Commit ·
cbe0714
0
Parent(s):
first commit
Browse files- .DS_Store +0 -0
- .gitignore +3 -0
- hype_pack/.DS_Store +0 -0
- hype_pack/__init__.py +0 -0
- hype_pack/hype_agent.py +27 -0
- hype_pack/tests/.DS_Store +0 -0
- hype_pack/tests/test_data/leo_linkedin_profile.pdf +0 -0
- hype_pack/tests/test_data/test_job_description.txt +71 -0
- hype_pack/tests/test_data/test_profile_entry.txt +5 -0
- hype_pack/utils/__init__.py +0 -0
- langgraph.json +0 -0
- output.mp3 +0 -0
- poetry.lock +0 -0
- pyproject.toml +28 -0
.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
.gitignore
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
.env
|
| 2 |
+
__pycache__/
|
| 3 |
+
hype_pack/depricated_files/
|
hype_pack/.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
hype_pack/__init__.py
ADDED
|
File without changes
|
hype_pack/hype_agent.py
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from utils.state import State
|
| 2 |
+
from utils.tools import read_pdf
|
| 3 |
+
|
| 4 |
+
def upload_documents(pdf_path: str, personal_history_text: str, aspiring_position_text: str) -> State:
|
| 5 |
+
"""
|
| 6 |
+
Uploads documents and updates the state with focus points.
|
| 7 |
+
|
| 8 |
+
Args:
|
| 9 |
+
- pdf_path (str): Path to the PDF file.
|
| 10 |
+
- personal_history_text (str): Free text input for personal history.
|
| 11 |
+
- aspiring_position_text (str): Free text input for aspiring position.
|
| 12 |
+
|
| 13 |
+
Returns:
|
| 14 |
+
- State: Updated state with focus points.
|
| 15 |
+
"""
|
| 16 |
+
# Read PDF and create a new state instance
|
| 17 |
+
pdf_text = read_pdf(pdf_path)
|
| 18 |
+
|
| 19 |
+
# Create a new State instance with the gathered data
|
| 20 |
+
state = State(
|
| 21 |
+
personal_history_focus_points=pdf_text + personal_history_text,
|
| 22 |
+
aspiring_position_focus_points=aspiring_position_text
|
| 23 |
+
)
|
| 24 |
+
|
| 25 |
+
# Here you would add logic to generate focus points from the text
|
| 26 |
+
# For now, we just return the state
|
| 27 |
+
return state
|
hype_pack/tests/.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
hype_pack/tests/test_data/leo_linkedin_profile.pdf
ADDED
|
Binary file (58 kB). View file
|
|
|
hype_pack/tests/test_data/test_job_description.txt
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Data and AI Specialist
|
| 2 |
+
Remote
|
| 3 |
+
|
| 4 |
+
About Crunchbase
|
| 5 |
+
Crunchbase helps over 75 million people around the world connect with the companies and people that matter. Powered by best-in-class proprietary data, Crunchbase is democratizing access to opportunities so salespeople, entrepreneurs, investors, job seekers, and others can accelerate innovation for a better future. We’re proud to build intelligent products that shape how companies and people connect and enable them to communicate in a more meaningful way.
|
| 6 |
+
|
| 7 |
+
We are committed to a positive, diverse, and inclusive culture by hiring for potential, focused on the inclusion of people who have different ways of thinking, different viewpoints, different backgrounds, and different skill sets. We value a transparent and open culture that positively impacts our teams and our products.
|
| 8 |
+
|
| 9 |
+
Crunchbase has a remote-first approach, and is open to hiring in residents of these states:
|
| 10 |
+
California, Colorado, Illinois, Florida, Georgia, Massachusetts, Nevada, New Jersey, New York, North Carolina, Oregon, Pennsylvania, South Carolina, Texas, Virginia, and Washington
|
| 11 |
+
|
| 12 |
+
Our inclusive remote-first culture, generous PTO policies, competitive pay, and employee wellness benefits set us apart!
