{
"cells": [
{
"cell_type": "markdown",
"source": [
"# Comparing OpenAI and open LLMs\n",
"\n",
"Using the [text-only content of the website of the journal AUR - Agrar- und Umweltrecht](langchain-experiments/data/input/journal-website.txt), \n",
"we compare the performance of GPT-4, GPT-3.5-turbo and Models available on Huggingface.\n",
"\n",
"## Preparation\n",
"\n",
"Import dependencies, define shorthand functions, and prepare test data"
],
"metadata": {
"collapsed": false
},
"id": "396ebd275b60c720"
},
{
"cell_type": "code",
"execution_count": 1,
"outputs": [],
"source": [
"import io\n",
"from langchain_core.prompts import ChatPromptTemplate\n",
"from langchain_openai import ChatOpenAI\n",
"from langchain_core.output_parsers import StrOutputParser\n",
"import pandas as pd\n",
"from dotenv import load_dotenv\n",
"\n",
"load_dotenv()\n",
"\n",
"def response_to_df(response):\n",
" data = io.StringIO(response)\n",
" try:\n",
" return pd.read_csv(data)\n",
" except:\n",
" raise RuntimeError(f\"Error while parsing response:\\n{response}\")\n",
"\n",
"def use_model(model, template, **params):\n",
" prompt = ChatPromptTemplate.from_template(template)\n",
" chain = (\n",
" prompt\n",
" | model\n",
" | StrOutputParser()\n",
" )\n",
" return response_to_df(chain.invoke(params))\n",
"\n",
"with open('data/input/journal-website.txt', encoding='utf-8') as f:\n",
" website_text = f.read()\n",
"journal_name = \"AUR - Agrar- und Umweltrecht\""
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-01-17T19:43:14.633251500Z",
"start_time": "2024-01-17T19:43:07.158102900Z"
}
},
"id": "e46d0648c1c6c96a"
},
{
"cell_type": "markdown",
"source": [
"## Prompt\n",
"\n",
"OpenAI's GPT-4 works perfectly with a minimal, German-language prompt, and infers the meaning of the columns\n",
"to returns the data we need:\n",
"\n",
"```\n",
"Finde im folgenden Text die Herausgeber, Redaktion/Schriftleitung und Beirat der Zeitschrift '{journal_name}' und gebe sie im CSV-Format zurück mit den Spalten 'lastname', 'firstname', 'title', 'position', 'affiliation','role'. Die Spalte 'role' enthält entweder 'Herausgeber', 'Redaktion', 'Beirat', 'Schriftleitung' oder ist leer wenn nicht bestimmbar. Wenn keine passenden Informationen verfügbar sind, gebe nur den CSV-Header zurück. Setze alle Werte in den CSV-Spalten in Anführungszeichen.\"\n",
"````\n",
"\n",
"\n",
"In contrast, the open models performed miserably with such a prompt. We therefore use English and provide very detailed instructions. "
],
"metadata": {
"collapsed": false
},
"id": "eb805270480fbfb5"
},
{
"cell_type": "code",
"execution_count": 5,
"outputs": [],
"source": [
"template = \"\"\"\n",
"In the following German text, which was scraped from a website, find the members of the editorial board or the advisory board of the journal '{journal_name}' as per the following rules:\n",
"- In German, typical labels for these roles are \"Herausgeber\", \"Redaktion/Redakteur/Schriftleitung\" and \"Beirat\". \n",
"- Return the data as comma-separated values, which can be saved to a `.csv` file. Put all values in the CSV rows in quotes. \n",
"- The CSV data must have the columns 'lastname', 'firstname', 'title', 'position', 'affiliation','role'. \n",
"- The column 'role' must contain either 'Herausgeber', 'Redaktion', 'Beirat' or is empty. Leave the column empty if you cannot determine the role. Use 'Redaktion' for the \"Schriftleitung\" role.\n",
"- The column 'title' should contain academic titles such as \"Dr.\" or \"Prof. Dr.\"\n",
"- The column 'position' should contain the job title\n",
"- The column 'affiliation' contains the institution or organization the person belongs to, or the city if one is mentioned\n",
