/* Global styles */

#topbar-cta-button {
  margin-left: 1rem;
}

#topbar-cta-button a {
  display: flex;
  align-items: center;
  padding: 0.375rem 1rem !important;
  gap: 0.5rem;
  background-color: #1C17FF;
  color: #fff !important;
  border-radius: 0.25rem;
  font-weight: 500;
  letter-spacing: 0.4px;
}

#topbar-cta-button a:hover {
  background-color: #030080 !important;
}


/* #topbar-cta-button span {
  border-radius: 4px;
  font-weight: 500;
  letter-spacing: 0.4px;
} */

/* #topbar-cta-button div > svg {
  display: none;
} */

/* inserting svg via :after isn't working for some reason, used js instead */
/* #topbar-cta-button div::after {
  content: url('data:image/svg+xml;utf8,<svg width="20" height="20" viewBox="0 0 20 20" fill="none" xmlns="http://www.w3.org/2000/svg"><g id="Icon Right"><path id="Vector" d="M8.08906 5L6.91406 6.175L10.7307 10L6.91406 13.825L8.08906 15L13.0891 10L8.08906 5Z" fill="white"/></g></svg>');
  content: "test";
  display: block;
  width: 20px;
  height: 20px;
  margin-left: 8px;
  background-image: url('data:image/svg+xml;utf8,<svg width="20" height="20" viewBox="0 0 20 20" fill="none" xmlns="http://www.w3.org/2000/svg"><g id="Icon Right"><path id="Vector" d="M8.08906 5L6.91406 6.175L10.7307 10L6.91406 13.825L8.08906 15L13.0891 10L8.08906 5Z" fill="white"/></g></svg>');
  background-color: #000000;
  background-size: contain;
  background-repeat: no-repeat;
  background-position: center;
} */


.documentation-link {
  color: #1c17ff;
  text-decoration: none;
}

.documentation-link:hover {
  color: #000000;
  /* Black color when hovering */
}

.custom-button {
  display: inline-block;
  padding: 2px 8px;
  background-color: #f1f1f1;
  color: #333;
  /* Text color */
  border: 1px solid #aaa;
  /* Border color */
  border-radius: 25px;
  /* Rounded borders */
  text-align: center;
  user-select: none;
  transition: background-color 0.3s ease;
  /* Smooth transition for background color */
}

/* Change the button color on hover (make it unclickable) */
.custom-button:hover {
  background-color: #1c17ff;
  color: #f1f1f1;
}

/* Adjust the width for the second column */
/* td:nth-child(2) {
  width: 200px; /* Adjust the width as per your requirement
} */

/* 
Add an announcement bar 
TODO: This can be version specific if you add a page-specific class/ID, but it doesn't seem to work for the OpenAI docs without rewriting the JSON
*/
/*  #navbar:before {
  background-color: #ff4c04;
  content: "The legacy version of the API, which required regional URLs for control plane operations, is deprecated as of April 15, 2024 and will be removed in a future, to be announced, release.";
  color: rgb(255, 255, 255);
  display: block;
  text-align: center;
  padding: 6px;
  font-size: 90%;
}
*/
/* Text color */
/* body {
  color: #121142 !important;
} */

/* Header */
#navbar {
  background: white;
  position: fixed;
  /* position: sticky !important; */
  /* top: 0 !important; */
}

#navbar-transition {
  border-bottom: 1px solid #e2e5e7;
}

#navbar .max-w-8xl {
  max-width: 100%;
}

/* Logo + "Docs" text + version select */
#navbar>div:first-of-type>div:first-of-type>div:first-of-type>div:first-of-type {
  flex: initial;
}

#navbar>div:first-of-type>div:first-of-type>div:first-of-type>div:first-of-type>a:first-of-type {
  flex: initial;
  display: flex;
}

#navbar img[alt="logo"] {
  max-width: 150px;
}

/* Version select */
[aria-haspopup="menu"] {
  border-radius: 0.25rem;
  border: 1px solid rgba(115, 143, 171, 0.50);
  background-color: transparent !important;
  color: #121142;
}

[aria-labelledby="headlessui-menu-button-:r0:"] {
  width: 11rem;
}

/* Right side nav container */
#navbar>div:first-of-type>div:first-of-type>div:first-of-type>div:nth-of-type(3) {
  flex: initial;
  margin-left: 0;
}

