mirror of
https://github.com/langchain-ai/langchain.git
synced 2026-10-06 18:05:25 +03:00
Change default Metaphor search example to use prompt optimizer (#8890)
- fix install command - change example notebook to use Metaphor autoprompt by default <!-- Thank you for contributing to LangChain! Replace this comment with: - Description: a description of the change, - Issue: the issue # it fixes (if applicable), - Dependencies: any dependencies required for this change, - Tag maintainer: for a quicker response, tag the relevant maintainer (see below), - Twitter handle: we announce bigger features on Twitter. If your PR gets announced and you'd like a mention, we'll gladly shout you out! Please make sure you're PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. Maintainer responsibilities: - General / Misc / if you don't know who to tag: @baskaryan - DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev - Models / Prompts: @hwchase17, @baskaryan - Memory: @hwchase17 - Agents / Tools / Toolkits: @hinthornw - Tracing / Callbacks: @agola11 - Async: @agola11 If no one reviews your PR within a few days, feel free to @-mention the same people again. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md -->
This commit is contained in:
Jeffrey Wang authored and GitHub committed
1 parent
d56eff042a
commit
ff44fe4e16
1 file changed
+36
-34
@@ -42,7 +42,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -51,7 +51,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -62,7 +62,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -72,14 +72,14 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"@tool\n",
|
||||
"def search(query: str):\n",
|
||||
" \"\"\"Call search engine with a query.\"\"\"\n",
|
||||
" return client.search(query)\n",
|
||||
" return client.search(query, use_autoprompt=True, num_results=5)\n",
|
||||
"\n",
|
||||
"@tool\n",
|
||||
"def get_contents(ids: List[str]):\n",
|
||||
@@ -95,12 +95,12 @@
|
||||
" \n",
|
||||
" The url passed in should be a URL returned from `search`\n",
|
||||
" \"\"\"\n",
|
||||
" return client.find_similar(url)"
|
||||
" return client.find_similar(url, num_results=5)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -116,7 +116,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"execution_count": 16,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -126,7 +126,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"execution_count": 18,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -139,7 +139,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"execution_count": 19,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -149,7 +149,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"execution_count": 20,
|
||||
"metadata": {
|
||||
"scrolled": false
|
||||
},
|
||||
@@ -165,25 +165,32 @@
|
||||
"Invoking: `search` with `{'query': 'hottest AI agent startups'}`\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[0m\u001b[36;1m\u001b[1;3mSearchResponse(results=[Result(title='The AI Hot 75', url='https://www.nfx.com/post/generative-ai-hot-75-list', id='pb0vypILvIakocJicoqm4w', score=0.19051167368888855, published_date='2023-04-27', author='NFX', extract=None), Result(title='10 new AI unicorns flying high in 2022', url='https://venturebeat.com/ai/10-new-ai-unicorns-flying-high-in-2022/', id='i4k-4QKod9mMo2bi8m19bw', score=0.18090465664863586, published_date='2022-06-27', author='Sharon Goldman', extract=None), Result(title='The 13 most promising early-stage artificial-intelligence startups of 2022, according to VCs investing in companies building technical infrastructure and developing tools', url='https://www.businessinsider.com/13-most-promising-earlier-stage-ai-startups-this-year-2022-11', id='ZA52Zk-yVy9skxWZtxOSgg', score=0.1796971708536148, published_date='2022-11-17', author='Sindhu Sundar', extract=None), Result(title='What to Watch in AI | The Generalist', url='https://www.generalist.com/briefing/what-to-watch-in-ai-2', id='cmKJmULl_vK4V-gth6yzWg', score=0.17643707990646362, published_date='2023-03-26', author='Artwork byÂ', extract=None), Result(title='Hot AI startups in San Francisco (2022) | Best', url='https://www.scoop.it/topic/best/p/4137745212/2022/11/08/hot-ai-startups-in-san-francisco-2022', id='wjo6lznHL-VI7jBOsvuwzA', score=0.17351359128952026, published_date='2022-11-08', author='Dr Stefan Gruenwald', extract=None), Result(title='New and recently funded AI Startups', url='https://www.ai-startups.org/', id='M0Cgw6hYIbLBvU6y-9oEBg', score=0.17336121201515198, published_date=None, author=None, extract=None), Result(title='A Search Engine for Machine Intelligence', url='https://bellow.ai/', id='bdYc6hvHww_JvLv9k8NhPA', score=0.17326533794403076, published_date='2023-01-01', author=None, extract=None), Result(title='26 AI experts who left Google to start new companies in 2022 as machine learning ushers in a new era of lifelike AI', url='https://www.businessinsider.com/26-ai-machine-learning-experts-left-google-for-startups-2022-12', id='MKxSDXGxC155eyQLva1Ksg', score=0.16997841000556946, published_date='2022-12-26', author='Matthew Lynley', extract=None), Result(title='Discover AI Startups', url='https://appliedai.com/discover', id='e_SK0_agdSNfvbf0Xn_wPQ', score=0.1694592982530594, published_date='2023-01-01', author=None, extract=None), Result(title='Careers at Top AI Startups', url='https://aijobnetwork.com/', id='jEBgBMmwMnOsEDZkxOWBWA', score=0.1688486635684967, published_date='2023-01-01', author=None, extract=None)], api=<metaphor_python.api.Metaphor object at 0x10f092d10>)\u001b[0m\u001b[32;1m\u001b[1;3m\n",
|
||||
"Invoking: `get_contents` with `{'ids': ['pb0vypILvIakocJicoqm4w', 'i4k-4QKod9mMo2bi8m19bw', 'ZA52Zk-yVy9skxWZtxOSgg']}`\n",
|
||||
"\u001b[0m\u001b[36;1m\u001b[1;3mSearchResponse(results=[Result(title='A Search Engine for Machine Intelligence', url='https://bellow.ai/', id='bdYc6hvHww_JvLv9k8NhPA', score=0.19460266828536987, published_date='2023-01-01', author=None, extract=None), Result(title='Adept: Useful General Intelligence', url='https://www.adept.ai/', id='aNBppxBZvQRZMov6sFVj9g', score=0.19103890657424927, published_date='2000-01-01', author=None, extract=None), Result(title='HiOperator | Generative AI-Enhanced Customer Service', url='https://www.hioperator.com/', id='jieb6sB53mId3EDo0z-SDw', score=0.18549954891204834, published_date='2000-01-01', author=None, extract=None), Result(title='Home - Stylo', url='https://www.askstylo.com/', id='kUiCuCjJYMD4N0NXdCtqlQ', score=0.1837376356124878, published_date='2000-01-01', author=None, extract=None), Result(title='DirectAI', url='https://directai.io/?utm_source=twitter&utm_medium=raw_message&utm_campaign=first_launch', id='45iSS8KnJ9tL1ilPg3dL9A', score=0.1835256814956665, published_date='2023-01-01', author=None, extract=None), Result(title='Sidekick AI | Customer Service Automated', url='https://www.sidekickai.co/', id='nCoPMUtqWQqhUvsdTjJT6A', score=0.18215584754943848, published_date='2020-01-01', author=None, extract=None), Result(title='Hebbia - Search, Reinvented', url='https://www.hebbia.ai/', id='Zy0YaekZdd4rurPQKkys7A', score=0.1799020767211914, published_date='2023-01-01', author=None, extract=None), Result(title='AI.XYZ', url='https://www.ai.xyz/', id='A5c1ePEvsaQeml2Kui_-vA', score=0.1797989457845688, published_date='2023-01-01', author=None, extract=None), Result(title='Halist AI', url='https://halist.ai/', id='-lKPLSb4N4dgMZlTgoDvJg', score=0.17975398898124695, published_date='2023-03-01', author=None, extract=None), Result(title='Clone your best expert', url='https://airin.ai/', id='_XIjx1YLPfI4cKePIEc_bQ', score=0.17957791686058044, published_date='2016-02-12', author=None, extract=None)], api=<metaphor_python.api.Metaphor object at 0x104192140>)\u001b[0m\u001b[32;1m\u001b[1;3m\n",
|
||||
"Invoking: `get_contents` with `{'ids': ['bdYc6hvHww_JvLv9k8NhPA', 'aNBppxBZvQRZMov6sFVj9g', 'jieb6sB53mId3EDo0z-SDw', 'kUiCuCjJYMD4N0NXdCtqlQ', '45iSS8KnJ9tL1ilPg3dL9A', 'nCoPMUtqWQqhUvsdTjJT6A', 'Zy0YaekZdd4rurPQKkys7A', 'A5c1ePEvsaQeml2Kui_-vA', '-lKPLSb4N4dgMZlTgoDvJg', '_XIjx1YLPfI4cKePIEc_bQ']}`\n",
|
||||
