From the uDemy course on LLM engineering.
https://www.udemy.com/course/llm-engineering-master-ai-and-large-language-models
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
567 lines
30 KiB
567 lines
30 KiB
{ |
|
"cells": [ |
|
{ |
|
"cell_type": "markdown", |
|
"id": "c79dc33e-1a3b-4601-a8f2-219b7a9b6d88", |
|
"metadata": {}, |
|
"source": [ |
|
"# Company Brochure - Relevant Links and Custom Tone\n", |
|
"\n", |
|
"Using GPT to generate a company brochure with the relevant links functionality and the ability to choose the desired tone." |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 1, |
|
"id": "e32f4aa7-6fc4-4dc9-8058-58e6a7f329c5", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Imports\n", |
|
"\n", |
|
"import os\n", |
|
"import requests\n", |
|
"import json\n", |
|
"from typing import List\n", |
|
"from dotenv import load_dotenv\n", |
|
"from bs4 import BeautifulSoup\n", |
|
"from IPython.display import Markdown, display, update_display\n", |
|
"from openai import OpenAI\n", |
|
"import gradio as gr" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 2, |
|
"id": "d1d65a21-bbba-44ff-a2be-85bf2055a493", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"OpenAI API Key set and good to go.\n" |
|
] |
|
} |
|
], |
|
"source": [ |
|
"# Load environment variables in a file called .env\n", |
|
"\n", |
|
"load_dotenv(override=True)\n", |
|
"openai_api_key = os.getenv('OPENAI_API_KEY')\n", |
|
"anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n", |
|
"google_api_key = os.getenv('GOOGLE_API_KEY')\n", |
|
"\n", |
|
"if openai_api_key:\n", |
|
" print(\"OpenAI API Key set and good to go.\")\n", |
|
"else:\n", |
|
" print(\"OpenAI API Key not set. :(\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 3, |
|
"id": "c5db63fe-5da8-496e-9b37-139598d600a7", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Setting up the OpenAI object\n", |
|
"\n", |
|
"openai = OpenAI()\n", |
|
"gpt_model = 'gpt-4o-mini'" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 4, |
|
"id": "535da52f-b280-48ce-aa8b-f82f9f9805d9", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# A class to represent a Webpage\n", |
|
"\n", |
|
"# Some websites need you to use proper headers when fetching them:\n", |
|
"headers = {\n", |
|
" \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36\"\n", |
|
"}\n", |
|
"\n", |
|
"class Website:\n", |
|
" \"\"\"\n", |
|
" A utility class to represent a Website that we have scraped, now with links\n", |
|
" \"\"\"\n", |
|
"\n", |
|
" def __init__(self, url):\n", |
|
" self.url = url\n", |
|
" response = requests.get(url, headers=headers)\n", |
|
" self.body = response.content\n", |
|
" soup = BeautifulSoup(self.body, 'html.parser')\n", |
|
" self.title = soup.title.string if soup.title else \"No title found\"\n", |
|
" if soup.body:\n", |
|
" for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n", |
|
" irrelevant.decompose()\n", |
|
" self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n", |
|
" else:\n", |
|
" self.text = \"\"\n", |
|
" links = [link.get('href') for link in soup.find_all('a')]\n", |
|
" self.links = [link for link in links if link]\n", |
|
"\n", |
|
" def get_contents(self):\n", |
|
" return f\"Webpage Title:\\n{self.title}\\nWebpage Contents:\\n{self.text}\\n\\n\"" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 5, |
|
"id": "8d5757c4-95f4-4038-8ed4-8c81da5112b0", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"link_system_prompt = \"You are provided with a list of links found on a webpage. \\\n", |
|
"You are able to decide which of the links would be most relevant to include in a brochure about the company, \\\n", |
|
"such as links to an About page, or a Company page, or Careers/Jobs pages.\\n\"\n", |
|
"link_system_prompt += \"You should respond in JSON as in this example:\"\n", |
|
"link_system_prompt += \"\"\"\n", |
|
"{\n", |
|
" \"links\": [\n", |
|
" {\"type\": \"about page\", \"url\": \"https://full.url/goes/here/about\"},\n", |
|
" {\"type\": \"careers page\": \"url\": \"https://another.full.url/careers\"}\n", |
|
" ]\n", |
|
"}\n", |
|
"\"\"\"" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 6, |
|