/* Prevent nav items from shrinking */
#navbar>div:first-of-type>div:first-of-type>div:first-of-type>div:nth-of-type(3)>nav {
  flex-shrink: 0;
}

/* nav links */
#navbar nav a {
  color: #121142;
  padding: 0.6rem 1rem;
  transition: background-color 250ms cubic-bezier(0.4, 0, 0.2, 1);
}

#navbar nav a:hover {
  background-color: rgba(27, 23, 245, 0.04);
  border-radius: 0.25rem;
}

#navbar nav ul li:not(:last-of-type) {
  margin-left: 0;
}

/* Hide dark mode toggle */
#navbar>div:first-of-type>div:first-of-type>div:first-of-type>div:nth-of-type(3)>div {
  display: none;
}

/* Second nav container */
/* Links */
#navbar a {
  color: #121142;
  margin: 0;
  padding-left: 0.875rem;
  padding-right: 0.875rem;
}

/* Selected links */
#navbar a.font-semibold {
  color: #1B17F5;
  border-bottom-width: 0.1875rem;
  border-color: #1B17F5;
}

#navbar div.absolute.bottom-0 {
  display: none;
}

/* Sidebar */
#sidebar {
  left: 0rem;
  padding-left: 3rem;
  background: white;
  border-right: 1px solid #e2e5e7;
  /* position: sticky; */
  /* flex-shrink: 0; */
  /* top: 0; */
}

#sidebar-content {
  padding-left: 2rem;
}

/* Sidebar headings and link color */
#sidebar-content h5,
#sidebar a {
  color: #121142;
}

/* Sidebar Introduction link */
#sidebar>div>ul>div:first-of-type>li:only-of-type {
  margin-left: 0;
}

#sidebar>div>ul>div:first-of-type>li:only-of-type>a {
  font-weight: 600;
}

/* Nav items */
#navigation-items>div>ul>li {
  margin-left: 0.75rem;
}

/* Selected nav items */
#navigation-items>div>ul>li a.font-semibold {
  color: #1B17F5;
  font-weight: 400;
  background-color: #3C72FF0A;
}

/* Main content area */
/* main > div:first-of-type > div:last-of-type > div:first-of-type {
  display: flex;
} */
@media screen and (min-width: 1024px) {
  #content-area>div:first-child:not(#header)>div.relative.w-full.flex.items-center.justify-center:first-child {
    margin-top: 7rem
  }
}


/* Content container */
/* #content-container {
  padding-left: 3.5rem !important;
} */
#content-container>div {
  padding-top: 10rem;
}

@media (min-width: 1024px) {
  #content-container>div {
    gap: 3rem;
  }

  #content-container #table-of-contents {
    padding-left: 0;
  }
}

/* Title eyebrow */
#header .eyebrow {
  text-transform: uppercase;
  color: #121142;
  font-size: 0.625rem;
  letter-spacing: 1px;
  line-height: 160%;
}

/* Hide empty eyebrow */
#header .eyebrow:empty {
  display: none;
}

/* Title container */
#header>div:first-of-type>div:nth-of-type(2) {
  margin-top: 0;
}

/* Title */
#header h1 {
  color: #121142;
}

/* Article text */
.prose h2,
.prose h3,
.prose h4,
.prose p {
  color: #121142;
}

.prose a {
  color: #1B17F5;
  font-weight: 400;
}

/* Overwrite tailwind max-width */
.max-w-8xl {
  max-width: 94.5rem;
}

.card {
  box-shadow: none;
  border: 1px solid #D8DDDF;
  border-radius: 0.25rem;
  transition: box-shadow 0.3s ease;
}

.card:hover {
  box-shadow: 0px 5px 5px -3px rgba(163, 169, 175, 0.20), 0px 8px 10px 1px rgba(163, 169, 175, 0.14), 0px 3px 14px 2px rgba(163, 169, 175, 0.12);
  border: 1px solid #D8DDDF !important;
}

.card>div {
  padding: 1.5rem;
}

.card h2,
.example-card h2 {
  font-size: 1.25rem;
}

.card p,
.example-card p {
  margin-top: 0.625rem;
  font-size: 0.875rem;
  color: #121142;
}

.card .eyebrow {
  font-size: 0.625rem;
  text-transform: uppercase;
  line-height: 160%;
  letter-spacing: 1px;
}