"\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[0m\u001b[33;1m\u001b[1;3mGetContentsResponse(contents=[DocumentContent(id='pb0vypILvIakocJicoqm4w', url='https://www.nfx.com/post/generative-ai-hot-75-list', title='The AI Hot 75', extract='<div><div><p><em>The hottest up & comers in generative AI. Early-stage companies showing leading indicators of future greatness. Curated by NFX.</em></p>\\n<p></p>\\n<p>No doubt generative AI is extremely <a href=\"https://www.nfx.com/post/find-the-fast-moving-water\">fast-moving water</a>. But while media hype focuses on incumbents and household names, we’re doubling down on the “AI underground.”</p>\\n<p>The generative AI groundswell is disproportionately fueled by a dense network of exceptional, early-stage companies. We’ve seen it growing throughout San Francisco, in “Cerebral Valley” at NFX HQ, inside hacker houses, and via 100’s of meetings with up-and-coming AI founders.</p>\\n<p>After we open-sourced our <a href=\"https://www.nfx.com/post/generative-ai-tech-market-map\">Generative AI market map</a> a few months ago, we went to work analyzing this network for early indicators of future greatness. It is going to produce the next generation of unicorns, at a faster rate and at lower cost than any other startups before them.</p>\\n<p>Today we are making public our findings. Meet the <a href=\"https://www.nfx.com/post/generative-ai-hot-75-list?#AI-Hot-75\">AI Hot 75</a>.</p>\\n<h2><strong>Identifying the AI Hot 75 </strong></h2>\\n<p>Broadly speaking, we searched for leading indicators that an early-stage generative AI company has broken into the right networks and has found a “white hot center” (a highway to massive growth).</p>\\n<p>With those guiding principles in place, we gave preference to early-stage companies generally at the Seed and Series A stage. We narrowed the list according to: total amount raised, status of key investors, proximity to a geographical AI center of excellence, and “buzz” – which we imputed from various virality, traction, and WOM factors.</p>\\n<p>We finalized our selections based on in-network reputation –\\xa0i.e. if a company has been recommended or regarded by peers or experts in our network.</p>\\n<p>This list will look different from many that you’ve already seen. While some of the companies are household names already, most aren’t the biggest companies out there – yet.</p>\\n<p>Instead, these are the companies indicative of the next generation. The ones with notable momentum. The hot ones worth following.</p>\\n<h2><strong>AI Hot 75</strong></h2>\\n<p><em>In addition to using proprietary NFX data for this list, we also referred to Pitchbook, Crunchbase, our network of friends and founders, </em><a href=\"https://twitter.com/NFX/status/1624103283236425729\"><em>The NFX AI Social Club</em></a><em>, and used ChatGPT to stress test analysis and language as well. </em></p>\\n</div></div>'), DocumentContent(id='i4k-4QKod9mMo2bi8m19bw', url='https://venturebeat.com/ai/10-new-ai-unicorns-flying-high-in-2022/', title='10 new AI unicorns flying high in 2022', extract='<div><div>\\n\\t<article>\\n\\t<div>\\n\\t<div>\\n<p><em>Check out all the on-demand sessions from the Intelligent Security Summit <a href=\"https://avolio.swapcard.com/intelligentsecuritysummit2022/registrations/Start?utm_source=vb&utm_medium=boiler&utm_content=ondemand&utm_campaign=IS22_BoilerPlates\">here</a></em>.</p>\\n<hr />\\n</div><p>Technology venture capital deals may be <a href=\"https://www.wsj.com/articles/corporate-investors-fill-startup-funding-gap-as-vc-firms-pull-back-11655851713\">slowing down</a>, but investment in artificial intelligence (AI) companies continues to boom. Investments in AI research and applications are set to hit <a href=\"https://www.idc.com/getdoc.jsp?containerId=prUS47482321\">$500 billion</a> by 2024, according to research firm IDC, while PwC predicts AI will contribute <a href=\"https://www.pwc.com/gx/en/issues/data-and-analytics/publications/artificial-intelligence-study.html\">$15.7 trillion</a> to the global economy by 2030.\\xa0</p>\\n<p>So, it’s no surprise that among the 206 new 2022 “unicorns” – that is, privately held startups with a value of over $1 billion – a boatload are in artificial intelligence and machine learning.\\xa0</p>\\n<p>Here is a look at ten AI companies from the newest unicorn cohort that are soaring in 2022:\\xa0</p>\\n<h2><strong>Abnormal Security</strong></h2>\\n<p><strong>Business: </strong>Uses behavioral AI to fight email attacks</p>\\n<div>\\n <h3>Event</h3>\\n <div><p>Intelligent Security Summit On-Demand</p>\\n<p>Learn the critical role of AI & ML in cybersecurity and industry specific case studies. Watch on-demand sessions today.</p>\\n</div>\\n <p><a href=\"https://avolio.swapcard.com/intelligentsecuritysummit2022/registrations/Start?utm_source=vb&utm_medium=incontent&utm_content=ondemand&utm_campaign=IS22_InContent\">\\n Watch Here </a>\\n </p></div><p><strong>BaLine truncated
