brad/LLM_Engineering_OLD
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Improved UI Layout, Added bulk domain check and early stop to improve cost efficiency.

Browse Source
This commit is contained in:
Nik
2025-10-23 12:46:26 +05:30
parent fb4012be8c
commit ca9c77d91c
1 changed files with 218 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files

268
week2/community-contributions/ai_domain_finder/ai_domain_finder.ipynb
View File

@@ -2,21 +2,10 @@
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"execution_count": null,
"id": "1633a440",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'\\nWeek 2 Assignment: LLM Engineering\\nAuthor: Nikhil Raut\\n\\nNotebook: ai_domain_finder.ipynb\\n\\nPurpose:\\nBuild an agentic AI Domain Finder that proposes short, brandable .com names, verifies availability via RDAP, \\nthen returns: \\n a list of available .coms, \\n one preferred pick, \\n and a brief audio rationale.\\n'"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"outputs": [],
"source": [
"\"\"\"\n",
"Week 2 Assignment: LLM Engineering\n",
@@ -35,7 +24,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": null,
"id": "da528fbe",
"metadata": {},
"outputs": [],
@@ -44,6 +33,7 @@
"import json\n",
"import requests\n",
"from typing import Dict, List, Tuple\n",
"import re\n",
"\n",
"from dotenv import load_dotenv\n",
"from openai import OpenAI\n",
@@ -68,56 +58,76 @@
"\n",
"def _to_com(domain: str) -> str:\n",
" d = domain.strip().lower()\n",
" if d.endswith(\".com\"):\n",
" return d\n",
" return f\"{d}.com\"\n",
" return d if d.endswith(\".com\") else f\"{d}.com\"\n",
"\n",
"def check_com_availability(domain: str) -> Dict:\n",
" \"\"\"\n",
" Returns: {\"domain\": \"name.com\", \"available\": bool, \"status\": int}\n",
" Rule: HTTP 200 => already registered (NOT available); 404 => available.\n",
" \"\"\"\n",
" fqdn = _to_com(domain)\n",
" try:\n",
" r = requests.get(RDAP_URL.format(fqdn), timeout=6)\n",
" available = (r.status_code == 404)\n",
" return {\"domain\": fqdn, \"available\": available, \"status\": r.status_code}\n",
" return {\"domain\": fqdn, \"available\": (r.status_code == 404), \"status\": r.status_code}\n",
" except requests.RequestException:\n",
" return {\"domain\": fqdn, \"available\": False, \"status\": 0}\n"
" return {\"domain\": fqdn, \"available\": False, \"status\": 0}\n",
"\n",
"def check_com_availability_bulk(domains: List[str]) -> Dict:\n",
" \"\"\"\n",
" Input: list of domain roots or FQDNs.\n",
" Returns:\n",
" {\n",
" \"results\": [{\"domain\": \"...\", \"available\": bool, \"status\": int}, ...],\n",
" \"available\": [\"...\"], # convenience\n",
" \"count_available\": int\n",
" }\n",
" \"\"\"\n",
" session = requests.Session()\n",
" results: List[Dict] = []\n",
" for d in domains:\n",
" fqdn = _to_com(d)\n",
" try:\n",
" r = session.get(RDAP_URL.format(fqdn), timeout=6)\n",
" ok = (r.status_code == 404)\n",
" results.append({\"domain\": fqdn, \"available\": ok, \"status\": r.status_code})\n",
" except requests.RequestException:\n",
" results.append({\"domain\": fqdn, \"available\": False, \"status\": 0})\n",
"\n",
" available = [x[\"domain\"] for x in results if x[\"available\"]]\n",
" return {\"results\": results, \"available\": available, \"count_available\": len(available)}\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": null,
"id": "cd20c262",
"metadata": {},
"outputs": [],
"source": [
"check_tool = {\n",
"check_tool_bulk = {\n",
" \"type\": \"function\",\n",
" \"function\": {\n",
" \"name\": \"check_com_availability\",\n",
" \"description\": \"Check if a .com domain is available using RDAP. Accepts root or full domain.\",\n",
" \"name\": \"check_com_availability_bulk\",\n",
" \"description\": \"Batch check .com availability via RDAP for a list of domains (roots or FQDNs).\",\n",
" \"parameters\": {\n",
" \"type\": \"object\",\n",
" \"properties\": {\n",
" \"domain\": {\n",
" \"type\": \"string\",\n",
" \"description\": \"Domain root or FQDN to check (limited to .com).\"\n",