"id": "d5fd31ac-7c81-454a-a1dc-4c58bd3db246", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def get_links_user_prompt(website):\n", |
|
" user_prompt = f\"Here is the list of links on the website of {website.url} - \"\n", |
|
" user_prompt += \"please decide which of these are relevant web links for a brochure about the company, respond with the full https URL in JSON format. \\\n", |
|
"Do not include Terms of Service, Privacy, email links.\\n\"\n", |
|
" user_prompt += \"Links (some might be relative links):\\n\"\n", |
|
" user_prompt += \"\\n\".join(website.links)\n", |
|
" return user_prompt" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 7, |
|
"id": "e8b67492-1ba4-4aad-a588-39116128fa18", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def gpt_get_links(url):\n", |
|
" website = Website(url)\n", |
|
" response = openai.chat.completions.create(\n", |
|
" model= gpt_model,\n", |
|
" messages=[\n", |
|
" {\"role\": \"system\", \"content\": link_system_prompt},\n", |
|
" {\"role\": \"user\", \"content\": get_links_user_prompt(website)}\n", |
|
" ],\n", |
|
" response_format={\"type\": \"json_object\"}\n", |
|
" )\n", |
|
" result = response.choices[0].message.content\n", |
|
" return json.loads(result)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 8, |
|
"id": "e8846e7a-ace2-487e-a0a8-fccb389f2eb9", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# This function provides uses the get_contents method in the Website Class as well as GPT to find relevant links.\n", |
|
"\n", |
|
"def get_all_details(url):\n", |
|
" result = \"Landing page:\\n\"\n", |
|
" result += Website(url).get_contents()\n", |
|
" links = gpt_get_links(url)\n", |
|
" print(\"Found links:\", links)\n", |
|
" for link in links[\"links\"]:\n", |
|
" result += f\"\\n\\n{link['type']}\\n\"\n", |
|
" result += Website(link[\"url\"]).get_contents()\n", |
|
" return result" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 9, |
|
"id": "18b42319-8342-4b9c-bef6-8b72acf92ab3", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def get_brochure_user_prompt(company_name, url):\n", |
|
" user_prompt = f\"You are looking at a company called: {company_name}\\n\"\n", |
|
" user_prompt += f\"Here are the contents of its landing page and other relevant pages; \\\n", |
|
" use this information to build a short brochure of the company in markdown.\\n\"\n", |
|
" \n", |
|
" user_prompt += get_all_details(url)\n", |
|
" user_prompt = user_prompt[:5_000] # Truncate if more than 5,000 characters\n", |
|
" return user_prompt" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 10, |
|
"id": "d7748293-a616-41de-93cb-89f65cc5c73d", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Let's create a call that streams back results\n", |
|
"# If you'd like a refresher on Generators (the \"yield\" keyword),\n", |
|
"# Please take a look at the Intermediate Python notebook in week1 folder.\n", |
|
"\n", |
|
"def stream_brochure(company_name, url, tone):\n", |
|
"\n", |
|
" system_message = f\"You are an assistant that analyzes the content of several relevant pages from a company website \\\n", |
|
" and creates a short brochure about the company for prospective customers, investors, and recruits. \\\n", |
|
" Include details of company culture, customers and careers/jobs if you have the information. \\\n", |
|
" Respond in markdown, and use a {tone.lower()} tone throughout the brochure.\"\n", |
|
"\n", |
|
" \n", |
|
" messages = [\n", |
|
" {\"role\": \"system\", \"content\": system_message},\n", |
|
" {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n", |
|
" ]\n", |
|
" stream = openai.chat.completions.create(\n", |
|
" model=gpt_model,\n", |
|
" messages=messages,\n", |
|
" stream=True\n", |
|
" )\n", |
|
" result = \"\"\n", |
|
" for chunk in stream:\n", |
|
" result += chunk.choices[0].delta.content or \"\"\n", |
|
" yield result" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 11, |
|
"id": "15222832-06e0-4452-a8e1-59b9b1755488", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"* Running on local URL: http://127.0.0.1:7860\n", |
|
"\n", |
|
"To create a public link, set `share=True` in `launch()`.\n" |
|
] |
|
}, |
|
{ |
|