"- If the journal is published (\"herausgeben von\") by an association, institute or other organization, but its name in the column 'lastname'. \n",
"- If you cannot find any information, simply return the CSV header. \n",
"- You must not output any introduction, commentary or explanation such as 'Here is the CSV data for the members of the editorial board or the advisory board of the journal'. Only return the data.\n",
"\n",
"{website_text}\n",
"\"\"\""
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-01-17T20:46:02.624154500Z",
"start_time": "2024-01-17T20:46:02.598111600Z"
}
},
"id": "23aef80911796078"
},
{
"cell_type": "markdown",
"source": [
"## ChatGPT-4 \n",
"\n",
"GPT-4 delivers an almost perfect [result](data/output/editors-openai-gpt-4.csv). There are some problems left which could be resolved by adding some more instructions to the prompt. \n",
"\n"
],
"metadata": {
"collapsed": false
},
"id": "8f994c771cc9b4ef"
},
{
"cell_type": "code",
"execution_count": 3,
"outputs": [
{
"data": {
"text/plain": " lastname firstname title \\\n0 DGAR NaN NaN \n1 Busse Christian Dr. \n2 Endres Ewald Prof. Dr. \n3 Francois Matthias Dr. \n4 von Garmissen Bernd Dr. \n5 Glas Ingo NaN \n6 Graß Christiane NaN \n7 Haarstrich Jens NaN \n8 Koch Erich Dr. \n9 Köpl Christian Dr. \n10 Martinez Jose Prof. Dr. \n11 Nies Volkmar NaN \n12 Stephany Ralf NaN \n13 Wedemeyer Harald NaN \n14 Martinez José Prof. Dr. \n15 Nies Volkmar LLD \n\n position \\\n0 Deutsche Gesellschaft für Agrarrecht \n1 Regierungsdirektor \n2 NaN \n3 Rechtsanwalt \n4 Rechtsanwalt \n5 Rechtsanwalt \n6 Rechtsanwältin \n7 Rechtsanwalt \n8 Ltd. Verwaltungsdirektor \n9 Ministerialrat \n10 NaN \n11 Ltd. Landwirtschaftsdirektor \n12 Rechtsanwalt/Steuerberater \n13 Rechtsanwalt \n14 Erster Schriftleiter \n15 Zweiter Schriftleiter \n\n affiliation role \n0 NaN Herausgeber \n1 Bundesministerium für Ernährung und Landwirtsc... Redaktion \n2 Hochschule Weihenstephan-Triesdorf, Freising Redaktion \n3 Bitburg Redaktion \n4 Göttingen Redaktion \n5 Rostock Redaktion \n6 Bonn Redaktion \n7 Peine Redaktion \n8 Sozialversicherung für Landwirtschaft, Forsten... Redaktion \n9 Bayerisches Staatsministerium für Ernährung, L... Redaktion \n10 Institut für Landwirtschaftsrecht, Georg-Augus... Redaktion \n11 Landwirtschaftskammer NRW, Bonn Redaktion \n12 Bonn Redaktion \n13 Landvolk Niedersachsen, Hannover Redaktion \n14 Institut für Landwirtschaftsrecht, Göttingen Redaktion \n15 50170 Kerpen Redaktion ",
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>lastname</th>\n <th>firstname</th>\n <th>title</th>\n <th>position</th>\n <th>affiliation</th>\n <th>role</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>DGAR</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>Deutsche Gesellschaft für Agrarrecht</td>\n <td>NaN</td>\n <td>Herausgeber</td>\n </tr>\n <tr>\n <th>1</th>\n <td>Busse</td>\n <td>Christian</td>\n <td>Dr.</td>\n <td>Regierungsdirektor</td>\n <td>Bundesministerium für Ernährung und Landwirtsc...</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>2</th>\n <td>Endres</td>\n <td>Ewald</td>\n <td>Prof. Dr.</td>\n <td>NaN</td>\n <td>Hochschule Weihenstephan-Triesdorf, Freising</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>3</th>\n <td>Francois</td>\n <td>Matthias</td>\n <td>Dr.</td>\n <td>Rechtsanwalt</td>\n <td>Bitburg</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>4</th>\n <td>von Garmissen</td>\n <td>Bernd</td>\n <td>Dr.