.card .integration-logo {
  width: 3.125rem;
  height: 3.125rem;
  display: flex;
  justify-content: center;
  align-items: center;
}

.card-grid {
  display: grid;
  gap: 1.5rem;
}

@media (min-width: 640px) {
  .card-grid {
    grid-template-columns: 1fr 1fr;
  }
}

@media (min-width: 1024px) {
  .card-grid {
    grid-template-columns: 1fr 1fr 1fr;
  }
}

.example-card {
  box-shadow: none;
  border: 1px solid #D8DDDF;
  border-radius: 0.25rem;
  transition: box-shadow 0.3s ease;
  padding: 1.5rem;
  display: flex;
  flex-direction: column;
  flex-grow: 1;
  background-color: #fff;
}

.example-card .arrow {
  margin-left: auto;
  margin-top: auto;
  opacity: 0;
  transition: opacity 0.3s ease;
}

.example-card:hover .arrow {
  opacity: 1;
}

.example-card:hover {
  box-shadow: 0px 5px 5px -3px rgba(163, 169, 175, 0.20), 0px 8px 10px 1px rgba(163, 169, 175, 0.14), 0px 3px 14px 2px rgba(163, 169, 175, 0.12);
  border: 1px solid #D8DDDF !important;
}

.example-card .tags {
  display: flex;
  flex-wrap: wrap;
  gap: 0.75rem;
  margin-top: 1.5rem;
}

.example-card .card-tag {
  border-radius: 1rem;
  background-color: rgba(115, 143, 171, 0.08);
  color: #121142;
  font-size: 0.8125rem;
  line-height: 138%;
  letter-spacing: 0.16px;
  padding: 0.1875rem 0.375rem;
  display: flex;
  gap: 0.375rem;
  align-items: center;
}

.example-card .vectors {
  color: #72788D;
  display: flex;
  flex-wrap: wrap;
  justify-content: space-between;
  gap: 1rem;
  font-size: 0.875rem;
  line-height: 150%;
  letter-spacing: 0.15px;
  padding-top: 2.875rem;
  margin-top: auto;
}

.examples-h2 {
  font-size: 1.25rem;
  margin-bottom: 1.5rem;
}

/* Integrations */
#integrations-banner {
  position: relative;
  margin-top: 7rem;
  height: 12.75rem;
  display: flex;
  flex-direction: column;
  justify-content: center;
  align-items: center;
  overflow: hidden;
  /* background: url('https://mintlify.s3-us-west-1.amazonaws.com/pinecone-2/images/background.png') no-repeat center center; */
  background-size: 90%;
  background-color: rgb(251, 251, 252);
  text-align: center;
  border-bottom: 1px solid #e2e5e7;
}

#integrations-banner h1 {
  color: #000000;
  font-size: 3rem;
}

#integrations-banner p {
  color: #000000;
  font-size: 1.25rem;
  opacity: 0.7;
  margin-top: 0.5rem;
}

/* Integrations related articles */
#related-articles {
  display: flex;
  flex-direction: column;
  width: 100%;
}

#related-articles h2 {
  color: #121142;
  font-size: 1.25rem;
  font-weight: 600;
  letter-spacing: 0.15px;
  line-height: 150%;
  margin-bottom: 1rem;
}

#related-articles a {
  padding: 1.0625rem 0;
  display: flex;
  align-items: flex-start;
  justify-content: space-between;
  gap: 1rem;
  color: #121142;
  font-size: 0.875rem;
  line-height: 150%;
  letter-spacing: 0.15px;
}

#related-articles a:not(:last-of-type) {
  border-bottom: 1px solid #D8DDDF;
}

#related-articles a:hover {
  opacity: 0.7;
}

#related-articles a>svg {
  flex-shrink: 0;
}

/* Integrations back button */
#back-button {
  display: flex;
  gap: 0.5rem;
  align-items: center;
  color: #121142 !important;
  font-size: 0.875rem;
  line-height: 150%;
  letter-spacing: 0.15px;
  margin-bottom: 1.5rem;
}

#back-button:hover {
  opacity: 0.7;
}

#back-button>svg {
  flex-shrink: 0;
}

/* Sample apps */

.sample-app {
  color: #121142;
}

.sample-app h2 {
  font-size: 2.125rem;
  font-weight: 600;
  line-height: 123.5%;
  letter-spacing: 0.25px;
}

