

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

CAMARA - NaaS

noreply@blogger.com (Manish Panchmatia) — Fri, 04 Apr 2025 06:14:00 +0000

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

अष्टाध्यायी - 2

noreply@blogger.com (Manish Panchmatia) — Sat, 15 Mar 2025 12:52:00 +0000

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.

Dr. Saroja Bhate explained (1) what is role of aakanksha in deciding anuvruti and

fundamentals of anuvruti

Compression in Sanskrit grammar. Sage PAANINI compressed LAGHU SIDDHANTA KAUMIDI with help of VRUTI to 1/3 size and wrote ASHTADHYAYI.

yathodasa is like Interpreter and karyakala is like compiler

abhidha, laxana and vyanjana are 3 powers of words. Not sure, when today's LLM will understand them.

MAHAA-BHAASHYA learning is better than learning ASHTADHYAYI.

Dr Srinivas Varkhedi has strong opinion that, Sanskrit scholar already knows computer science concepts and programming with knowledge of Sanskrit grammar. In future, we will not have trust our car. As it might be hacked by AI tools. So we will travel by bullock cart, because bullocks listen to us, car may not. AI tools cannot hack bullocks.

Today's LLMs are fed against SANAATANAA DHARMA. It is difficult to erase. They are biased against SANAATANAA DHARMA. We know that, it is difficult to re-train our kids who studied in school/college. Then retraining LLMs is even more difficult. The current generation will use AI and they may be against SANAATANAA DHARMA in future. So we need 1000 Sanskrit students who can say what is right and what is wrong about SANAATANAA DHARMA with authenticity.

Reference:

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

PythonKrit

noreply@blogger.com (Manish Panchmatia) — Sat, 15 Mar 2025 12:52:00 +0000

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

Text

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

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

Python

noreply@blogger.com (Manish Panchmatia) — Tue, 04 Mar 2025 05:48:00 +0000

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