|
||||
"\n",
|
||||
"1. The AI Hot 75: This list, curated by NFX, showcases early-stage companies in generative AI that show leading indicators of future greatness. These companies are at the forefront of the generative AI groundswell. [Read more](https://www.nfx.com/post/generative-ai-hot-75-list)\n",
|
||||
"\u001b[0m\u001b[33;1m\u001b[1;3mGetContentsResponse(contents=[DocumentContent(id='bdYc6hvHww_JvLv9k8NhPA', url='https://bellow.ai/', title='A Search Engine for Machine Intelligence', extract=\"<div><div><h2>More Opinions</h2><p>Get responses from multiple AIs</p><p>Don't rely on a single source of truth, explore the full space of machine intelligence and get highly tailored results.</p></div></div>\"), DocumentContent(id='aNBppxBZvQRZMov6sFVj9g', url='https://www.adept.ai/', title='Adept: Useful General Intelligence', extract='<div><div><p>Useful <br />General <br />Intelligence</p></div>'), DocumentContent(id='jieb6sB53mId3EDo0z-SDw', url='https://www.hioperator.com/', title='HiOperator | Generative AI-Enhanced Customer Service', extract=\"<div><div><div><div><div><h2>Generative AI-Enhanced Customer Support Automation</h2><p>Flexible, Scalable Customer Support</p></div><div><p></p></div></div><p></p></div><div><div><p>Why HiOperator?</p><h2>Truly scalable customer service</h2><p>A digital-first customer service provider that changes all the rules of what's possible. Scalable. 100% US-Based. Effortless. HiOperator is the digital payoff.</p></div><p></p></div><div><div><p>Next-Gen Customer Service</p><h2>Scaling with HiOperator's Superagents</h2><p>HiOperator is only possible in the digital era. Our revolutionary software connects with your systems to empower our agents to learn quickly and deliver incredible accuracy. </p></div><div><div><p></p><div><h3>Train Us Once</h3><p>We handle all of the recruiting, hiring, and training moving forward. Never have to deal with another classroom retraining or head count headaches.</p></div></div><div><div><h3>Send Us Tickets</h3><p>We pull tickets automatically from your preferred CRM vendor into our custom system. You have full control over <strong>how</strong> and <strong>when</strong> we get tickets.</p></div><p></p></div><div><p></p><div><h3>Pay per resolution</h3><p>We charge for each conversation we solve. No onboarding fees. No hourly rates. Pay for what you use.</p></div></div></div></div><div><p>Customer Experience</p><h2>Insights &Â\\xa0News</h2></div><div><div><h2>Let's transform your customer service.</h2><p>We can onboard in a matter of days and we offer highly flexible contracts. Whether you need a large team to handle your support or some overflow assistance, getting started is easy.</p></div><p>We can onboard in a matter of days and we offer highly flexible contracts. Whether you need a large team to handle your support or some overflow assistance, getting started is easy.</p></div></div>\"), DocumentContent(id='kUiCuCjJYMD4N0NXdCtqlQ', url='https://www.askstylo.com/', title='Home - Stylo', extract='<div><div><header><div><p></p><h2>Stop angry customers from breaking support</h2><p></p></div></header><div><p></p><h2><em> </em><strong><em>â\\x80\\x9cWe solve 99 tickets perfectly </em>ð\\x9f\\x98\\x87<em> but the 1 we miss lands in the CEOâ\\x80\\x99s inbox </em>ð\\x9f\\x98«<em>â\\x80\\x9d<br /></em></strong></h2><p></p><div><p><strong>â\\x80\\x8d</strong>That 1 costly ticket breaks your process, metrics, and the will of your team. Angry customers make support teams less effective, which makes customers angrier in return.