" \"domains\": {\n",
" \"type\": \"array\",\n",
" \"items\": {\"type\": \"string\"},\n",
" \"minItems\": 1,\n",
" \"maxItems\": 50,\n",
" \"description\": \"List of domain roots or .com FQDNs.\"\n",
" }\n",
" },\n",
" \"required\": [\"domain\"],\n",
" \"required\": [\"domains\"],\n",
" \"additionalProperties\": False\n",
" }\n",
" }\n",
"}\n",
"\n",
"TOOLS = [check_tool]\n"
"TOOLS = [check_tool_bulk]\n"
]
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": null,
"id": "2a9138b6",
"metadata": {},
"outputs": [],
@@ -225,7 +235,7 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": null,
"id": "7bdf7c67",
"metadata": {},
"outputs": [],
@@ -257,32 +267,184 @@
"metadata": {},
"outputs": [],
"source": [
"INTRO = (\n",
" \"Please provide details as text (three lines or paragraphs):\\n\"\n",
" \"Industry: ...\\n\"\n",
" \"Target Customers: ...\\n\"\n",
" \"Description: ...\\n\\n\"\n",
" \"You can refine in follow-ups (e.g., tone, shorter names, avoid words, etc.).\"\n",
"\n",
"_DOMAIN_RE = re.compile(r\"\\b[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\\.com\\b\", re.I)\n",
"\n",
"def _norm_domain(s: str) -> str:\n",
" s = s.strip().lower()\n",
" return s if s.endswith(\".com\") else f\"{s}.com\"\n",
"\n",
"def parse_available(md: str) -> list[str]:\n",
" lines = md.splitlines()\n",
" out = []\n",
" in_section = False\n",
" for ln in lines:\n",
" if ln.strip().lower().startswith(\"1) available .com domains\"):\n",
" in_section = True\n",
" continue\n",
" if in_section and ln.strip().lower().startswith(\"2) preferred\"):\n",
" break\n",
" if in_section:\n",
" if ln.strip().startswith((\"-\", \"*\")) or _DOMAIN_RE.search(ln):\n",
" for m in _DOMAIN_RE.findall(ln):\n",
" out.append(_norm_domain(m))\n",
" # dedupe while preserving order\n",
" seen, uniq = set(), []\n",
" for d in out:\n",
" if d not in seen:\n",
" seen.add(d)\n",
" uniq.append(d)\n",
" return uniq\n",
"\n",
"def parse_preferred(md: str) -> str:\n",
" # look in the preferred section; fallback to first domain anywhere\n",
" lower = md.lower()\n",
" idx = lower.find(\"2) preferred domain\")\n",
" if idx != -1:\n",
" seg = md[idx: idx + 500]\n",
" m = _DOMAIN_RE.search(seg)\n",
" if m:\n",
" return _norm_domain(m.group(0))\n",
" m = _DOMAIN_RE.search(md)\n",
" return _norm_domain(m.group(0)) if m else \"\"\n",
"\n",
"def merge_and_sort(old: list[str], new: list[str]) -> list[str]:\n",
" merged = {d.lower() for d in old} | {d.lower() for d in new}\n",
" return sorted(merged, key=lambda s: (len(s), s))\n",
"\n",
"def fmt_available_md(domains: list[str]) -> str:\n",
" if not domains:\n",
" return \"### Available .com domains (cumulative)\\n\\n*– none yet –*\"\n",
" items = \"\\n\".join(f\"- `{d}`\" for d in domains)\n",
" return f\"### Available .com domains (cumulative)\\n\\n{items}\"\n",
"\n",
"def fmt_preferred_md(d: str) -> str:\n",
" if not d:\n",
" return \"### Preferred domain\\n\\n*– not chosen yet –*\"\n",
" return f\"### Preferred domain\\n\\n`{d}`\"\n",
"\n",
"def build_initial_message(industry: str, customers: str, desc: str) -> str:\n",
" return (\n",
" \"Please propose .com domains based on:\\n\"\n",
" f\"Industry: {industry}\\n\"\n",
" f\"Target Customers: {customers}\\n\"\n",
" f\"Description: {desc}\"\n",
" )\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "07f079d6",
"metadata": {},
"outputs": [],
"source": [
"def initial_submit(industry: str, customers: str, desc: str,\n",
" history: list[dict], known_avail: list[str], preferred_now: str):\n",
" msg = build_initial_message(industry, customers, desc)\n",
" history = (history or []) + [{\"role\": \"user\", \"content\": msg}]\n",
"\n",
" reply_md, new_avail, preferred, audio_text = run_and_extract(history)\n",
" history += [{\"role\": \"assistant\", \"content\": reply_md}]\n",
"\n",
" all_avail = merge_and_sort(known_avail or [], new_avail)\n",
" preferred_final = preferred or preferred_now or \"\"\n",
" audio_bytes = synth_audio(audio_text)\n",
"\n",
" return (\n",
" history, # s_history\n",