.sample-app h2:not(:first-of-type) {
  margin: 4rem 0 0 0;
}

.sample-app h2:first-of-type {
  margin: 0;
}

.sample-app h3 {
  font-size: 1.25rem;
  font-weight: 600;
  line-height: 150%;
  letter-spacing: 0.15px;
  margin: 3rem 0 0 0;
}

.sample-app h4 {
  font-size: 0.875rem;
  font-weight: 700;
  line-height: 150%;
  letter-spacing: 0.15px;
  margin: 3rem 0 0 0;
}

.sample-app p,
.sample-app ul {
  margin: 1.5rem 0 0 0;
  font-size: 0.875rem;
  list-style-type: disc;
}

.sample-app li::before {
  display: none;
}

.sample-app li {
  padding-left: 0 !important;
  margin-left: 1.25rem;
}

.sample-app li::marker {
  color: #121142;
}

.sample-app-heading {
  display: flex;
  flex-direction: column;
  align-items: center;
  text-align: center;
}

.sample-app-heading .eyebrow {
  color: #121142;
  font-size: 0.625rem;
  line-height: 160%;
  letter-spacing: 1px;
  text-transform: uppercase;
}

.sample-app-heading h1 {
  color: #121142;
  margin: 0.5rem 0 0 0;
  font-size: 2.125rem;
  font-weight: 600;
  line-height: 123.5%;
  letter-spacing: 0.25px;
}

.sample-app-heading p {
  color: #121142;
  margin: 0.5rem 0 1.5rem 0;
  font-size: 1.25rem;
  font-weight: 600;
  line-height: 150%;
  letter-spacing: 0.15px;
}

/* Sample apps content area with sidebar */
.sample-app-split {
  display: flex;
  flex-direction: column;
  gap: 3rem;
}

.sample-app-split .sidebar a:not(.connect-with-pinecone) {
  font-size: 0.875rem;
  color: #121142;
  border-bottom: none;
}

.sample-app-split .toc-list {
  display: flex;
  flex-direction: column;
  gap: 1rem;
}

.sample-app-split .toc-list a.bold {
  font-weight: 700;
  margin-top: 0.5rem;
}

.sample-app-split>.content.no-margin>p:first-of-type {
  margin-top: 0 !important;
}

.connect-with-pinecone {
  border: 1px solid rgba(115, 143, 171, 0.50);
  border-radius: 0.25rem;
  padding: 0.5rem 1rem;
  display: inline-flex;
  align-items: center;
  gap: 0.5rem;
  font-size: 0.875rem;
  font-weight: 500;
  line-height: 1.5rem;
  letter-spacing: 0.4px;
  color: #121142 !important;
  text-decoration: none;
  align-self: flex-start;
}

@media (min-width: 1280px) {
  .sample-app-split {
    flex-direction: row;
  }

  .sample-app-split .content {
    overflow-x: auto;
  }

  .sample-app-split .sidebar {
    width: 20.625rem;
    flex-shrink: 0;
  }
}

/* Hacky codeblock targeting */
div[class*="bg-codeblock"].relative {
  background: #121142;
  border-radius: 0.25rem;
}

p>code {
  font-size: 0.75rem;
  line-height: 150%;
  letter-spacing: 0.5px;
  border-radius: 0.25rem;
  padding: 0.125rem 0.5rem;
  background-color: rgba(115, 143, 171, 0.08);
  color: #030080;
  border: none;
}

code .api-key.set {
  color: orange;
}

.pinecone-connect-connected {
  width: 100%;
  max-width: 31.25rem;
  background-color: rgb(255, 255, 255);
  transition: box-shadow 300ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;
  border-radius: 0.25rem;
  padding: 1.5rem;
  margin: 1.5rem 0;
  border: 1px solid rgb(224, 224, 224);
}

.pinecone-connect-connected img {
  height: 1.875rem;
  margin: 0;
}

.pinecone-connect-connected p {
  color: rgba(0, 0, 0, 0.87) !important;
}

.pinecone-connect-connected p:last-of-type {
  margin-top: 0.75rem;
}

.remove-api-key {
  display: flex;
  width: 100%;
  max-width: 31.25rem;
  margin-top: -1.25rem;
}