<strong><br />â\\x80\\x8d</strong><br />Stylo is AI that tells you where to most effectively spend your time to improve the customer experience. This leads to happier customers, employees, and reduces churn.</p><p>â\\x80\\x8d<strong>No setup, no learning curve, just plug it in and go.</strong></p></div></div><div><div><p></p><div><p>â\\x80\\x9cIâ\\x80\\x99m able to better manage the team because I can pinpoint gaps in the teamâ\\x80\\x99s knowledge or training, and find room for process improvements.â\\x80\\x9d</p><p></p></div></div></div></div>'), DocumentContent(id='45iSS8KnJ9tL1ilPg3dL9A', url='https://directai.io/?utm_source=twitter&utm_medium=raw_message&utm_campaign=first_launch', title='DirectAI', extract=\"<div><div><div><h2>Vision models without training data.<br /></h2><p>Build and deploy powerful computer vision models with plain language.<br />No code or training required.</p></div><div><h2>Fundamentally different.</h2><p>We use large language models and zero-shot learning to instantly build models that fit your description.</p><br /></div><div><div><p></p><h2>We're removing the last major barrier to creating custom models - <br />training data.</h2><p></p></div><div><table><colgroup></colgroup><thead><tr><th><p>Deploy and iterate in seconds with DirectAI</p></th></tr></thead><tbody><tr><td>• Don't spend time assembling training data.</td></tr><tr><td>• Don't pay a third party to label your data.</td></tr><tr><td>• Don't pay to train your model.</td></tr><tr><td>• Don't spend months finetuning your model's behavior.</td></tr></tbody></table></div></div><div><h2>Venture-backed.<p>Based in NYC.</p><p>We're changing how people use AI in the real world.</p><p>Come talk to us on .</p></h2></div></dLine truncated
|
||||
"\n",
|
||||
"2. 10 new AI unicorns flying high in 2022: This article highlights ten AI companies from the newest unicorn cohort that are soaring in 2022. One example is Abnormal Security, which uses behavioral AI to fight email attacks. [Read more](https://venturebeat.com/ai/10-new-ai-unicorns-flying-high-in-2022/)\n",
|
||||
"1. [Bellow AI](https://bellow.ai/): This startup provides a search engine for machine intelligence. It allows users to get responses from multiple AIs, exploring the full space of machine intelligence and getting highly tailored results.\n",
|
||||
"\n",
|
||||
"3. The 13 most promising early-stage artificial-intelligence startups of 2022: According to VCs investing in companies building technical infrastructure and developing tools, these 13 AI startups demonstrate the most potential. One example is OtterTune, a machine-learning-based platform to manage databases. [Read more](https://www.businessinsider.com/13-most-promising-earlier-stage-ai-startups-this-year-2022-11)\n",
|
||||
"2. [Adept AI](https://www.adept.ai/): Adept is focused on creating useful general intelligence.\n",
|
||||
"\n",
|
||||
"Please note that these are just a few examples, and there are many more AI agent startups out there.\u001b[0m\n",
|
||||
"3. [HiOperator](https://www.hioperator.com/): HiOperator offers generative AI-enhanced customer support automation. It provides scalable, digital-first customer service and uses its software to empower agents to learn quickly and deliver accurate results.\n",
|
||||
"\n",
|
||||
"4. [Stylo](https://www.askstylo.com/): Stylo uses AI to help manage customer support, identifying where to most effectively spend time to improve the customer experience.\n",
|
||||
"\n",
|
||||
"5. [DirectAI](https://directai.io/): DirectAI allows users to build and deploy powerful computer vision models with plain language, without the need for code or training.\n",
|
||||
"\n",
|
||||
"6. [Sidekick AI](https://www.sidekickai.co/): Sidekick AI is built to hold natural and dynamic conversations with customers, providing personalized service depending on the customer's needs.\n",
|
||||
"\n",
|
||||
"7. [Hebbia](https://www.hebbia.ai/): Hebbia is reinventing search with cutting-edge AI, retrieving every answer, even insights humans overlook.\n",
|
||||
"\n",
|
||||
"8. [AI.XYZ](https://www.ai.xyz/): AI.XYZ allows users to design their own AI, tackling information overload and providing support and inspiration throughout the day.\n",