"data": { |
|
"text/html": [ |
|
"<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>" |
|
], |
|
"text/plain": [ |
|
"<IPython.core.display.HTML object>" |
|
] |
|
}, |
|
"metadata": {}, |
|
"output_type": "display_data" |
|
}, |
|
{ |
|
"data": { |
|
"text/plain": [] |
|
}, |
|
"execution_count": 11, |
|
"metadata": {}, |
|
"output_type": "execute_result" |
|
}, |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"Found links: {'links': [{'type': 'about page', 'url': 'https://www.snowflake.com/about/events/'}, {'type': 'company page', 'url': 'https://www.snowflake.com/en/company/overview/about-snowflake/'}, {'type': 'company leadership page', 'url': 'https://www.snowflake.com/en/company/overview/leadership-and-board/'}, {'type': 'careers page', 'url': 'https://careers.snowflake.com/us/en'}, {'type': 'company ESG page', 'url': 'https://www.snowflake.com/en/company/overview/esg/'}, {'type': 'company ventures page', 'url': 'https://www.snowflake.com/en/company/overview/snowflake-ventures/'}, {'type': 'end data disparity page', 'url': 'https://www.snowflake.com/en/company/overview/end-data-disparity/'}]}\n", |
|
"Found links: {'links': [{'type': 'about page', 'url': 'https://www.snowflake.com/about/events/'}, {'type': 'about page', 'url': 'https://www.snowflake.com/company/overview/about-snowflake/'}, {'type': 'leadership page', 'url': 'https://www.snowflake.com/company/overview/leadership-and-board/'}, {'type': 'careers page', 'url': 'https://careers.snowflake.com/us/en'}, {'type': 'investor relations', 'url': 'https://investors.snowflake.com/overview/default.aspx'}, {'type': 'ESG page', 'url': 'https://www.snowflake.com/company/overview/esg/'}, {'type': 'snowflake ventures', 'url': 'https://www.snowflake.com/company/overview/snowflake-ventures/'}, {'type': 'end data disparity', 'url': 'https://www.snowflake.com/company/overview/end-data-disparity/'}]}\n" |
|
] |
|
}, |
|
{ |
|
"name": "stderr", |
|
"output_type": "stream", |
|
"text": [ |
|
"Traceback (most recent call last):\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/connectionpool.py\", line 464, in _make_request\n", |
|
" self._validate_conn(conn)\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/connectionpool.py\", line 1093, in _validate_conn\n", |
|
" conn.connect()\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/connection.py\", line 741, in connect\n", |
|
" sock_and_verified = _ssl_wrap_socket_and_match_hostname(\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/connection.py\", line 920, in _ssl_wrap_socket_and_match_hostname\n", |
|
" ssl_sock = ssl_wrap_socket(\n", |
|
" ^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/util/ssl_.py\", line 460, in ssl_wrap_socket\n", |
|
" ssl_sock = _ssl_wrap_socket_impl(sock, context, tls_in_tls, server_hostname)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/util/ssl_.py\", line 504, in _ssl_wrap_socket_impl\n", |
|
" return ssl_context.wrap_socket(sock, server_hostname=server_hostname)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/ssl.py\", line 517, in wrap_socket\n", |
|
" return self.sslsocket_class._create(\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/ssl.py\", line 1104, in _create\n", |
|
" self.do_handshake()\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/ssl.py\", line 1382, in do_handshake\n", |
|
" self._sslobj.do_handshake()\n", |
|
"ssl.SSLCertVerificationError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1006)\n", |
|
"\n", |
|
"During handling of the above exception, another exception occurred:\n", |
|
"\n", |
|
"Traceback (most recent call last):\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/connectionpool.py\", line 787, in urlopen\n", |
|
" response = self._make_request(\n", |
|
" ^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/connectionpool.py\", line 488, in _make_request\n", |
|
" raise new_e\n", |
|
"urllib3.exceptions.SSLError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1006)\n", |
|
"\n", |
|
"The above exception was the direct cause of the following exception:\n", |
|
"\n", |
|
"Traceback (most recent call last):\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/requests/adapters.py\", line 667, in send\n", |