.remove-api-key>button {
  font-size: 0.8125rem;
  font-weight: 500;
  color: #1d4ed8;
  margin-left: auto;
}


/* Model Gallery */

.featured-card-container {
  position: relative;
  width: 100%;
  overflow: visible;
  overflow-x: auto;
  overflow-y: visible;
  margin-right: 0;
  /* Added to remove extra right margin */
}

.featured-model-cards {
  display: flex;
  transition: transform 1s ease-in-out;
  width: 100%;
  gap: 1rem;
  justify-content: space-between;
  overflow: visible;
  overflow-y: visible;
  margin-right: 0;
  /* Added to remove extra right margin */
}

@media (max-width: 768px) {
  .featured-model-cards {
    flex-direction: column;
  }
}

.outlined-button {
  display: flex;
  flex-direction: column;
  justify-content: center;
  align-items: center;
  width: 150px;
  height: 36px;
  padding: 4px;
  border-radius: 4px;
  border: 1px solid var(--Light-Secondary-Shades-50p, rgba(115, 143, 171, 0.5));
  color: #FFFFFF;
  text-decoration: none;
  font-size: 14px;
  letter-spacing: 0.4;
  text-align: center;
  color: #121142;
  font-weight: 500;
  transition: background-color 0.3s ease, border 0.3s ease, color 0.3s ease;
}

.outlined-button:hover {
  background-color: #3C72FF0A;
  border: 1px solid #1B17F5;
  color: #FFFFFF;
}


.control {
  position: absolute;
  top: 50%;
  transform: translateY(-50%);
  background-color: rgba(255, 255, 255, 0.7);
  border-radius: 50%;
  width: 40px;
  height: 40px;
  display: flex;
  align-items: center;
  justify-content: center;
  cursor: pointer;
  opacity: 0.5;
  transition: opacity 0.3s ease;
}

.control:hover {
  opacity: 1;
}

.prev-slide {
  left: 10px;
}

.next-slide {
  right: 10px;
}

.inference-text p {
  margin-top: 0rem;
}


/* Model page */
.model-page-card {
  padding: 1.5rem;
  border-radius: 0.25rem;
  border: 1px solid #D8DDDF;
  background: #FFF;
  margin-bottom: 2.5rem;
}

.model-page-card-title {
  display: flex;
  flex-wrap: wrap;
  gap: 1rem;
  align-items: center;
}

.model-page-card-title>h1 {
  font-size: 1.5rem;
  color: #121142;
}

.model-page-card-logo {
  width: 2.125rem;
  height: 2.125rem;
  flex-shrink: 0;
}

.model-page-card-logo>img {
  width: 100%;
  height: 100%;
  object-fit: contain;
}

.model-page-card-inference {
  border-radius: 1rem;
  border: 1px solid #D8DDDF;
  padding: 0.25rem 0.375rem 0.25rem 0.25rem;
  display: flex;
  align-items: center;
  gap: 0.375rem;
  font-size: 0.8125rem;
}

.model-page-card-stats {
  display: flex;
  gap: 1.5rem;
  flex-wrap: wrap;
  margin-top: 1rem;
}

.model-page-card-stats>div>span {
  font-size: 0.625rem;
  color: #72788D;
  letter-spacing: 0.2px;
  font-weight: 500;
}

.model-page-card-stats>div>p {
  font-size: 0.75rem;
  color: #121142;
  letter-spacing: 0.17px;
}

.model-page-card-stats>div.price {
  margin-left: auto;
}

.model-page-card-stats>div.price>p {
  margin-left: auto;
  font-weight: 600;
}

.model-page-tabs {
  display: flex;
  width: 100%;
  border-bottom: 1px solid #D8DDDF;
  margin-bottom: 2rem;
}

.model-page-tabs>button {
  padding: 0.5625rem 1rem;
  border-bottom: 1px solid transparent;
  color: #72788D;
  display: flex;
  align-items: center;
  gap: 0.375rem;
  font-weight: 500;
  letter-spacing: 0.4px;
}

.model-page-tabs>button>svg>path {
  fill: #72788D;
}

.model-page-tabs>button.active {
  border-bottom: 2px solid #1B17F5;
  color: #1B17F5;
}

.model-page-tabs>button.active>svg>path {
  fill: #1B17F5;
}

.model-page-playground {
  display: none;
}

.model-page-guides {
  display: flex;
  flex-direction: column;
  gap: 3rem;
}

.model-page-content {
  flex-shrink: 1;
  width: auto;
  max-width: 1050px;

