Recruiting · Production

Personal RAG chatbot answering resume questions built with OpenAI, Chroma DB, HuggingFace Spaces, and Gradio

The problem

The author wanted to gain hands-on experience with Generative AI tooling, engage recruiters through more naturalized interactions, and evaluate the readiness of available tooling for real-world projects.

Workflow diagram · grounded in source
1
LinkedIn profile downloaded
trigger
“I manually downloaded my public LinkedIn profile and saved it as an HTML file”
2
HTML converted to Markdown
integration
“I first converted the HTML file into a plain text file using Pandoc. Subsequently, I manually transformed this text file into Markdown to enhance both its format and content.”
3
Content chunked and indexed in Chroma DB
integration
“Subsequently, I crafted another function to import these chunks into Chroma DB”
4
User query submitted via Gradio
trigger
“A personal chatbot is now integrated into my website, ready to field your questions”
5
RAG retrieval from vector database
ai_action
“the function can fetch pertinent information from the Vector Database to enrich the content (via RAG). It's crucial at this stage to not exceed the token limitations imposed by the LLM and to refrain from including irrelevant information…”
6
Response generated by GPT-3.5
ai_action
“Once the responses are formulated, they are sent to the Large Language Model for processing. In my case, I utilized OpenAI's GPT-3.5 16k model”
7
Answer displayed via Gradio
output
“The model's output can then be displayed directly to the user”
Reported outcome

A personal chatbot was successfully deployed on HuggingFace Spaces and integrated into the author's website, ready to answer questions about their professional background.

Reported metrics
Learning and deployment outcomedeeply enriching experience
Reported stack
OpenAI APIgpt-3.5-turbo-16ktext-embedding-ada-002Chroma DBGradioHuggingFace SpacesPandoc
Source
https://mlops.community/blog/forging-a-personal-chatbot-with-openai-api-chroma-db-huggingface-spaces-and-gradio
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

A personal chatbot was successfully deployed on HuggingFace Spaces and integrated into the author's website, ready to answer questions about their professional background.

What tools did this team use?

OpenAI API, gpt-3.5-turbo-16k, text-embedding-ada-002, Chroma DB, Gradio, HuggingFace Spaces, Pandoc.

What results were reported?

Learning and deployment outcome: deeply enriching experience (source-reported, not independently verified).

How is this recruiting AI workflow structured?

LinkedIn profile downloaded → HTML converted to Markdown → Content chunked and indexed in Chroma DB → User query submitted via Gradio → RAG retrieval from vector database → Response generated by GPT-3.5 → Answer displayed via Gradio.

Related recruiting cases