From d3a34971c1af0c4fd6bc17e1e296c36e3ca8d787 Mon Sep 17 00:00:00 2001 From: Paul Wozniczka <25128922+pwoznic@users.noreply.github.com> Date: Wed, 23 Aug 2023 12:57:39 -0500 Subject: [PATCH] Update H1/H2 headings throughout (#78) * Update About URL and add link to Vectara's Discord channel. Update the About link to correct the 404 error. Then add a Social Media link to Vectara's Discord channel. * Update file_upload.md Add doc_meta example and update curl command syntax with single quotes around URL * Update file_upload.md Update doc_metadata example * Update file_upload.md Fix example for doc_meta * Update indexing topics Updated a few statements based on team discussion around indexing * Update spacing 80 char spacing * Add warning about keeping keys and tokens private Users need to be careful so that they do not accidentally share their keys or tokens in public channels. I added this note to three topics that discuss API keys and OAuth tokens. * Update spacing Updated spacing to resolve conflict * Update introduction and add new topic Update information about the Vectara platform along with information about common use cases Update sidebar to reflect changes * Fix H1 headings Updated H1 headings to be H2 or H3 where appropriate and also fixed some typos * Update topics on feedback Updated headings based on feedback --------- Signed-off-by: Paul Wozniczka <25128922+pwoznic@users.noreply.github.com> --- www/docs/api-reference/auth-apis/api-keys.md | 5 ++-- www/docs/api-reference/auth-apis/oauth.md | 4 +-- .../indexing-apis/deleting_documents.md | 2 +- .../indexing-apis/file-upload/file_formats.md | 6 ++--- .../file-upload/supported_file_formats.md | 14 +++++------ .../api-reference/indexing-apis/indexing.md | 2 +- www/docs/api-reference/overview.md | 8 +++--- .../api-reference/protobuf-definitions.md | 2 +- www/docs/api-reference/rest.md | 6 ++--- .../search-apis/batched-queries.md | 6 ++--- .../search-apis/exact-boolean-text-matches.md | 4 +-- .../app-authn-authz/authorization.md | 4 +-- .../app-authn-authz/create_api_keys.md | 10 +++++--- www/docs/common-use-cases/batched-queries.md | 4 +-- .../built_in_filterable_metadata.md | 6 ++--- .../data_encryption.md | 6 ++--- .../keeping-your-data-private/textless.md | 16 ++++++------ .../question-answer/overview.md | 6 ++--- .../recommendation-systems/overview.md | 14 ++++++----- www/docs/console-ui/manage_user.md | 4 +-- www/docs/use-case-exploration.md | 25 +++++++++---------- www/docs/welcome.md | 2 +- 22 files changed, 81 insertions(+), 75 deletions(-) diff --git a/www/docs/api-reference/auth-apis/api-keys.md b/www/docs/api-reference/auth-apis/api-keys.md index 3fae4b0fe..2e1eb893d 100644 --- a/www/docs/api-reference/auth-apis/api-keys.md +++ b/www/docs/api-reference/auth-apis/api-keys.md @@ -7,7 +7,7 @@ sidebar_label: API Keys API Keys can be used for querying and indexing operations, but cannot at this time be used for administrative operations such as creating or deleting corpora. -# Creating an API Key +## Create an API Key Go to [https://console.vectara.com/console/api-keys](https://console.vectara.com/console/api-keys) to create a new API key. API Keys can be scoped either to be query-only or both query and index. It's recommended that you choose the most limited scope @@ -22,7 +22,8 @@ organizationally "expensive." In general, it's recommended that you use ::: -# Use an API Key +## Use an API Key + To use an API key in a request, you need to pass in `x-api-key` as an HTTP header. diff --git a/www/docs/api-reference/auth-apis/oauth.md b/www/docs/api-reference/auth-apis/oauth.md index c30bd0242..2ecdf6937 100644 --- a/www/docs/api-reference/auth-apis/oauth.md +++ b/www/docs/api-reference/auth-apis/oauth.md @@ -28,12 +28,12 @@ OAuth 2.0 has several advantages over API keys or simple usernames/passwords: ::: -# Creating an application client +## Create an application client Go to [https://console.vectara.com/console/authentication/app-client](https://console.vectara.com/console/authentication/app-client) to create a new application client. Most applications will want to use the `Client Credentials` grant. -# Obtain a JWT Token +## Obtain a JWT Token Before continuing, you'll need the OAuth 2.0 token endpoint. You can obtain that by