Skip to content

Commit

Permalink
update langgraph and resume app
Browse files Browse the repository at this point in the history
  • Loading branch information
jbcodeforce committed Aug 31, 2024
1 parent 56e9d11 commit d638c83
Show file tree
Hide file tree
Showing 13 changed files with 221 additions and 9 deletions.
3 changes: 2 additions & 1 deletion .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -22,4 +22,5 @@ pytorch/computer-vision/data/
**/.env
**/.taipy/
techno/crew-ai/db/
**/agent_domain_store/
**/agent_domain_store/
**/agent_vstore
14 changes: 7 additions & 7 deletions docs/coding/langgraph.md
Original file line number Diff line number Diff line change
@@ -1,20 +1,20 @@
# LangGraph

!!!- info "Updates"
Created 04/2024 - Update 07/19/2024
Created 04/2024 - Update 08/27/2024

[LangGraph](https://python.langchain.com/docs/langgraph) is a library for building stateful, **multi-actor** applications, and being able to add cycles to LLM app. It is not a DAG.

Single and multi-agent flows are described and represented as graphs.

## Value propositions

* build stateful, multi-actor applications with LLMs
* coordinate multiple chains or actors across multiple steps of computation in a cyclic manner
* build plan of the actions to take
* take the actions
* observe the effects
* support persistence to save state after each step in the graph. This allows human in the loop pattern
* Build stateful, multi-actor applications with LLMs
* Coordinate multiple chains or actors across multiple steps of computation in a cyclic manner
* Build plan of the actions to take
* Take the actions
* Observe the effects
* Support persistence to save state after each step in the graph. This allows human in the loop pattern
* Support Streaming agent tokens and node transitions

## [Concepts](https://langchain-ai.github.io/langgraph/concepts/)
Expand Down
23 changes: 23 additions & 0 deletions e2e-demos/resume_tuning/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
# Resume Tuning App

## Pre-requisites

* Install Python 3.11
* Create Virtual Environment
* Activate
* Install needed libraries

## Prepare input documents

1. Need to copy paste the job application in a md file, be sure to use the md headers as

"#" = "Header 1"
"##"= "Header 2"
"###"= "Header 3"
"####"= "Header 4"

2. Get resume in pdf or md format. The resume may have a lot of skills and projects listed, the system will take the most appropriate.

## Usage

python main.py -a application_file.md -r resume.pdf -c firstname
Binary file not shown.
Binary file not shown.
Binary file not shown.
Empty file.
Binary file removed e2e-demos/resume_tuning/agent_vstore/chroma.sqlite3
Binary file not shown.
76 changes: 76 additions & 0 deletions e2e-demos/resume_tuning/centific.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,76 @@
# About the job

## About Centific–

Centific expertly engineers platforms and curates multimodal, multilingual data to empower the ‘Magnificent Seven’ and enterprise clients with safe, scalable Artificial intelligence (AI) deployment. Our team includes over 150 PhDs and data scientists, along with more than 4,000 AI practitioners and engineers. We leverage an integrated ecosystem comprised of industry-leading partnerships, and 1.8 million vertical domain experts across 230 locales, to create high-quality pre-trained datasets, fine-tuned industry-specific Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG) pipelines supported by vector databases. Our innovations can reduce Generative Artificial Intelligence (Gen AI) costs by up to 80% and bring Gen AI solutions to market 50% faster.


Our mission is to bridge the gap between AI creators and industry leaders by bringing best practices in Generative AI to unicorn innovators and enterprise customers. We aim to help these organizations unlock significant business value by leveraging Generative AI at scale, ensuring they stay at the forefront of technological advancement and maintain a competitive edge in their respective markets.

## Job Title: Field CTO

### Position Overview:

Centific is seeking a seasoned Field CTO to join our team to lead account specific strategic planning and drive end-end solution design. This senior role is pivotal in shaping and driving our Generative AI initiatives. The ideal candidate will act as the voice of our company, serving as a thought leader and ambassador in the generative AI space. This role requires a blend of technical expertise, strategic vision, and exceptional communication skills to influence both internal and external stakeholders.


### Key Responsibilities:

Thought Leadership and Advocacy
·Act as the primary spokesperson for Generative AI solutions, representing the company at customer meetings, industry events, conferences, and in public forums.
·Develop and communicate a clear vision and strategy for the company's Gen AI initiatives.
·Publish whitepapers, articles, and thought leadership pieces to enhance the company’s reputation in the AI community.

·Lead day-to-day interactions with data science, product, and engineering teams at the target account/s to problem-solve and apply creative ideas to meet client requirements.
·Overall accountability for CSAT and Growth within the account from a technical/solutions perspective. The role has tremendous potential to make a direct impact across the board and we are looking for candidates who excel in navigating complex situations to achieve a



### Strategic Planning and Execution

·Define and drive the roadmap for Gen AI solutions in alignment with business goals.
·Collaborate with cross-functional teams including product management, engineering, marketing, and sales to ensure successful delivery and adoption of Gen AI solutions.
·Identify market trends and opportunities, and guide product innovation to maintain a competitive edge. In effect, this person serves as the Field CTO for the specified account/s and bridges the gap between business strategy and technology.