|
| 13 |
+
|
| 14 |
+
Job Summary:
|
| 15 |
+
|
| 16 |
+
At Crunchbase, our dataset is a living, breathing entity, expanding daily through the collective efforts of the public, our venture program, partners, and our dedicated internal team. The Data Management team at Crunchbase takes the lead in driving initiatives that not only ensure the accuracy but also accelerate the growth of our dynamic dataset.
|
| 17 |
+
|
| 18 |
+
If you're motivated by the prospect of solving complex problems using data and AI, then we have an exciting opportunity for you! We're seeking individuals with a passion for engaging in diverse projects that span across building tools to enable AI initiatives, optimization of AI models, research, data curation, analysis, and program management.
|
| 19 |
+
|
| 20 |
+
Essential Duties/Responsibilities:
|
| 21 |
+
|
| 22 |
+
Compile and experiment with different prompts to test and optimize LLM outputs to achieve desired results
|
| 23 |
+
Collaborate with data scientists and engineers to create training data sets and fine-tune the AI model's behavior and responses
|
| 24 |
+
Define LLMs models' performance metrics and conduct regular evaluations to measure and improve model performance
|
| 25 |
+
Design, develop, and maintain tools and infrastructure to support and enable LLM initiatives, staying ahead of industry advancements and updating tooling as necessary to ensure cutting-edge capabilities and optimal performance
|
| 26 |
+
Keep abreast of industry best practices, stay informed on emerging trends, and ethical considerations in AI development
|
| 27 |
+
Work with external vendors to get high quality data labels
|
| 28 |
+
Review and fix and data quality issues within Crunchbase data
|
| 29 |
+
Review and audit outsource team’s work to ensure the accuracy of the data entered in Crunchbase
|
| 30 |
+
Required Skills/Abilities:
|
| 31 |
+
|
| 32 |
+
Excellent written and verbal communication skills
|
| 33 |
+
Ability to generate high-quality documentation
|
| 34 |
+
Ability to work independently and in a team environment
|
| 35 |
+
Strong analytical and problem-solving skills.
|
| 36 |
+
Education and Experience:
|
| 37 |
+
|
| 38 |
+
1+ years of industry experience in data labeling or other data management fields
|
| 39 |
+
Familiarity or experience in LLMs such as GPT
|
| 40 |
+
Intermediate/Advanced SQL skills, Python skills
|
| 41 |
+
Experience with Google Sheets
|
| 42 |
+
You hold a high bar on code quality and enjoy building systems and tools that can be used by others.
|
| 43 |
+
You are excited and interested in production systems and enabling LLMs and other MLs models.
|
| 44 |
+
Excellent written and verbal communication skills, problem-solving skills, and analytical skills
|
| 45 |
+
Ability to generate high-quality documentation
|
| 46 |
+
Ability to work independently and in a team environment
|
| 47 |
+
Physical Requirements:
|
| 48 |
+
|
| 49 |
+
Prolonged periods of sitting at a desk and working on a computer.
|
| 50 |
+
You may also be entitled to receive equity and benefits.
|
| 51 |
+
Salary Range
|
| 52 |
+
|
| 53 |
+
$100,000 - $120,000 USD
|
| 54 |
+
|
| 55 |
+
What Crunchbase Offers:
|
| 56 |
+
Competitive salary and equity
|
| 57 |
+
Remote first policy
|
| 58 |
+
Generous Reimbursement policy for learning and development activities
|
| 59 |
+
Monthly fitness / mental health stipend
|
| 60 |
+
14 weeks of fully-paid time off for new parents
|
| 61 |
+
Flexible Paid Time Off (PTO)
|
| 62 |
+
Volunteering Paid Time Off
|
| 63 |
+
Incredible medical, vision and dental benefits for employees and their families
|
| 64 |
+
401(k) and Roth plans, and free annual financial adviser check-in
|
| 65 |
+
Monthly internet stipend
|
| 66 |
+
Work from home allowance to purchase furniture for your work from home space
|
| 67 |
+
Matching charity contributions for our Townhall awards
|
| 68 |
+
A team of creative, transparent entrepreneurs driven to accomplish our mission
|
| 69 |
+
At Crunchbase, we value team members who are passionate and enthusiastic about what we're building here. We believe there is no "perfect" candidate, and want to encourage applying even if all the requirements listed aren’t met. If you're passionate about Crunchbase and looking to learn and grow, then we look forward to reviewing your application!