navigating to the [Authentication page](https://console.vectara.com/authentication) and then selecting the App Client tab. Append `/oauth2/token` to this URL and diff --git a/www/docs/api-reference/indexing-apis/deleting_documents.md b/www/docs/api-reference/indexing-apis/deleting_documents.md index b576201f6..58f823122 100644 --- a/www/docs/api-reference/indexing-apis/deleting_documents.md +++ b/www/docs/api-reference/indexing-apis/deleting_documents.md @@ -44,7 +44,7 @@ retry may not succeed. - `UNAVAILABLE`: The service is temporarily unavailable, and the operation should be retried, preferably with a backoff. Note that the deletion operation is idempotent, so it is fine to re-apply. -### Example +### Delete a Document Example The code snippet below illustrates how to delete a document from a corpus. For information on how to get the call credentials and metadata, please consult diff --git a/www/docs/api-reference/indexing-apis/file-upload/file_formats.md b/www/docs/api-reference/indexing-apis/file-upload/file_formats.md index 88cb3a38f..de94fb7e3 100644 --- a/www/docs/api-reference/indexing-apis/file-upload/file_formats.md +++ b/www/docs/api-reference/indexing-apis/file-upload/file_formats.md @@ -13,7 +13,7 @@ to individual sections within it. Below is a sample document in each format. -## JSON +## Sample JSON Document ```json { @@ -44,7 +44,7 @@ Below is a sample document in each format. } ``` -## Pbtxt +## Sample Pbtxt Document ``` document_id: "selected-works-of-shakespeare" @@ -69,7 +69,7 @@ section { } ``` -## Python +## Sample Python Document For reference, these documents were output by the following Python program: diff --git a/www/docs/api-reference/indexing-apis/file-upload/supported_file_formats.md b/www/docs/api-reference/indexing-apis/file-upload/supported_file_formats.md index bb959487e..fbb7b9095 100644 --- a/www/docs/api-reference/indexing-apis/file-upload/supported_file_formats.md +++ b/www/docs/api-reference/indexing-apis/file-upload/supported_file_formats.md @@ -6,7 +6,7 @@ title: Supported File Types import {Config} from '@site/docs/definitions.md'; import {vars} from '@site/static/variables.json'; -## Binary file types +## Raw document types The upload endpoint supports several raw document types. Vectara extracts text from these documents and sections them as best it can. This provides a @@ -20,19 +20,19 @@ types are supported: - Microsoft Word (`doc`, `docx`). - Microsoft Powerpoint (`ppt`, `pptx`). - Text files (`txt`). -- HTML files. -- LXML files. -- RTF files. -- ePUB files. +- HTML files (`.html`). +- LXML files (`.lxml`). +- RTF files (`.rtf`). +- ePUB files (`.epub`). - Email files conforming to RFC 822. -## Semi-structured +## Semi-structured documents In addition, the [upload endpoint](/docs/api-reference/indexing-apis/file-upload/file-upload) supports sending semi-structured documents through this endpoint that reflect a `Document` proto message. Those can be sent in the following formats: -- `pb`: Contains binary serialized `Document` proto message. +- `pb`: Contains binary serialized `Document` proto message. - `pbtxt`: Contains `Document` proto message in proto text format. diff --git a/www/docs/api-reference/indexing-apis/indexing.md b/www/docs/api-reference/indexing-apis/indexing.md index 7f1cec50f..646e024f6 100644 --- a/www/docs/api-reference/indexing-apis/indexing.md +++ b/www/docs/api-reference/indexing-apis/indexing.md @@ -64,7 +64,7 @@ message IndexDocumentResponse { } ``` -### Document +### Document Definition in Vectara A document is a piece of coherent textual matter. It defines an ID, **document_id**, which must be unique among all the documents in diff --git a/www/docs/api-reference/overview.md b/www/docs/api-reference/overview.md index e5b5afd78..c303ff34d 100644 --- a/www/docs/api-reference/overview.md +++ b/www/docs/api-reference/overview.md @@ -6,11 +6,11 @@ sidebar_label: API Overview import {Config} from '@site/docs/definitions.md'; -Everything in is driven by APIs. This page serves +Everything in is driven by APIs. This page serves as an overview of the APIs and how to navigate this documentation to use those APIs. -# gRPC and REST +## gRPC and REST APIs Almost every API has both a [gRPC](https://en.wikipedia.org/wiki/GRPC) and a