  @media (max-width: 1500px) {
    max-width: 700px;
  }
}

.model-page-content> :first-child {
  margin-top: 0;
}

.model-page-content pre {
  white-space: pre-wrap;
}

.model-page-sidebar {
  width: 100%;
  flex-shrink: 1;
}

.model-page-sidebar .iframe-placeholder {
  height: 800px;
}

/* removing inline padding for now */
@media (min-width: 1280px) {
  .model-search-container {
    padding-inline: 0px;
  }
}

.model-page-sidebar-readmore {
  font-size: 0.875rem;
  font-style: normal;
  font-weight: 500;
  line-height: 150%;
  letter-spacing: 0.15px
}

.model-page-sidebar-readmore svg {
  margin-bottom: 2px;
}

.model-search-container {
  height: 1045px;

  @media (max-width: 768px) {
    height: 1200px;
  }
}

@media (min-width: 1080px) {
  .model-page-guides {
    flex-direction: row;
  }

  .model-page-sidebar {
    max-width: 20.6875rem;
    flex-shrink: 0;
  }

}

Pinecone Docs

Home

Guides

Reference

Examples

Models

Integrations

Troubleshooting

Releases

Sign up free

Status

Support

Log In

2024-10 (latest)

2024-07

2024-04

The `start_import` operation starts an asynchronous import of vectors from object storage into an index. 

For guidance and examples, see [Import data](https://docs.pinecone.io/guides/data/import-data).

Start import

Indicates how to respond to errors during the import process.

The request for the `start_import` operation.

ApiKeyAuth

The response for the `start_import` operation.

Overview

Pinecone Documentation

Database quickstart

Pinecone Database quickstart

Assistant quickstart

Pinecone Assistant quickstart

Key features

Build a RAG chatbot

Multitenancy

Implement multitenancy using namespaces

Semantic search

Image search

Multimodal search

Recommender

Threat detection

More examples

Glossary

Understanding indexes

Create an index

Migrate a pod-based index to serverless

View index information

Understanding backups and collections

Back up an index

Restore an index

Delete an index

Prevent index deletion

Tag an index

Use namespaces

Configure an index

Choose a pod type and size

Scale pod-based indexes

Understanding imports

Import data

Upsert data

Query data

Fetch data

Update data

Delete data

List record IDs

Target an index

Filter with metadata

Manage RAG documents

Understanding data freshness

Check data freshness

Understanding hybrid search

Encode sparse vectors

Upsert sparse-dense vectors

Query sparse-dense vectors

Use sample datasets

Use public Pinecone datasets

Create and load private datasets

Understanding Pinecone Inference

Generate embeddings

Rerank documents

Understanding Pinecone Assistant

Create an assistant

List assistants

Check assistant status

Update an assistant

Upload a file to an assistant

List the files in an assistant

Check assistant file status

Delete an uploaded file

Chat with an assistant

Delete an assistant

Understanding Evaluation API

Evaluate answers

Move to production

Performance tuning

Understanding security

Configure SSO with Okta

Configure CMEK

Connect to AWS PrivateLink

Manage storage integrations

Integrate with Amazon S3

Monitoring

Understanding organizations

Change your billing plan

Set up billing through AWS Marketplace

Set up billing through Azure Marketplace

Set up billing through GCP Marketplace

Understanding subscription status

Understanding cost

Monitor your usage

Manage cost

Manage organization members

Understanding projects

Create a project

Manage project members

Rename a project

Set a project pod limit

Introduction

API reference

Authentication

Errors

Versioning

API versioning

This operation returns a list of all indexes in a project.

List indexes

This operation deploys a Pinecone index. This is where you specify the measure of similarity, the dimension of vectors to be stored in the index, which cloud provider you would like to deploy with, and more.
  
For guidance and examples, see [Create an index](https://docs.pinecone.io/guides/indexes/create-an-index#create-a-serverless-index).


Describe an index

This operation deletes an existing index.

This operation configures an existing index. 

For serverless indexes, you can configure only index deletion protection and tags. For pod-based indexes, you can configure the pod size, number of replicas, tags, and index deletion protection. 