### Stakeholder Engagement

·Build and maintain strong relationships with key stakeholders, including customers, partners, and industry influencers.
·Conduct regular meetings and presentations to communicate progress, gather feedback, and adjust strategies as needed.
·Serve as the liaison between technical teams and business units to ensure alignment on objectives and expectations.


### Customer and Market Insights

·Gather and analyze customer feedback and market data to inform product development and marketing strategies.
·Understand customer pain points and needs, translating them into actionable product features and improvements.
·Conduct competitive analysis to benchmark our Gen AI solutions against industry standards and competitors.


### Innovation and Continuous Improvement

·Stay abreast of the latest advancements in generative AI and related technologies.
·Foster a culture of innovation, encouraging the team to explore new ideas and approaches.
·Evaluate and implement tools, processes, and methodologies to enhance the efficiency and effectiveness of the Gen AI team.


### Qualifications

Education: Bachelor’s degree in Computer Science, Engineering, Business, or a related field. A Master’s degree or Ph.D. in a relevant discipline is preferred.


### Experience

·10+ years of experience in AI, machine learning, or a related field, with a focus on generative AI.
·Proven track record of successfully leading strategic initiatives and product development in a senior role.
·Experience in a thought leadership capacity, including public speaking and publishing would be plus
·Proven ability to stand & deliver – this is especially critical given the strategic account focus


### Skills and Competencies

·Deep understanding of generative AI technologies, applications, and market dynamics.
·Exceptional communication and presentation skills, with the ability to articulate complex technical concepts to diverse audiences.
·Strong strategic thinking and problem-solving abilities.
·Demonstrated ability to build and maintain relationships with stakeholders at all levels.
·High degree of adaptability, creativity, and a passion for continuous learning.
71 changes: 71 additions & 0 deletions e2e-demos/resume_tuning/jbr.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,71 @@
Former IBM Distinguished Engineer
Former AWS Principal Solution Architect


## Background summary

For the last ten years as AWS principal solution architect and an IBM distinguished engineer, he helps customers adopt hybrid cloud, designing complex solutions around microservices, streaming and data management for AI/ML. Currently helping customers adopt Generative AI agents combined with traditional symbolic AI to get real actionable value from AI.
With years of experience in business process automation and decision automation with rule engine systems. Book authors, conferences speaker, still hands-on to develop MVPs, and proof of technology.

Contributed to multiple patents and publications on business rule models, IBM BPM and decision management integrations.

## Skills

* Amazon Cloud Architecture Professional Certified
* Event-driven architecture and streaming technologies with Apache Kafka, Flink, Kafka Streams, IBM MQ, Active MQ, AWS SQS
* Cloud and hybrid technology such as Serverless, Lambda, API Gateway, DynamoDB Kubernetes, OpenShift, Java Microprofile and Quarkus
* AI: Classification, clustering, Deep Learning with PyTorch, Generative AI with prompt engineering, RAG, LangChain, Langgraph, LlamaIndex and different LLMs: OpenAI, WatsonX.ai, Claude, LLama, Mistral, Cohere
* Methodology: Agile development, Lean Startup, Design Thinking, Event Storming and Domain Driven Design
* Programming language: Java, Python, shell, nodejs
* DevOps, gitops, cloud formation, AWS CDK


## Professional experience

### 04/204 \- Present: Athena Decision Systems:
Principal consultant for Neuro Symbolic AI solution implementations. I lead an open source project to develop agentic AI application to address different AI use cases, like RAG, similarity search, entity extraction and rule based system.

### 09/2022- 03/2024: AWS Principal Solution architect ISV market

I support Data & AI ISVs, and led solution architecture for Databricks, Fivetran and Tecton.ai, from designing and implementing scalable, highly available SaaS platforms to meet the needs of their 100k clients.
Reduce cost by 15% and support managing petabyte of data.

Develop Generative AI solutions and around 10 proof of concepts for enterprise customers to help on their
journey to AI. Member of the serverless field community and event-driven expert team.

## 10/2016-09/2022: IBM Distinguished Engineer
Event-driven architecture CTO, specialized in hybrid cloud and reactive microservices based solution. Engaged with major IBM strategic accounts. Yearly business impact around 150 M$.

## 02/09 – 09/2016: IBM Lab Service \- Solution Architect for BPM solution

Worldwide position, leading complex solution delivery around IBM business process management and business rules management projects. Around 50+ customer engagements. 20 to 30 M$ impact per year.