REST(https://en.wikipedia.org/wiki/Representational_state_transfer) endpoint. The 1 exception to this is the [File Upload](/docs/api-reference/indexing-apis/file-upload/file-upload) @@ -23,11 +23,11 @@ gRPC has several advantages over REST: However, we include REST APIs as there's a lot of developer tooling around REST APIs and some organizations still struggle with using HTTP/2.0 due to firewalls. -## REST +### REST API If you'd like more details about how to use our REST APIs, including details on our OpenAPI specification and services, a good place to start is the [REST](rest) page. -## gRPC +### gRPC API If you'd like more details about how to use our gRPC APIs, including details on how to generate strongly typed clients, see our [gRPC](protobuf-definitions) page. \ No newline at end of file diff --git a/www/docs/api-reference/protobuf-definitions.md b/www/docs/api-reference/protobuf-definitions.md index 33b27407b..206f68eb1 100644 --- a/www/docs/api-reference/protobuf-definitions.md +++ b/www/docs/api-reference/protobuf-definitions.md @@ -37,7 +37,7 @@ proto $ curl -s -o ext/google/api/http.proto --create-dirs \ https://raw.githubusercontent.com/googleapis/googleapis/master/google/api/http.proto ``` -## Examples +## Example Protocol Buffers The [Quickstart Examples](https://github.com/vectara/getting-started) GitHub repository has examples of connecting via gRPC in a variety of languages. diff --git a/www/docs/api-reference/rest.md b/www/docs/api-reference/rest.md index eb67bca3b..4bfec16f5 100644 --- a/www/docs/api-reference/rest.md +++ b/www/docs/api-reference/rest.md @@ -9,7 +9,7 @@ import {Config} from '@site/docs/definitions.md'; While gRPC provides low latency and excellent scalability, in some scenarios it may be simpler to integrate using REST APIs. -# API Formatting Guidelines +## API Formatting Guidelines All of the APIs can be found at https:///<version>/<api-endpoint>ee The API endpoints are outlined in the various subsections of this API Reference @@ -23,13 +23,13 @@ from the protobuf definitions to REST is: - API parameters can be sent in either `camelCase` or lowercase with `underscores`. For example, you could submit either `numResults` or `num_results` in the Search API - JSON responses are always returned in `camelCase` form -# Authentication +## API Authentication All APIs are authenticated. Indexing and Search APIs can be authenticated via [API Keys](/docs/common-use-cases/app-authn-authz/api-keys) however, Admin actions (creating/deleting corpora) must be done via [OAuth 2.0](/docs/api-reference/auth-apis/oauth-2). -# API Playground and OpenAPI Specifications +## API Playground and OpenAPI Specifications You can find up-to-date OpenAPI specifications at [https://docs.vectara.com/vectara-oas.yaml](https://docs.vectara.com/vectara-oas.yaml). These are automatically derived from the gRPC protobuf definitions as well. diff --git a/www/docs/api-reference/search-apis/batched-queries.md b/www/docs/api-reference/search-apis/batched-queries.md index 54d792b86..e11e826b8 100644 --- a/www/docs/api-reference/search-apis/batched-queries.md +++ b/www/docs/api-reference/search-apis/batched-queries.md @@ -38,10 +38,10 @@ separate query for billing purposes. ::: -# Responses +## Responses -When you a query , you get back an array oof results -This is to assist in using a +When you a query , you get back an array of results. +This array is to assist in using [Batched Query](/docs/api-reference/search-apis/batched-queries.md), ```jsx diff --git a/www/docs/api-reference/search-apis/exact-boolean-text-matches.md b/www/docs/api-reference/search-apis/exact-boolean-text-matches.md index 3d8d47bc5..ada4d6f71 100644 --- a/www/docs/api-reference/search-apis/exact-boolean-text-matches.md +++ b/www/docs/api-reference/search-apis/exact-boolean-text-matches.md @@ -15,7 +15,7 @@ term was absent from Vectara's training data (e.g. product SKUs) - Incorporate typical keyword modifiers like a `NOT` function, exact phrase matching, and wildcard prefixes of terms -# Enabling Exact and Boolean Text Matching +## Enable Exact and Boolean Text Matching By default, the exact and Boolean text matching is disabled and only neural retrieval is used. You can enable the feature by specifying a value, `lambda`, at