</td>\n <td>Rechtsanwalt</td>\n <td>Göttingen</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>5</th>\n <td>Glas</td>\n <td>Ingo</td>\n <td>NaN</td>\n <td>Rechtsanwalt</td>\n <td>Rostock</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>6</th>\n <td>Graß</td>\n <td>Christiane</td>\n <td>NaN</td>\n <td>Rechtsanwältin</td>\n <td>Bonn</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>7</th>\n <td>Haarstrich</td>\n <td>Jens</td>\n <td>NaN</td>\n <td>Rechtsanwalt</td>\n <td>Peine</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>8</th>\n <td>Koch</td>\n <td>Erich</td>\n <td>Dr.</td>\n <td>Ltd. Verwaltungsdirektor</td>\n <td>Sozialversicherung für Landwirtschaft, Forsten...</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>9</th>\n <td>Köpl</td>\n <td>Christian</td>\n <td>Dr.</td>\n <td>Ministerialrat</td>\n <td>Bayerisches Staatsministerium für Ernährung, L...</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>10</th>\n <td>Martinez</td>\n <td>Jose</td>\n <td>Prof. Dr.</td>\n <td>NaN</td>\n <td>Institut für Landwirtschaftsrecht, Georg-Augus...</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>11</th>\n <td>Nies</td>\n <td>Volkmar</td>\n <td>NaN</td>\n <td>Ltd. Landwirtschaftsdirektor</td>\n <td>Landwirtschaftskammer NRW, Bonn</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>12</th>\n <td>Stephany</td>\n <td>Ralf</td>\n <td>NaN</td>\n <td>Rechtsanwalt/Steuerberater</td>\n <td>Bonn</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>13</th>\n <td>Wedemeyer</td>\n <td>Harald</td>\n <td>NaN</td>\n <td>Rechtsanwalt</td>\n <td>Landvolk Niedersachsen, Hannover</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>14</th>\n <td>Martinez</td>\n <td>José</td>\n <td>Prof. Dr.</td>\n <td>Erster Schriftleiter</td>\n <td>Institut für Landwirtschaftsrecht, Göttingen</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>15</th>\n <td>Nies</td>\n <td>Volkmar</td>\n <td>LLD</td>\n <td>Zweiter Schriftleiter</td>\n <td>50170 Kerpen</td>\n <td>Redaktion</td>\n </tr>\n </tbody>\n</table>\n</div>"
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model = ChatOpenAI(model_name=\"gpt-4\")\n",
"df = use_model(model, template, journal_name=journal_name, website_text=website_text)\n",
"df.to_csv('data/output/editors-openai-gpt-4.csv')\n",
"df"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-01-17T19:43:51.821749100Z",
"start_time": "2024-01-17T19:43:22.643583400Z"
}
},
"id": "initial_id"
},
{
"cell_type": "markdown",
"source": [
"## ChatGPT 3.5-turbo\n",
"\n",
"GPT-3.5 [performs less well](data/output/editors-openai-gpt-3.5-turbo.csv), but still ok. It gets some of the 'title' amd 'position' \n",
"column data confused, and does not recognize the institutional publisher (Herausgeber) of the journal. \n"
],
"metadata": {
"collapsed": false
},
"id": "9cef77bb17d57b53"
},
{
"cell_type": "code",
"execution_count": 4,
"outputs": [
{
"data": {
"text/plain": " lastname firstname title \\\n0 Busse Christian Dr. \n1 Endres Ewald Prof. Dr. \n2 Francois Matthias Dr. \n3 von Garmissen Bernd Dr. \n4 Glas Ingo NaN \n5 Graß Christiane Rechtsanwältin \n6 Haarstrich Jens Rechtsanwalt \n7 Koch Erich Dr. \n8 Köpl Christian Dr. \n9 Martinez Jose Prof. Dr. \n10 Nies Volkmar Ltd. Landwirtschaftsdirektor \n11 Stephany Ralf Rechtsanwalt/Steuerberater \n12 Wedemeyer Harald Rechtsanwalt \n\n position \\\n0 Regierungsdirektor \n1 NaN \n2 Rechtsanwalt \n3 Rechtsanwalt \n4 Rechtsanwalt \n5 NaN \n6 NaN \n7 Ltd. Verwaltungsdirektor \n8 Ministerialrat \n9 NaN \n10 NaN \n11 NaN \n12 NaN \n\n affiliation role \n0 Bundesministerium für Ernährung und Landwirtsc... Redaktion \n1 Hochschule Weihenstephan-Triesdorf, Freising Redaktion \n2 Bitburg Redaktion \n3 Göttingen Redaktion \n4 Rostock Redaktion \n5 Bonn Redaktion \n6 Peine Redaktion \n7 Sozialversicherung für Landwirtschaft, Forsten... Redaktion \n8 Bayerisches Staatsministerium für Ernährung, L... Redaktion \n9 Institut für Landwirtschaftsrecht, Georg-Augus... Redaktion \n10 Landwirtschaftskammer NRW, Bonn Redaktion \n11 Bonn Redaktion \n12 Landvolk Niedersachsen, Hannover Redaktion ",