## 12/99-1/09 ILOG Inc – Professional Service – Technical Director
ISV vendor for rule based system and operational research software. I was Principal consultant to director position to lead the architect groups worldwide to develop best practices and highly qualified architects to support complex project delivery. Directly involved in the most complex NA consulting engagements.Transform a 10 M$ to 80M$ consulting business in 2 years.

## Professional certifications
* 2024: IBM WatsonX.ai tech seller
* 2023: AWS Solution Architect Professional - Serverless Technical Field Community - Generative AI and Databricks
advocate.
* 2016: IBM Distinguished Engineer - CTO
* PMI: Project Management Professional

## Education
Master Computer Science, Nice University, France
Bachelor of Science in Computer Science, Nice University, France


## Publications and presentations

* EDA virtual book: https://jbcodeforce.github.io/eda-studies/ with all the related repositories to support assets and reference implementations.
* Machine learning and agentic book: https://jbcodeforce.github.io/ML-studies/
* Patent issued: #10885440 “Contextual evaluation of process model and extraction” – 4 others filed.
* Co Author: “Sustainable IT Architecture” Wisley
* Co Author: “Agile Business Rule Development with JRules” Springer.
* Agile Business Rule Development. First Open Source methodology to develop business application with BRMS
* Speaker every year at IBM conferences like Impact, Think and Interconnect from 2010 to 2021
* Speaker at external conference like Business Rule forum, ILOG Dialog, Gartner BPM symposium
* ILOG consultant of the year 2003, 1M$ quarter quota achievement 1Q03
* ILOG 3 stars (2004) and 2 stars employee (2006)
* IBM Outstanding Corporate Achievement award – 2011, 2013, 2016, 2018, 2019
* IBM Exceptional Restricted Share Distribution Award – 2014, 2016, 2018, 2019, 202
34 changes: 34 additions & 0 deletions e2e-demos/resume_tuning/new_resume.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@

With over a decade of experience as an AWS Principal Solution Architect and IBM Distinguished Engineer, I excel in aiding customers in adopting hybrid cloud solutions, focusing on microservices, streaming, and data management for AI/ML applications. Currently, I am assisting clients in integrating Generative AI agents with traditional symbolic AI to derive actionable insights. My expertise lies in leading Neuro Symbolic AI solution implementations and spearheading open-source projects for developing agentic AI applications.

## Skills
- **Cloud Technologies:** Amazon Cloud Architecture Professional Certified, expertise in AWS services like Lambda, API Gateway, DynamoDB, and Kubernetes.
- **AI Expertise:** Proficient in Deep Learning with PyTorch, Generative AI technologies including RAG, LangChain, and OpenAI.
- **Methodologies:** Skilled in Agile development, Lean Startup, Design Thinking, and Domain Driven Design.
- **Programming Languages:** Experienced in Java, Python, shell scripting, and nodejs.
- **DevOps:** Well-versed in DevOps practices, including gitops, cloud formation, and AWS CDK.

## Professional Experience
- **Athena Decision Systems (04/2014 - Present):** Leading Neuro Symbolic AI solution implementations and spearheading an open-source project for developing agentic AI applications.
- **AWS Principal Solution Architect (09/2022 - 03/2024):** Provided support to Data & AI ISVs, designed scalable SaaS platforms, reduced costs by 15%, and managed petabytes of data. Developed Generative AI solutions for enterprise customers.
- **IBM Distinguished Engineer (10/2016 - 09/2022):** Specialized in event-driven architecture and reactive microservices for hybrid cloud solutions, driving significant business impact.
- **IBM Lab Service (02/2009 - 09/2016):** Led global complex solution deliveries for BPM and business rules management projects with substantial yearly impact.

## Certifications
- IBM WatsonX.ai tech seller (2024)
- AWS Solution Architect Professional (2023)
- PMI Project Management Professional

## Education
- Master's in Computer Science, Nice University, France
- Bachelor's in Computer Science, Nice University, France

## Publications and Contributions
- Co-author of books on "Sustainable IT Architecture" and "Agile Business Rule Development".
- Issued patent on "Contextual evaluation of process model and extraction."
- Regular speaker at IBM and external conferences on business rules, AI, and cloud technologies.

## Awards and Recognition
- Received multiple accolades including IBM Outstanding Corporate Achievement awards and Exceptional Restricted Share Distribution awards.
- Recognized as ILOG consultant of the year in 2003.

7 changes: 7 additions & 0 deletions e2e-demos/resume_tuning/requirements.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@

langchain
langchain-community
pypdf>=3.8,<4
sqlalchemy>1,<2
python-dotenv
sentence-transformers
2 changes: 1 addition & 1 deletion llm-langchain/rag/multiple_queries_rag.py
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
from langchain_openai import OpenAIEmbeddings
from langchain.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_community.vectorstores import Chroma
from langchain_chroma.vectorstores import Chroma

DOMAIN_VS_PATH="./agent_domain_store"

Expand Down

0 comments on commit d638c83

Please sign in to comment.