" all_avail, # s_available\n",
" preferred_final, # s_preferred\n",
" gr.update(value=fmt_preferred_md(preferred_final)), # preferred_md\n",
" gr.update(value=fmt_available_md(all_avail)), # available_md\n",
" gr.update(value=\"\", visible=True), # reply_in -> now visible\n",
" gr.update(value=audio_bytes, visible=True), # audio_out\n",
" )\n",
"\n",
"def refine_submit(reply: str,\n",
" history: list[dict], known_avail: list[str], preferred_now: str):\n",
" if not reply.strip():\n",
" return (\"\", history, known_avail, preferred_now,\n",
" gr.update(), gr.update(), gr.update())\n",
"\n",
" history = (history or []) + [{\"role\": \"user\", \"content\": reply.strip()}]\n",
" reply_md, new_avail, preferred, audio_text = run_and_extract(history)\n",
" history += [{\"role\": \"assistant\", \"content\": reply_md}]\n",
"\n",
" all_avail = merge_and_sort(known_avail or [], new_avail)\n",
" preferred_final = preferred or preferred_now or \"\"\n",
" audio_bytes = synth_audio(audio_text)\n",
"\n",
" return (\n",
" \"\", # clear Reply box\n",
" history, # s_history\n",
" all_avail, # s_available\n",
" preferred_final, # s_preferred\n",
" gr.update(value=fmt_preferred_md(preferred_final)), # preferred_md\n",
" gr.update(value=fmt_available_md(all_avail)), # available_md\n",
" gr.update(value=audio_bytes, visible=True), # audio_out\n",
" )\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d52ebc02",
"metadata": {},
"outputs": [],
"source": [
"with gr.Blocks(title=\"AI Domain Finder (.com only)\") as ui:\n",
" gr.Markdown(\"# AI Domain Finder (.com only)\")\n",
" gr.Markdown(\"Provide your business details. The Agent will suggest .com options, verify availability, pick a preferred domain, and speak a short rationale.\")\n",
" with gr.Row():\n",
" chatbot = gr.Chatbot(type=\"messages\", height=460)\n",
" with gr.Row():\n",
" audio_out = gr.Audio(label=\"Audio explanation\", autoplay=True)\n",
" with gr.Row():\n",
" msg = gr.Textbox(label=\"Your input\", placeholder=INTRO, lines=6)\n",
" gr.Markdown(\"Agent proposes .com domains, verifies via RDAP, picks a preferred choice, and explains briefly.\")\n",
"\n",
" def _append_user(m, hist):\n",
" return \"\", hist + [{\"role\": \"user\", \"content\": m}]\n",
" # App state\n",
" s_history = gr.State([])\n",
" s_available = gr.State([])\n",
" s_preferred = gr.State(\"\")\n",
"\n",
" msg.submit(_append_user, inputs=[msg, chatbot], outputs=[msg, chatbot]).then(\n",
" chat, inputs=[msg, chatbot], outputs=[chatbot, audio_out]\n",
" with gr.Row():\n",
" with gr.Column(scale=7): # LEFT 70%\n",
" with gr.Group():\n",
" industry_in = gr.Textbox(label=\"Industry\")\n",
" customers_in = gr.Textbox(label=\"Target Customers\")\n",
" desc_in = gr.Textbox(label=\"Description\", lines=3)\n",
" find_btn = gr.Button(\"Find Domains\", variant=\"primary\")\n",
"\n",
" audio_out = gr.Audio(label=\"Audio explanation\", autoplay=True, visible=False)\n",
"\n",
" reply_in = gr.Textbox(\n",
" label=\"Reply\",\n",
" placeholder=\"Chat with agent to refine the outputs\",\n",
" lines=2,\n",
" visible=False, # 👈 hidden for the first input\n",
" )\n",
"\n",
"ui.launch(inbrowser=True, auth=None, show_error=True)\n"
" with gr.Column(scale=3): # RIGHT 30%\n",
" preferred_md = gr.Markdown(fmt_preferred_md(\"\"))\n",
" available_md = gr.Markdown(fmt_available_md([]))\n",
"\n",
" # Events\n",
" find_btn.click(\n",
" initial_submit,\n",
" inputs=[industry_in, customers_in, desc_in, s_history, s_available, s_preferred],\n",
" outputs=[\n",
" s_history, s_available, s_preferred,\n",
" preferred_md, available_md,\n",
" reply_in, # 👈 becomes visible after first run\n",
" audio_out # 👈 becomes visible after first run\n",
" ],\n",
" )\n",
"\n",
" reply_in.submit(\n",
" refine_submit,\n",
" inputs=[reply_in, s_history, s_available, s_preferred],\n",
" outputs=[\n",
" reply_in, s_history, s_available, s_preferred,\n",
" preferred_md, available_md, audio_out\n",
" ],\n",
" )\n",
"\n",
"ui.launch(inbrowser=True, show_error=True)\n"
]
}
],