अष्टाध्यायी - 2
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
PythonKrit
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
Python
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
AI for Observability
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
AI Language Model
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:
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