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>lastname</th>\n <th>firstname</th>\n <th>title</th>\n <th>position</th>\n <th>affiliation</th>\n <th>role</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>Busse</td>\n <td>Christian</td>\n <td>Dr.</td>\n <td>Regierungsdirektor</td>\n <td>Bundesministerium für Ernährung und Landwirtsc...</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>1</th>\n <td>Endres</td>\n <td>Ewald</td>\n <td>Prof. Dr.</td>\n <td>NaN</td>\n <td>Hochschule Weihenstephan-Triesdorf, Freising</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>2</th>\n <td>Francois</td>\n <td>Matthias</td>\n <td>Dr.</td>\n <td>Rechtsanwalt</td>\n <td>Bitburg</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>3</th>\n <td>von Garmissen</td>\n <td>Bernd</td>\n <td>Dr.</td>\n <td>Rechtsanwalt</td>\n <td>Göttingen</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>4</th>\n <td>Glas</td>\n <td>Ingo</td>\n <td>NaN</td>\n <td>Rechtsanwalt</td>\n <td>Rostock</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>5</th>\n <td>Graß</td>\n <td>Christiane</td>\n <td>Rechtsanwältin</td>\n <td>NaN</td>\n <td>Bonn</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>6</th>\n <td>Haarstrich</td>\n <td>Jens</td>\n <td>Rechtsanwalt</td>\n <td>NaN</td>\n <td>Peine</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>7</th>\n <td>Koch</td>\n <td>Erich</td>\n <td>Dr.</td>\n <td>Ltd. Verwaltungsdirektor</td>\n <td>Sozialversicherung für Landwirtschaft, Forsten...</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>8</th>\n <td>Köpl</td>\n <td>Christian</td>\n <td>Dr.</td>\n <td>Ministerialrat</td>\n <td>Bayerisches Staatsministerium für Ernährung, L...</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>9</th>\n <td>Martinez</td>\n <td>Jose</td>\n <td>Prof. Dr.</td>\n <td>NaN</td>\n <td>Institut für Landwirtschaftsrecht, Georg-Augus...</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>10</th>\n <td>Nies</td>\n <td>Volkmar</td>\n <td>Ltd. Landwirtschaftsdirektor</td>\n <td>NaN</td>\n <td>Landwirtschaftskammer NRW, Bonn</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>11</th>\n <td>Stephany</td>\n <td>Ralf</td>\n <td>Rechtsanwalt/Steuerberater</td>\n <td>NaN</td>\n <td>Bonn</td>\n <td>Redaktion</td>\n </tr>\n <tr>\n <th>12</th>\n <td>Wedemeyer</td>\n <td>Harald</td>\n <td>Rechtsanwalt</td>\n <td>NaN</td>\n <td>Landvolk Niedersachsen, Hannover</td>\n <td>Redaktion</td>\n </tr>\n </tbody>\n</table>\n</div>"
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model = ChatOpenAI(model_name=\"gpt-3.5-turbo\")\n",
"df = use_model(model, template, journal_name=journal_name, website_text=website_text)\n",
"df.to_csv('data/output/editors-openai-gpt-3.5-turbo.csv')\n",
"df"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-01-17T19:46:04.139744300Z",
"start_time": "2024-01-17T19:45:46.825487Z"
}
},
"id": "e1aedc5ef3cab564"
},
{
"cell_type": "markdown",
"source": [
"Now, let's try the open models via the Huggingface Inference Endpoint. For this to work, you need to deploy\n",
"endpoints via https://ui.endpoints.huggingface.co/ and update the value of `enpoint_url` below."
],
"metadata": {
"collapsed": false
},
"id": "31084716e138fe06"
},
{
"cell_type": "markdown",
"source": [
"## TheBloke/Llama-2-13B-chat-GPTQ \n",
"\n",
"The [LLama2 13 billion parameter model](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ) produces [unusuable output](data/output/editors-llama-2-13b-chat-gptq.txt)."