query time. This value can range from `0` to `1` (inclusive). @@ -34,7 +34,7 @@ the scores of the results of the two different scoring models. Users often see best results by setting this value somewhere between 0.01 and 0.1, and we typically recommend users start experimentation with a value of 0.025. -# Syntax +## Syntax Interpretation When interpreting query strings, Vectara treats the following syntax specially. Words that are quoted must match exactly in that order. So, for example, the diff --git a/www/docs/common-use-cases/app-authn-authz/authorization.md b/www/docs/common-use-cases/app-authn-authz/authorization.md index a1a91def4..d728a91c5 100644 --- a/www/docs/common-use-cases/app-authn-authz/authorization.md +++ b/www/docs/common-use-cases/app-authn-authz/authorization.md @@ -14,10 +14,10 @@ identity by presenting a valid JWT token. Even entities that lack explicit roles may still be able to perform operations on the platform through the use of **default permissions**. -These concepts are explained in further detail in the sections below. - ## Roles +This section explains these concepts in further detail: + ### Account Level Roles - **Owner** is initially granted to whoever created the account. It grants diff --git a/www/docs/common-use-cases/app-authn-authz/create_api_keys.md b/www/docs/common-use-cases/app-authn-authz/create_api_keys.md index 872851806..daf8fcc63 100644 --- a/www/docs/common-use-cases/app-authn-authz/create_api_keys.md +++ b/www/docs/common-use-cases/app-authn-authz/create_api_keys.md @@ -26,7 +26,7 @@ Administrative actions cannot be performed through these keys. The remainder of this guide walks you through managing and using the API Keys. -## Creating a Key +## Create an API Key If you have the necessary permissions you'll see the `API Keys` in the sidebar. Click on it and you'll see the following page @@ -51,7 +51,7 @@ You can now start using the key. ::: -## Using a Key +## Use an API Key To use an API key, pass it using the `x-api-key` header request. @@ -147,7 +147,9 @@ END ## Management -### Disable and Enable +This section describes how to manage API keys. + +### Disable and Enable API Keys To temporarily disable access to an API key, begin by visiting the API Keys screen. Select disable by clicking on the action menu (three dots) of the key @@ -160,7 +162,7 @@ It will take around a minute for query requests using this key to be blocked. Once disabled, a key can be reenabled through the action menu. It will take a minute or two before it can serve query traffic again. -### Delete +### Delete API Keys A key may be permanently deleted through its action menu. Proceed with caution, once deleted, there is no way to undelete it, and all external systems that diff --git a/www/docs/common-use-cases/batched-queries.md b/www/docs/common-use-cases/batched-queries.md index 54d792b86..f99de6d9a 100644 --- a/www/docs/common-use-cases/batched-queries.md +++ b/www/docs/common-use-cases/batched-queries.md @@ -38,9 +38,9 @@ separate query for billing purposes. ::: -# Responses +## Responses -When you a query , you get back an array oof results +When you a query , you get back an array of results This is to assist in using a [Batched Query](/docs/api-reference/search-apis/batched-queries.md), diff --git a/www/docs/common-use-cases/filtering-by-metadata/built_in_filterable_metadata.md b/www/docs/common-use-cases/filtering-by-metadata/built_in_filterable_metadata.md index 9eb004078..7a1469e0a 100644 --- a/www/docs/common-use-cases/filtering-by-metadata/built_in_filterable_metadata.md +++ b/www/docs/common-use-cases/filtering-by-metadata/built_in_filterable_metadata.md @@ -6,13 +6,13 @@ title: Default Filterable Metadata import {Config} from '@site/docs/definitions.md'; A few pieces of metadata are filterable out of the box, as they're very -useful in a variety of situations. This page describes these. +useful in a variety of situations. This page describes these. Note that you can set up additional fields to filter on by setting up [filter attributes](/docs/api-reference/admin-apis/create-corpus#filter-attribute) on a corpus. -## part.lang +## `part.lang` field Each section of a document is evaluated for its language at index time and the `part.lang` field is