|
||||
"\n",
|
||||
"9. [Halist AI](https://halist.ai/): Halist AI provides optimized access to ChatGPT, powered by OpenAI GPT-3 and GPT-4, on mobile.\n",
|
||||
"\n",
|
||||
"10. [Airin](https://airin.ai/): Airin clones how your top expert solves problems in as little as 2 hours, creating an AI companion for the rest of your team. It automates remote coaching for new hires and dramatically reduces time to productivity.\n",
|
||||
"\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
@@ -191,10 +198,10 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Here are some of the hottest AI agent startups and what they do:\\n\\n1. The AI Hot 75: This list, curated by NFX, showcases early-stage companies in generative AI that show leading indicators of future greatness. These companies are at the forefront of the generative AI groundswell. [Read more](https://www.nfx.com/post/generative-ai-hot-75-list)\\n\\n2. 10 new AI unicorns flying high in 2022: This article highlights ten AI companies from the newest unicorn cohort that are soaring in 2022. One example is Abnormal Security, which uses behavioral AI to fight email attacks. [Read more](https://venturebeat.com/ai/10-new-ai-unicorns-flying-high-in-2022/)\\n\\n3. The 13 most promising early-stage artificial-intelligence startups of 2022: According to VCs investing in companies building technical infrastructure and developing tools, these 13 AI startups demonstrate the most potential. One example is OtterTune, a machine-learning-based platform to manage databases. [Read more](https://www.businessinsider.com/13-most-promising-earlier-stage-ai-startups-this-year-2022-11)\\n\\nPlease note that these are just a few examples, and there are many more AI agent startups out there.'"
|
||||
"\"Here are some of the hottest AI agent startups and what they do:\\n\\n1. [Bellow AI](https://bellow.ai/): This startup provides a search engine for machine intelligence. It allows users to get responses from multiple AIs, exploring the full space of machine intelligence and getting highly tailored results.\\n\\n2. [Adept AI](https://www.adept.ai/): Adept is focused on creating useful general intelligence.\\n\\n3. [HiOperator](https://www.hioperator.com/): HiOperator offers generative AI-enhanced customer support automation. It provides scalable, digital-first customer service and uses its software to empower agents to learn quickly and deliver accurate results.\\n\\n4. [Stylo](https://www.askstylo.com/): Stylo uses AI to help manage customer support, identifying where to most effectively spend time to improve the customer experience.\\n\\n5. [DirectAI](https://directai.io/): DirectAI allows users to build and deploy powerful computer vision models with plain language, without the need for code or training.\\n\\n6. [Sidekick AI](https://www.sidekickai.co/): Sidekick AI is built to hold natural and dynamic conversations with customers, providing personalized service depending on the customer's needs.\\n\\n7. [Hebbia](https://www.hebbia.ai/): Hebbia is reinventing search with cutting-edge AI, retrieving every answer, even insights humans overlook.\\n\\n8. [AI.XYZ](https://www.ai.xyz/): AI.XYZ allows users to design their own AI, tackling information overload and providing support and inspiration throughout the day.\\n\\n9. [Halist AI](https://halist.ai/): Halist AI provides optimized access to ChatGPT, powered by OpenAI GPT-3 and GPT-4, on mobile.\\n\\n10. [Airin](https://airin.ai/): Airin clones how your top expert solves problems in as little as 2 hours, creating an AI companion for the rest of your team. It automates remote coaching for new hires and dramatically reduces time to productivity.\\n\""
|
||||
]
|
||||
},
|
||||
"execution_count": 18,
|
||||
"execution_count": 20,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -392,7 +399,7 @@
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
@@ -406,12 +413,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.1"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
|
||||
}
|
||||
"version": "3.10.0"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
Reference in new issue
Block a user