|
" resp = conn.urlopen(\n", |
|
" ^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/connectionpool.py\", line 841, in urlopen\n", |
|
" retries = retries.increment(\n", |
|
" ^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/util/retry.py\", line 519, in increment\n", |
|
" raise MaxRetryError(_pool, url, reason) from reason # type: ignore[arg-type]\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
"urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='petrofac.com', port=443): Max retries exceeded with url: / (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1006)')))\n", |
|
"\n", |
|
"During handling of the above exception, another exception occurred:\n", |
|
"\n", |
|
"Traceback (most recent call last):\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/gradio/queueing.py\", line 625, in process_events\n", |
|
" response = await route_utils.call_process_api(\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/gradio/route_utils.py\", line 322, in call_process_api\n", |
|
" output = await app.get_blocks().process_api(\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/gradio/blocks.py\", line 2103, in process_api\n", |
|
" result = await self.call_function(\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/gradio/blocks.py\", line 1662, in call_function\n", |
|
" prediction = await utils.async_iteration(iterator)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/gradio/utils.py\", line 735, in async_iteration\n", |
|
" return await anext(iterator)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/gradio/utils.py\", line 729, in __anext__\n", |
|
" return await anyio.to_thread.run_sync(\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/anyio/to_thread.py\", line 56, in run_sync\n", |
|
" return await get_async_backend().run_sync_in_worker_thread(\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/anyio/_backends/_asyncio.py\", line 2461, in run_sync_in_worker_thread\n", |
|
" return await future\n", |
|
" ^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/anyio/_backends/_asyncio.py\", line 962, in run\n", |
|
" result = context.run(func, *args)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/gradio/utils.py\", line 712, in run_sync_iterator_async\n", |
|
" return next(iterator)\n", |
|
" ^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/gradio/utils.py\", line 873, in gen_wrapper\n", |
|
" response = next(iterator)\n", |
|
" ^^^^^^^^^^^^^^\n", |
|
" File \"/var/folders/yc/m81x80gn66j4fbm15pk5gmfr0000gn/T/ipykernel_39727/601932735.py\", line 15, in stream_brochure\n", |
|
" {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/var/folders/yc/m81x80gn66j4fbm15pk5gmfr0000gn/T/ipykernel_39727/3764629295.py\", line 6, in get_brochure_user_prompt\n", |
|
" user_prompt += get_all_details(url)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/var/folders/yc/m81x80gn66j4fbm15pk5gmfr0000gn/T/ipykernel_39727/2913862724.py\", line 5, in get_all_details\n", |
|
" result += Website(url).get_contents()\n", |
|
" ^^^^^^^^^^^^\n", |
|
" File \"/var/folders/yc/m81x80gn66j4fbm15pk5gmfr0000gn/T/ipykernel_39727/1579423502.py\", line 15, in __init__\n", |
|
" response = requests.get(url, headers=headers)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/requests/api.py\", line 73, in get\n", |
|
" return request(\"get\", url, params=params, **kwargs)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/requests/api.py\", line 59, in request\n", |
|
" return session.request(method=method, url=url, **kwargs)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/requests/sessions.py\", line 589, in request\n", |
|
" resp = self.send(prep, **send_kwargs)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/requests/sessions.py\", line 703, in send\n", |
|
" r = adapter.send(request, **kwargs)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/requests/adapters.py\", line 698, in send\n", |
|
" raise SSLError(e, request=request)\n", |
|
"requests.exceptions.SSLError: HTTPSConnectionPool(host='petrofac.com', port=443): Max retries exceeded with url: / (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1006)')))\n", |
|