added with a 3-character lower-case language code ([ISO 639-2](https://en.wikipedia.org/wiki/List_of_ISO_639-2_codes)). For @@ -24,7 +24,7 @@ Valid filter expressions for this would be something like: * `part.lang = 'deu'` * `part.lang = 'eng' OR part.lang = 'deu'` -## part.is_title +## `part.is_title` field When adding content, will add a special Boolean field to indicate whether the field is a title field or not. This is useful for a few different cases depending on how you model your data. For example, diff --git a/www/docs/common-use-cases/keeping-your-data-private/data_encryption.md b/www/docs/common-use-cases/keeping-your-data-private/data_encryption.md index c6fa088a5..d31bd31dc 100644 --- a/www/docs/common-use-cases/keeping-your-data-private/data_encryption.md +++ b/www/docs/common-use-cases/keeping-your-data-private/data_encryption.md @@ -90,7 +90,7 @@ The key should look like the following: The final step to creating the AWS KMS key to finish the key creation. -## Attach your key to your account +## Attach your AWS KMS key to your account In order to get to use your key, you must contact Support. Send us the ARN for the KMS key you created (starting with `arn:aws:kms:us-west-2`). @@ -99,11 +99,11 @@ The team will set the configuration up for you. In the future, you will be able to set the ARN on the Console and these instructions will be updated. -## How does it work +## How the encryption key works Once your AWS KMS key is configured in the platform, when encrypting your document text or metadata, will connect to your KMS service to generate an encryption key. The encryption key provided by the KMS is stored in-memory and used to encrypt and decrypt your data. In-memory key -will expire every hour. In turn, every hour will +will expire every hour. In turn, every hour will ask your AWS KMS to generate that encryption key again. diff --git a/www/docs/common-use-cases/keeping-your-data-private/textless.md b/www/docs/common-use-cases/keeping-your-data-private/textless.md index 53a121f26..dbc29f018 100644 --- a/www/docs/common-use-cases/keeping-your-data-private/textless.md +++ b/www/docs/common-use-cases/keeping-your-data-private/textless.md @@ -8,13 +8,15 @@ import Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem'; import {Config} from '@site/docs/definitions.md'; -## Textless When you create a corpus [via the API](/docs/api-reference/admin-apis/create-corpus) or the [UI](/docs/console-ui/creating-a-corpus), you will have the option to create it -and "don't store the text," also known as a "textless" mode. When this is -enabled, several things happen in the platform. This document talks about when -it's appropriate to enable textless, what happens on the platform, and what -benefits and limitations it brings. +and "don't store the text," also known as a "textless" mode. + +## Textless Mode + +When you enable textless mode, several things happen in the platform. +Let's look at when it's appropriate to enable textless, what happens on the +platform, and what benefits and limitations it brings. ## What happens when textless is enabled When you enable `textless` on a corpus, discards @@ -28,7 +30,7 @@ retrieve the document from a separate system of record based on the ID to show it and also allows to perform any metadata-based filtering on the document. -## Use cases +### Textless mode use cases One use case for `textless` is when you have very sensitive text content. By enabling this feature, the text content becomes unrecoverable to or to any user that manages to query for and @@ -38,7 +40,7 @@ In general, this feature is optimal for use cases where the cost of any information leakage is very high. Note that does [encrypt documents](encryption) -## Limitations +### Limitations Currently, the [reranking](/docs/api-reference/search-apis/reranking) capability relies on the text being stored. As a result, attempting to rerank search results on any corpora where text storage has been turned off will not work at this time. \ No newline at end of file diff --git a/www/docs/common-use-cases/question-answer/overview.md b/www/docs/common-use-cases/question-answer/overview.md index 705dd957f..caefd0b33 100644 --- a/www/docs/common-use-cases/question-answer/overview.md +++ b/www/docs/common-use-cases/question-answer/overview.md @@ -16,7 +16,7 @@ build very tight controls for the types of questions users can ask and get authoritative answers to. These can be great for building things like RFP-answering systems for employees and FAQ lookups for customers. -# Formatting data for indexing +## Format data for indexing When you send data to for this use case, we recommend that you index the question in the `title` field and the answer to that question in the text content. For example: @@ -37,7 +37,7 @@ that question in the text content. For example: } ``` -# Querying for similar questions +## Query for similar questions Suppose you wanted to find the answer to a question related to this example. You can put into a document-matching mode by setting `semantics` to `RESPONSE`. For example: @@ -67,7 +67,7 @@ instead tells it to find similar questions. You can also add a [filter expression](/docs/common-use-cases/filtering-by-metadata/filter-overview) of `part.is_title = true` to *only* match the questions. -# Combining question matching and answering +## Combine question matching and answering Expanding on the previous example, we can help users find question or answer matches together by using [batched queries](/docs/api-reference/search-apis/batched-queries) combined with filter expressions. For example: diff --git a/www/docs/common-use-cases/recommendation-systems/overview.md b/www/docs/common-use-cases/recommendation-systems/overview.md index 25de2b0d0..62e66ffbd 100644 --- a/www/docs/common-use-cases/recommendation-systems/overview.md +++ b/www/docs/common-use-cases/recommendation-systems/overview.md @@ -9,15 +9,17 @@ import {Config} from '@site/docs/definitions.md'; Vectara can be used as a semantic recommendation system out of the box in order to provide your users with semantically similar documents/products. -# Before you begin +## Semantic recommendation system considerations Before you begin using for a semantic recommendation system, it's useful to think through what types of recommendation flows you want to enable. For example: -- Do you want to recommend based on the entire document content or just 1 section/field like the document title? -- Do you want to recommend semantically similar content regardless of the source language or do you want to only match a particular language? +- Do you want to recommend based on the entire document content or just 1 + section/field like the document title? +- Do you want to recommend semantically similar content regardless of the + source language or do you want to only match a particular language? - Are you looking for exact duplicates or semantic similarity? -# Exact duplicate matching +## Exact duplicate matching Exact duplicate matching can be useful when you want to ensure no duplicate content exists in your corpora or to find exact matches of "known bad" documents like those that might violate compliance rules in your organization. In general, @@ -28,7 +30,7 @@ Specifically: 1. When you index your content, hash your content using something like SHA-256 and add that as custom metadata on the document 2. To find similar content to a particular document, hash the entire document using the same hashing algorithm and then perform a filtered query to find exact hash matches -# Similar document matching and near-duplicates +## Similar document matching and near-duplicates Sometimes, you want to recommend alternative products or web pages to a user that are similar to the one they're looking at or a recently purchased product. These use cases can be dealt with by using in a @@ -84,7 +86,7 @@ this document text to and set the `semantics` to This will find documents that are most semantically similar to that document. -## Further refinement +## Further recommendation refinement At times, it can be useful to further refine the recommendations. For example: - Only suggest based on similar document titles - Only suggest results that share the same language diff --git a/www/docs/console-ui/manage_user.md b/www/docs/console-ui/manage_user.md index 4a2150752..896b068b0 100644 --- a/www/docs/console-ui/manage_user.md +++ b/www/docs/console-ui/manage_user.md @@ -6,7 +6,7 @@ title: Manage users In this section, you will learn how to create and