It is not possible to change the pod type of a pod-based index. However, you can create a collection from a pod-based index and then [create a new pod-based index with a different pod type](http://docs.pinecone.io/guides/indexes/create-an-index#create-an-index-from-a-collection) from the collection. For guidance and examples, see [Configure an index](http://docs.pinecone.io/guides/indexes/configure-an-index).

The `describe_index_stats` operation returns statistics about the contents of an index, including the vector count per namespace, the number of dimensions, and the index fullness.

Serverless indexes scale automatically as needed, so index fullness is relevant only for pod-based indexes.

For pod-based indexes, the index fullness result may be inaccurate during pod resizing; to get the status of a pod resizing process, use [`describe_index`](https://docs.pinecone.io/reference/api/control-plane/describe_index).

Get index stats

The `upsert` operation writes vectors into a namespace. If a new value is upserted for an existing vector ID, it will overwrite the previous value.

For guidance and examples, see [Upsert data](https://docs.pinecone.io/guides/data/upsert-data).

Upsert vectors

The `query` operation searches a namespace, using a query vector. It retrieves the ids of the most similar items in a namespace, along with their similarity scores.

For guidance and examples, see [Query data](https://docs.pinecone.io/guides/data/query-data).

Query vectors

The `fetch` operation looks up and returns vectors, by ID, from a single namespace. The returned vectors include the vector data and/or metadata.

For guidance and examples, see [Fetch data](https://docs.pinecone.io/guides/data/fetch-data).

Fetch vectors

The `update` operation updates a vector in a namespace. If a value is included, it will overwrite the previous value. If a `set_metadata` is included, the values of the fields specified in it will be added or overwrite the previous value.

For guidance and examples, see [Update data](https://docs.pinecone.io/guides/data/update-data).

Update a vector

The `delete` operation deletes vectors, by id, from a single namespace.

For guidance and examples, see [Delete data](https://docs.pinecone.io/guides/data/delete-data).

Delete vectors

The `list` operation lists the IDs of vectors in a single namespace of a serverless index. An optional prefix can be passed to limit the results to IDs with a common prefix.

By default, `list` returns up to 100 IDs per page in sorted order (bitwise "C" collation). If the `limit` parameter is set, `list` returns up to that number of IDs instead. Whenever there are additional IDs to return, the response also includes a `pagination_token` that you can use to get the next batch of IDs. When the response does not include a `pagination_token`, there are no more IDs to return.

For guidance and examples, see [List record IDs](https://docs.pinecone.io/guides/data/list-record-ids).

**Note:** `list_vectors` is supported only for serverless indexes.

List vector IDs

The `list_imports` operation lists all recent and ongoing import operations. 

By default, `list_imports` returns up to 100 imports per page. If the `limit` parameter is set, `list` returns up to that number of imports instead. Whenever there are additional IDs to return, the response also includes a `pagination_token` that you can use to get the next batch of imports. When the response does not include a `pagination_token`, there are no more imports to return.

For guidance and examples, see [Import data](https://docs.pinecone.io/guides/data/import-data).

List imports

The `describe_import` operation returns details of a specific import operation. 

For guidance and examples, see [Import data](https://docs.pinecone.io/guides/data/import-data).

Describe an import

The `cancel_import` operation cancels an import operation if it is not yet finished. It has no effect if the operation is already finished. 

For guidance and examples, see [Import data](https://docs.pinecone.io/guides/data/import-data).

Cancel an import

This operation returns a list of all collections in a project.
Serverless indexes do not support collections.


List collections

This operation creates a Pinecone collection.
  
Serverless indexes do not support collections.


Create a collection

This operation gets a description of a collection.
Serverless indexes do not support collections.


Describe a collection

This operation deletes an existing collection.
Serverless indexes do not support collections.


Delete a collection

The `list` operation lists the IDs of vectors in a single namespace of a serverless index. An optional prefix can be passed to limit the results to IDs with a common prefix.

`list` returns up to 100 IDs at a time by default in sorted order (bitwise "C" collation). If the `limit` parameter is set, `list` returns up to that number of IDs instead. Whenever there are additional IDs to return, the response also includes a `pagination_token` that you can use to get the next batch of IDs. When the response does not include a `pagination_token`, there are no more IDs to return.

For guidance and examples, see [List record IDs](https://docs.pinecone.io/guides/data/list-record-ids).