"Traceback (most recent call last):\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/connectionpool.py\", line 464, in _make_request\n", |
|
" self._validate_conn(conn)\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/connectionpool.py\", line 1093, in _validate_conn\n", |
|
" conn.connect()\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/connection.py\", line 741, in connect\n", |
|
" sock_and_verified = _ssl_wrap_socket_and_match_hostname(\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/connection.py\", line 920, in _ssl_wrap_socket_and_match_hostname\n", |
|
" ssl_sock = ssl_wrap_socket(\n", |
|
" ^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/util/ssl_.py\", line 460, in ssl_wrap_socket\n", |
|
" ssl_sock = _ssl_wrap_socket_impl(sock, context, tls_in_tls, server_hostname)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/util/ssl_.py\", line 504, in _ssl_wrap_socket_impl\n", |
|
" return ssl_context.wrap_socket(sock, server_hostname=server_hostname)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/ssl.py\", line 517, in wrap_socket\n", |
|
" return self.sslsocket_class._create(\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/ssl.py\", line 1104, in _create\n", |
|
" self.do_handshake()\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/ssl.py\", line 1382, in do_handshake\n", |
|
" self._sslobj.do_handshake()\n", |
|
"ssl.SSLCertVerificationError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1006)\n", |
|
"\n", |
|
"During handling of the above exception, another exception occurred:\n", |
|
"\n", |
|
"Traceback (most recent call last):\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/connectionpool.py\", line 787, in urlopen\n", |
|
" response = self._make_request(\n", |
|
" ^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/connectionpool.py\", line 488, in _make_request\n", |
|
" raise new_e\n", |
|
"urllib3.exceptions.SSLError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1006)\n", |
|
"\n", |
|
"The above exception was the direct cause of the following exception:\n", |
|
"\n", |
|
"Traceback (most recent call last):\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/requests/adapters.py\", line 667, in send\n", |
|
" resp = conn.urlopen(\n", |
|
" ^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/connectionpool.py\", line 841, in urlopen\n", |
|
" retries = retries.increment(\n", |
|
" ^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/urllib3/util/retry.py\", line 519, in increment\n", |
|
" raise MaxRetryError(_pool, url, reason) from reason # type: ignore[arg-type]\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
"urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='petrofac.com', port=443): Max retries exceeded with url: / (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1006)')))\n", |
|
"\n", |
|
"During handling of the above exception, another exception occurred:\n", |
|
"\n", |
|
"Traceback (most recent call last):\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/gradio/queueing.py\", line 625, in process_events\n", |
|
" response = await route_utils.call_process_api(\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/gradio/route_utils.py\", line 322, in call_process_api\n", |
|
" output = await app.get_blocks().process_api(\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/gradio/blocks.py\", line 2103, in process_api\n", |
|
" result = await self.call_function(\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/gradio/blocks.py\", line 1662, in call_function\n", |
|
" prediction = await utils.async_iteration(iterator)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/gradio/utils.py\", line 735, in async_iteration\n", |
|
" return await anext(iterator)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/gradio/utils.py\", line 729, in __anext__\n", |
|
" return await anyio.to_thread.run_sync(\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/anyio/to_thread.py\", line 56, in run_sync\n", |
|
" return await get_async_backend().run_sync_in_worker_thread(\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/anyio/_backends/_asyncio.py\", line 2461, in run_sync_in_worker_thread\n", |
|