],
"metadata": {
"collapsed": false
},
"id": "90ce37abf037e19f"
},
{
"cell_type": "code",
"execution_count": 4,
"outputs": [
{
"data": {
"text/plain": "['Martinez, Dr. Christian Busse, Bundesministerium für Ernährung und Landwirtschaft, Bonn Agrarprodukt Recht',\n 'Prof. Dr. Ewald Endres, Hochschule Weihenstephan-Triesdorf Freising Forsting Forsting, Jagd, Fischerei, Fischerei',\n 'Lawyeranwalt Ingo Glas, Bitburg Boden Recht',\n 'Christiane Grass, Bonn Agrarzivil Recht',\n 'Jens Haarstrich, Peine Redaktionär, Rostock',\n 'Prof. Dr. Bernd von Garmissen, Göttingen Erb, Redaktion, Umwelt',\n 'Ltdr. Jose Martinez, Georg-August-Universität Göttingen, Göttingen',\n '',\n '',\n \"Note: The column 'Role' contains the following values: 'Herausgeber', 'Redaktion', 'Beirat'\"]"
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from lib.hf_llama2_chat_gptq import query\n",
"llama2_template = f\"<s>[INST] <<SYS>>You are a helpful assistant. No comments or explanation, just answer the question.<</SYS>>{template}[/INST]\"\n",
"\n",
"endpoint_url = \"https://z8afrqamxvaaitmf.us-east-1.aws.endpoints.huggingface.cloud\"\n",
"query(endpoint_url, template, journal_name=journal_name, website_text=website_text).split(\"\\n\")\n"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-01-17T19:31:23.221568600Z",
"start_time": "2024-01-17T19:31:16.694648400Z"
}
},
"id": "f05098a4cf2aa3dc"
},
{
"cell_type": "markdown",
"source": [
"## TheBloke/Llama-2-70B-chat-GPTQ via Huggingface Inference Endpoint\n",
"\n",
"The 70 billion parameter variant [does a bit better](data/output/editors-llama-2-70b-chat-gptq.csv) but, among other things, doesn't the academic titles right. It also cannot be persuaded to [not comment on the CSV output].(data/output/editors-llama-2-70b-chat-gptq.txt). Given that the model costs $13/h to run, that's not really that impressive."
],
"metadata": {
"collapsed": false
},
"id": "ca33fb28f6772cbc"
},
{
"cell_type": "code",
"execution_count": 3,
"outputs": [
{
"data": {
"text/plain": "' Here is the CSV data for the members of the editorial board or the advisory board of the journal \\'AUR - Agrar- und Umweltrecht\\':\\n\\n\"lastname\",\"firstname\",\"title\",\"affiliation\",\"role\"\\n\"Busse\",\"Christian\", \"Regierungsdirektor\", \"Bundesministerium für Ernährung und Landwirtschaft, Bonn\", \"Herausgeber\"\\n\"Endres\",\"Ewald\", \"Prof. Dr.\", \"Hochschule Weihenstephan-Triesdorf, Freising\", \"Redaktion\"\\n\"Francois\",\"Matthias\", \"Rechtsanwalt\", \"Bitburg\", \"Redaktion\"\\n\"Garmissen\",\"Bernd\", \"Rechtsanwalt\", \"Göttingen\", \"Redaktion\"\\n\"Graß\",\"Christiane\", \"Rechtsanwältin\", \"Bonn\", \"Redaktion\"\\n\"Haarstrich\",\"Jens\", \"Rechtsanwalt\", \"Peine\", \"Redaktion\"\\n\"Köpl\",\"Christian\", \"Ministerialrat\", \"Bayerisches Staatsministerium für Ernährung, Landwirtschaft und Forsten, München\", \"\"\\n\"Martinez\",\"Jose\", \"Prof. Dr.\", \"Institut für Landwirtschaftsrecht, Georg-August-Universität Göttingen, Göttingen\", \"Herausgeber\"\\n\"Nies\",\"Volkmar\", \"Ltd. Landwirtschaftsdirektor\", \"Landwirtschaftskammer NRW, Bonn\", \"Redaktion\"\\n\"Stephany\",\"Ralf\", \"Rechtsanwalt/Steuerberater\", \"Bonn\", \"Redaktion\"\\n\"Wedemeyer\",\"Harald\", \"Rechtsanwalt\", \"Landvolk Niedersachsen, Hannover\", \"Redaktion\"\\n\"Schell\",\"Irina Valeska\", \"\", \"Georg-August-Universität Göttingen, Göttingen\", \"\"\\n\\nNote: The column \\'role\\' is empty for some members, as their role could not be determined.'"
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"endpoint_url = \"https://gp8iviqlqee101a0.us-east-1.aws.endpoints.huggingface.cloud\"\n",
"query(endpoint_url, template, journal_name=journal_name, website_text=website_text).split(\"\\n\")"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-01-17T19:14:56.752808800Z",
"start_time": "2024-01-17T19:13:45.800635700Z"
}
},
"id": "b94cf62b996bf3a2"
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.6"
}
},
"nbformat": 4,
"nbformat_minor": 5
}