|
| 70 |
+
|
| 71 |
+
Crunchbase does not discriminate on the basis of race, creed, color, ethnicity, national origin, religion, sex, sexual orientation, gender expression, age, height, weight, veteran status, military obligations, or marital status. We will consider for employment qualified applicants with arrest and conviction records. Every day our team is honored to work with entrepreneurs and innovators from every corner of the globe, and we aim to build a team that reflects the diversity of our customers. Each individual at Crunchbase brings their own perspectives, work experiences, lifestyles, and cultures with them, and we believe that a more diverse team creates more innovative products, provides a better service to its customers, and helps us all grow and learn as individuals.
|
hype_pack/tests/test_data/test_profile_entry.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Hi, I'm Leo Walker, a Data Scientist with a unique blend of military leadership and technical expertise. I've built and deployed LLM pipelines at IVP and developed NLP solutions at BP that delivered measurable business impact. Most recently, I've been focused on generative AI projects, including SearchArena, which compares different search providers, and LlamaWorksDB, which won "Best Use of LlamaIndex" in a recent hackathon2.
|
| 2 |
+
My background includes implementing machine learning solutions that drove operational improvements worth millions of dollars1
|
| 3 |
+
, and I'm particularly passionate about building practical AI applications using tools like Langraph. With my Master's in Data Science from the University of Denver and certifications in project management, I bring both technical depth and proven leadership experience from managing complex operations in the 75th Ranger Regiment1
|
| 4 |
+
3.
|
| 5 |
+
I'm excited about the future of AI agents and looking to leverage my experience in LLMs, Python, and data pipeline development to help companies build and scale their generative AI solutions. My combination of technical skills, business acumen, and ability to lead cross-functional teams makes me uniquely qualified to drive AI initiatives forward.
|
hype_pack/utils/__init__.py
ADDED
|
File without changes
|
langgraph.json
ADDED
|
File without changes
|
output.mp3
ADDED
|
Binary file (211 kB). View file
|
|
|
poetry.lock
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pyproject.toml
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[tool.poetry]
|
| 2 |
+
name = "hypecast"
|
| 3 |
+
version = "0.1.0"
|
| 4 |
+
description = "AI-powered career matching system"
|
| 5 |
+
authors = ["Leo Walker <leowalker89@gmail.com>"]
|
| 6 |
+
|
| 7 |
+
[tool.poetry.dependencies]
|
| 8 |
+
python = ">=3.9,<3.12"
|
| 9 |
+
langchain = ">=0.3.0,<0.4.0"
|
| 10 |
+
langchain-openai = ">=0.2.0"
|
| 11 |
+
langchain-anthropic = ">=0.2.0,<0.3.0"
|
| 12 |
+
langchain-google-genai = ">=0.0.5"
|
| 13 |
+
langchain-community = ">=0.3.0,<0.4.0"
|
| 14 |
+
pypdf = "^3.17.1"
|
| 15 |
+
pydantic = ">=2.0.0,<3.0.0"
|
| 16 |
+
python-dotenv = "^1.0.0"
|
| 17 |
+
openai = ">=1.6.1"
|
| 18 |
+
lmnt = "^0.1.0"
|
| 19 |
+
pydub = "^0.25.1"
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
[tool.poetry.group.dev.dependencies]
|
| 23 |
+
ipykernel = "^6.29.5"
|
| 24 |
+
notebook = "^7.2.2"
|
| 25 |
+
|
| 26 |
+
[build-system]
|
| 27 |
+
requires = ["poetry-core"]
|
| 28 |
+
build-backend = "poetry.core.masonry.api"
|