**Note:** `list` is supported only for serverless indexes.

This operation deploys a Pinecone index. This is where you specify the measure of similarity, the dimension of vectors to be stored in the index, which cloud provider you would like to deploy with, and more.

For guidance and examples, see [Create an index](https://docs.pinecone.io/guides/indexes/create-an-index#create-a-serverless-index).


This operation configures the pod size and number of replicas for a pod-based index.

It is not possible to change the pod type of an index. However, you can create a collection from an index and then [create a new index with a different pod type](http://docs.pinecone.io/guides/indexes/create-an-index#create-an-index-from-a-collection) from the collection.

This operation returns a list of all collections in a project.

Serverless indexes do not support collections.


This operation creates a Pinecone collection.

Serverless indexes do not support collections.


This operation gets a description of a collection.

Serverless indexes do not support collections.


This operation deletes an existing collection.

Serverless indexes do not support collections.


Generate embeddings for input data.

For guidance and examples, see [Generate embeddings](https://docs.pinecone.io/guides/inference/generate-embeddings).

Embed data

Rerank documents according to their relevance to a query.

For guidance and examples, see [Rerank documents](https://docs.pinecone.io/guides/inference/rerank).

The `list_assistants` endpoint returns a [list of all assistants](https://docs.pinecone.io/guides/assistant/list-assistants) in a project.

The `create_assistant` endpoint [creates a Pinecone Assistant](https://docs.pinecone.io/guides/assistant/create-assistant). This is where you specify the underlying training model, which cloud provider you would like to deploy with, and more.

The `get_assistant` endpoint [gets the status](https://docs.pinecone.io/guides/assistant/check-assistant-status) of an assistant.

The `update_assistant` endpoint [updates an existing assistant](https://docs.pinecone.io/guides/assistant/update-assistant). You can modify the assistant's instructions and metadata.

The `delete_assistant` endpoint [deletes an existing assistant](https://docs.pinecone.io/guides/assistant/delete-assistant).

The `list_files` endpoint returns a [list of all files in an assistant](https://docs.pinecone.io//guides/assistant/list-files), with an option to filter files with metadata.

List Files

The `upload_file` endpoint [uploads a file](https://docs.pinecone.io/guides/assistant/upload-file) to the specified assistant.

Upload file to assistant

The `describe_file` endpoint provides the [current status and metadata of a file](https://docs.pinecone.io/guides/assistant/check-file-status) uploaded to an assistant.

Describe a file upload

The `delete_file` endpoint [deletes an uploaded file](https://docs.pinecone.io/guides/assistant/delete-file) from an assistant.

The `chat_assistant` operation allows you to [chat with an assistant](https://docs.pinecone.io/guides/assistant/chat-with-assistant) and get back citations in structured form. 

This is the recommended way to chat with an assistant, as it offers more functionality and control over the assistant's responses and references than the `chat_completion_assistant` operation.

The `chat_completion_assistant` endpoint is used to [chat with an assistant](https://docs.pinecone.io/guides/assistant/chat-with-assistant). This endpoint is based on the OpenAI Chat Completion API, a commonly used and adopted API. 

It is useful if you need inline citations or OpenAI-compatible responses, but has limited functionality compared to the [`chat_assistant`](https://docs.pinecone.io/reference/api/assistant/chat_assistant) endpoint.

Chat through an OpenAI-compatible interface

The `metrics_alignment` endpoint [evaluates](https://docs.pinecone.io/guides/assistant/understanding-evaluation) the correctness, completeness, and alignment of a generated answer with respect to a question and a ground truth answer. The correctness and completeness are evaluated based on the precision and recall of the generated answer with respect to the ground truth answer facts. Alignment is the harmonic mean of correctness and completeness.

Evaluate an answer

Python SDK

Node.js SDK

Java SDK

Go SDK

.NET SDK

Rust SDK

Pinecone datasets

Pinecone text client

Spark-Pinecone connector

Serverless architecture

Pod-based architecture

Object identifiers

Quotas and limits

Known limitations

Notebooks

Sample apps

Reference architectures

Pinecone integrations enable you to build and deploy AI applications faster and more efficiently. Integrate Pinecone with your favorite frameworks, data sources, and infrastructure providers.

APIs

Database

Inference

Assistant

SDKs

Tools

Architecture

Miscellaneous

Start import

Authorizations

Body

Response