code-llm2/interactive_resume
0
1{
2 "cells": [
3 {
4 "cell_type": "code",
5 "execution_count": 1,
6 "id": "f2644433",
7 "metadata": {},
8 "outputs": [],
9 "source": [
10 "from dotenv import load_dotenv\n",
11 "from openai import OpenAI\n",
12 "import json\n",
13 "from openai import OpenAI\n",
14 "\n",
15 "load_dotenv(override=True)\n",
16 "openai = OpenAI()"
17 ]
18 },
19 {
20 "cell_type": "code",
21 "execution_count": 2,
22 "id": "5357c55a",
23 "metadata": {},
24 "outputs": [],
25 "source": [
26 "# read my profile\n",
27 "from pypdf import PdfReader\n",
28 "reader = PdfReader(\"profile/Profile.pdf\")\n",
29 "linkedin = \"\"\n",
30 "for page in reader.pages:\n",
31 " text = page.extract_text()\n",
32 " if text:\n",
33 " linkedin += text\n",
34 "\n",
35 "with open(\"profile/profile_2025-08.md\", \"r\", encoding=\"utf-8\") as f:\n",
36 " summary = f.read()\n",
37 "\n",
38 "name = \"Tanmay Bansal\""
39 ]
40 },
41 {
42 "cell_type": "code",
43 "execution_count": 3,
44 "id": "93309073",
45 "metadata": {},
46 "outputs": [
47 {
48 "name": "stdout",
49 "output_type": "stream",
50 "text": [
51 "# Tanmay Bansal\n",
52 "**Big Data | Spark | AWS | OLTP | OLAP | Data & Analytics | Data Pipeline | Data Architecture | Data Modelling | Data Lifecycle | Al Predictive Scalable Analytics | IaaC | CI/CD | Data Lakehouse | Data Quality & Governance.**\n",
53 "\n",
54 "**Bengaluru, Karnataka, India**\n",
55 "**tanmaybansal@hotmail.com**\n",
56 "**www.linkedin.com/in/tanmaybansal (LinkedIn)**\n",
57 "\n",
58 "---\n",
59 "\n",
60 "### **Summary**\n",
61 "Data Whisperer | Architecting Data Landscapes across Airlines, Aerospace & Finance | 14+ Years Driving Insights with OLAP / OLTP, AI, Prompt Engineering and Cloud Expertise (AWS, Spark)\n",
62 "Passionate about turning data into tangible business value | High Learning Quotient\n",
63 "\n",
64 "\n",
65 "---\n",
66 "\n",
67 "### **Skills and Core Competencies**\n",
68 "* **Data Modelling / Architecture** - Expertise in OLTP, OLAP, Big Data architecture, designing scalable and efficient data pipelines.\n",
69 "* **AI & Predictive Analytics** - Led cross-functional teams in developing distributed analytics on PySpark / EMR, driving AI / ML initiatives.\n",
70 "* **Data Pipelining & Architecture** & DataOps - Designed and implemented robust data pipelines using IaaS and CI/CD, streamlining data flow and onboarding teams effectively.\n",
71 "* **Data Infrastructure & Optimization** – Proven ability to optimize analytics and data infrastructure leading to significant cost reduction.\n",
72 "* **Data Curation & Imputation** - Expertise in managing data quality, consistency, and completeness through effective curation and imputation techniques.\n",
73 "* **End-to-End Module Owner** - Successfully delivered customer-facing modules from requirement gathering to deployment and training.\n",
74 "* **AI Landscape** & Architecting & Solutioning - Knowledge of AI landscape, made AI agents and workflows and RAG models using n8n, LangChain, AWS Bedrock, Hugging Face, Ollama, Open Source Models like Llama, QWEN, vectr Databases like Pinecone and Chroma.\n",
75 "\n",
76 "---\n",
77 "\n",
78 "### Technical Proficiency: \n",
79 "Proficient in a wide range of technologies including:\n",
80 "* **Databases**: Oracle, Postgres, Redshift\n",
81 "* **vector Stores**: Pinecone, Chroma\n",
82 "* **Cloud**: AWS (S3, Athena, EMR, IAM, Lambda, EventBridge, SNS, CloudFormation, CodeBuild)\n",
83 "* **Big Data**: Spark (PySpark), UDFs, Hadoop ecosystem\n",
84 "* **Programming & Tools**: Python, Boto3, SQL, Git, VS Code, Zeppelin, Copilot, Gemini\n",
85 "* **Other**: Oracle Forms and Reports, MS Office 365, Draw.io, Confluence, Bugzilla\n",
86 "\n",
87 "---\n",
88 "\n",
89 "### **Top Skills**\n",
90 "* Distributed computng frameworks like PySpark\n",
91 "* Databases and SQL\n",
92 "* AI Agents, AI Landscape\n",
93 "* ENterprise Data Management\n",
94 "\n",
95 "---\n",
96 "\n",
97 "### **Experience**\n",
98 "\n",
99 "**GE Aerospace**\n",
100 "* **Data Pipeline Architect**\n",
101 " * December 2023 - Present (1 year 9 months)\n",
102 " * Bengaluru, Karnataka, India\n",
103 " * Architected data pipeline for Flight Data through stream to warehouse giving the capability for downstream applications and users to consume data in a usable form\n",
104 "* **FF Pod Lead**\n",
105 " * February 2022 - Present (3 years 7 months)\n",
106 " * Bengaluru, Karnataka, India\n",
107 " * Leading a cross-functional team to build a highly scalable and configurable big data analytic and working with multiple stakeholders in different functions\n",
108 "* **Senior Data Engineer**\n",
109 " * October 2018 - Present (6 years 11 months)\n",
110 " * Bengaluru, Karnataka, India\n",
111 "* **Total Duration:** 6 years 11 months\n",
112 "\n",
113 "**Epsilon**\n",
114 "* **Senior Database Developer**\n",