" return await future\n", |
|
" ^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/anyio/_backends/_asyncio.py\", line 962, in run\n", |
|
" result = context.run(func, *args)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/gradio/utils.py\", line 712, in run_sync_iterator_async\n", |
|
" return next(iterator)\n", |
|
" ^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/gradio/utils.py\", line 873, in gen_wrapper\n", |
|
" response = next(iterator)\n", |
|
" ^^^^^^^^^^^^^^\n", |
|
" File \"/var/folders/yc/m81x80gn66j4fbm15pk5gmfr0000gn/T/ipykernel_39727/601932735.py\", line 15, in stream_brochure\n", |
|
" {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/var/folders/yc/m81x80gn66j4fbm15pk5gmfr0000gn/T/ipykernel_39727/3764629295.py\", line 6, in get_brochure_user_prompt\n", |
|
" user_prompt += get_all_details(url)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/var/folders/yc/m81x80gn66j4fbm15pk5gmfr0000gn/T/ipykernel_39727/2913862724.py\", line 5, in get_all_details\n", |
|
" result += Website(url).get_contents()\n", |
|
" ^^^^^^^^^^^^\n", |
|
" File \"/var/folders/yc/m81x80gn66j4fbm15pk5gmfr0000gn/T/ipykernel_39727/1579423502.py\", line 15, in __init__\n", |
|
" response = requests.get(url, headers=headers)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/requests/api.py\", line 73, in get\n", |
|
" return request(\"get\", url, params=params, **kwargs)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/requests/api.py\", line 59, in request\n", |
|
" return session.request(method=method, url=url, **kwargs)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/requests/sessions.py\", line 589, in request\n", |
|
" resp = self.send(prep, **send_kwargs)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/requests/sessions.py\", line 703, in send\n", |
|
" r = adapter.send(request, **kwargs)\n", |
|
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", |
|
" File \"/opt/anaconda3/envs/llms/lib/python3.11/site-packages/requests/adapters.py\", line 698, in send\n", |
|
" raise SSLError(e, request=request)\n", |
|
"requests.exceptions.SSLError: HTTPSConnectionPool(host='petrofac.com', port=443): Max retries exceeded with url: / (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1006)')))\n" |
|
] |
|
}, |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"Found links: {'links': [{'type': 'about page', 'url': 'https://www.petrofac.com/who-we-are/'}, {'type': 'what we do page', 'url': 'https://www.petrofac.com/who-we-are/what-we-do/'}, {'type': 'careers page', 'url': 'https://www.petrofac.com/careers/'}, {'type': 'our structure page', 'url': 'https://www.petrofac.com/who-we-are/our-structure/'}, {'type': 'energy transition page', 'url': 'https://www.petrofac.com/who-we-are/energy-transition/'}, {'type': 'sustainability and ESG page', 'url': 'https://www.petrofac.com/who-we-are/sustainability-and-esg/'}, {'type': 'investor relations page', 'url': 'https://www.petrofac.com/investors/'}, {'type': 'services page', 'url': 'https://www.petrofac.com/services/'}, {'type': 'where we operate page', 'url': 'https://www.petrofac.com/where-we-operate/'}]}\n" |
|
] |
|
} |
|
], |
|
"source": [ |
|
"view = gr.Interface(\n", |
|
" fn=stream_brochure,\n", |
|
" inputs=[\n", |
|
" gr.Textbox(label=\"Company name:\"),\n", |
|
" gr.Textbox(label=\"Landing page URL including http:// or https://\"),\n", |
|
" gr.Textbox(label=\"Tone:\")],\n", |
|
" outputs=[gr.Markdown(label=\"Brochure:\")],\n", |
|
" flagging_mode=\"never\"\n", |
|
")\n", |
|
"view.launch(inbrowser=True)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "70d6398c-21dd-44f8-ba7d-0204414dffa0", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [] |
|
} |
|
], |
|
"metadata": { |
|
"kernelspec": { |
|
"display_name": "Python 3 (ipykernel)", |
|
"language": "python", |
|
"name": "python3" |
|
}, |
|
"language_info": { |
|
"codemirror_mode": { |
|
"name": "ipython", |
|
"version": 3 |
|
}, |
|
"file_extension": ".py", |
|
"mimetype": "text/x-python", |
|
"name": "python", |
|
"nbconvert_exporter": "python", |
|
"pygments_lexer": "ipython3", |
|
"version": "3.11.11" |
|
} |
|
}, |
|
"nbformat": 4, |
|
"nbformat_minor": 5 |
|
}
|
|
|