115 " * September 2016 - September 2018 (2 years 1 month)\n",
116 " * Bengaluru, Karnataka, India\n",
117 "\n",
118 "**Bank of America**\n",
119 "* **Senior Software Engineer**\n",
120 " * August 2015 - August 2016 (1 year 1 month)\n",
121 " * Gurugram, Haryana, India\n",
122 "\n",
123 "**NIIT Technologies**\n",
124 "* **Total Duration:** 5 years\n",
125 "* **Technical Analyst**\n",
126 " * April 2014 - July 2015 (1 year 4 months)\n",
127 " * Greater Delhi Area\n",
128 "* **Senior Software Engineer**\n",
129 " * October 2012 - March 2014 (1 year 6 months)\n",
130 " * Greater Delhi Area\n",
131 "* **Software Engineer**\n",
132 " * August 2010 - September 2012 (2 years 2 months)\n",
133 " * Greater Delhi Area\n",
134 "\n",
135 "---\n",
136 "\n",
137 "### **Education**\n",
138 "\n",
139 "* **Apeejay College of Engineering**\n",
140 " * Bachelors of Engineering, Computer Science (2006-2010)\n",
141 "* **Maharshi Dayanand University**\n",
142 " * Bachelors of Engineering, Computer Science (2006-2010)\n",
143 "\n",
144 "---\n",
145 "\n",
146 "### **Certifications**\n",
147 "\n",
148 "* Oracle Certified Associate PL/SQL Developer\n",
149 "* Cloudera - CCA - Spark and Hadoop Developer\n",
150 "* Gen AI: Navigate the Landscape\n",
151 "* Google Prompting Essentials\n",
152 "* Informatica Cloud Data Governance & Catalog Foundation Series Certificate\n",
153 "* Oracle Database SQL Certified Expert\n",
154 "* DeepMind.AI - Data Engineering Professional\n",
155 "* Universoty of Illinois - Financial Accounting Foundations and Advanced Topics\n",
156 "\n",
157 "---\n",
158 "\n",
159 "### **Languages**\n",
160 "* Hindi\n",
161 "* English\n",
162 "* Punjabi\n"
163 ]
164 }
165 ],
166 "source": [
167 "print(summary)"
168 ]
169 },
170 {
171 "cell_type": "code",
172 "execution_count": 4,
173 "id": "7d93e1d0",
174 "metadata": {},
175 "outputs": [],
176 "source": [
177 "system_prompt = f\"You are acting as {name}. You are answering questions \\\n",
178 "particularly related to {name}'s career, background, skills and experience. \\\n",
179 "Your responsibility is to represent {name} for interactions on the website as faithfully as possible. \\\n",
180 "You are given a complete profile of {name}'s background and LinkedIn profile which you can use to answer questions. \\\n",
181 "Be professional and engaging, as if talking to a potential client or future employer who came across the profile. \\\n",
182 "If you don't know the answer to any question, clearly state that 'you don't know the answer to it, but will appreciate if you can leave your questions at tanmaybansal@hotmail.com', even if it's about something trivial or unrelated to career. \\\n",
183 "If the user is engaging in discussion, try to steer them towards getting in touch via email.\"\n",
184 "\n",
185 "system_prompt += f\"\\n\\n## 'about me':\\n{summary}\\n\\n## LinkedIn Profile:\\n{linkedin}\\n\\n\"\n",
186 "system_prompt += f\"With this context, please chat with the user, always staying in character as {name}.\"\n"
187 ]
188 },
189 {
190 "cell_type": "code",
191 "execution_count": 5,
192 "id": "9ec79605",
193 "metadata": {},
194 "outputs": [],
195 "source": [
196 "\n",
197 "def chat(message, history):\n",
198 " messages = [{\"role\": \"system\", \"content\": system_prompt}] + history + [{\"role\": \"user\", \"content\": message}]\n",
199 " # This is the call to the LLM\n",
200 " response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)\n",
201 " return response.choices[0].message.content"
202 ]
203 },
204 {
205 "cell_type": "code",
206 "execution_count": 6,
207 "id": "5dcbad80",
208 "metadata": {},
209 "outputs": [
210 {
211 "name": "stdout",
212 "output_type": "stream",
213 "text": [
214 "* Running on local URL: http://127.0.0.1:7860\n",
215 "* To create a public link, set `share=True` in `launch()`.\n"
216 ]
217 },
218 {
219 "data": {
220 "text/html": [
221 "<div><iframe src=\"http://127.0.0.1:7860/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
222 ],
223 "text/plain": [
224 "<IPython.core.display.HTML object>"
225 ]
226 },
227 "metadata": {},
228 "output_type": "display_data"
229 },
230 {
231 "data": {
232 "text/plain": []
233 },
234 "execution_count": 6,
235 "metadata": {},
236 "output_type": "execute_result"
237 }
238 ],
239 "source": [
240 "import gradio as gr\n",
241 "gr.ChatInterface(chat, type=\"messages\").launch()"
242 ]
243 }
244 ],
245 "metadata": {
246 "kernelspec": {
247 "display_name": "agents",
248 "language": "python",
249 "name": "python3"
250 },
251 "language_info": {
252 "codemirror_mode": {
253 "name": "ipython",
254 "version": 3
255 },
256 "file_extension": ".py",
257 "mimetype": "text/x-python",
258 "name": "python",
259 "nbconvert_exporter": "python",
260 "pygments_lexer": "ipython3",
261 "version": "3.12.11"
262 }
263 },
264 "nbformat": 4,
265 "nbformat_minor": 5
266}
267