manage a user, including adjusting account and corpus level authorizations. -# Add User +## Add User Users can be created by the account administrator. Once you've logged in, navigate to the **User** tab under **Authentication** to create new users @@ -20,7 +20,7 @@ administrator, corpus administrator, and billing administrator. A user without assigned roles at the account level can still be given corpus-level roles, as described later. -# Edit User +## Edit User A list of all users is available on the User screen. An existing user can be modified directly from this list by clicking the three-dotted button at the far diff --git a/www/docs/use-case-exploration.md b/www/docs/use-case-exploration.md index adae3f2e2..8119d46fa 100644 --- a/www/docs/use-case-exploration.md +++ b/www/docs/use-case-exploration.md @@ -24,7 +24,6 @@ their information on what you and your users care about – information grounded in facts. also provides result recommendations and enables global collaboration through its **cross-language** search. - ## Vectara GenAI Use Cases This versatile GenAI platform caters to a wide range of use @@ -39,8 +38,8 @@ sovereignty and provides you with peace of mind. ### Conversational AI Use to leverage the power of intelligent chatbots that provide -an interactive user experience. Enable your users with self-service as they engage in -human-like interactions, providing context in queries, and receiving +an interactive user experience. Enable your users with self-service as they engage +in human-like interactions, providing context in queries, and receiving intelligent answers because the system understands them. This technology sits behind virtual assistants, chatbots, and messaging applications to help businesses automate customer service and streamline operations. @@ -63,7 +62,6 @@ workers on data, and enhance your website search. em organization to create a dynamic, responsive, and continuous improving Question and Answer system that enhances the user experience and provides context-aware answers. - ### Research and Analysis Vectara sifts through volumes of publications, news articles, financial reports, @@ -72,10 +70,10 @@ summarized answers to guide decision-making in your domain. Collaborate with researchers to streamline the peer review process by investigating topics and questions in these vast volumes of data to identify key insights. -Using is like having a global research assistant that can read and -understand large volumes of documents in an instant. Let the platform speed up -your research process, find the most relevant information, and become a -recommendation system for your domain. +Using is like having a global research assistant that +can read and understand large volumes of documents in an instant. Let the +platform speed up your research process, find the most relevant information, +and become a recommendation system for your domain. Vectara can help transform data into insights which help make decision-making easier. This platform can provide hidden insights and patterns from your data, @@ -90,13 +88,14 @@ being an LLM expert. You provide data and queries through simple APIs in our SaaS service. Enable your users to find the most relevant products, support cases, and -documents that answer their questions. helps you bridge the gap -between user queries and the vast amount of data within an application. -Users can find exactly what they are looking for despite how they ask. +documents that answer their questions. helps you +bridge the gap between user queries and the vast amount of data within +an application. Users can find exactly what they are looking for despite +how they ask. ## Sample Vectara Demos and Applications -We provide this list of sample applications to help inspire developer +We provide this list of sample open source applications to help inspire developer creativity: * [**AskNews**](https://asknews.demo.vectara.com) @@ -118,7 +117,7 @@ creativity: :::note -These sample applications are examples of our platform in action and not supported products. +These sample open source applications are examples of our platform in action and not supported products. ::: diff --git a/www/docs/welcome.md b/www/docs/welcome.md index 627946548..7f60ca4b0 100644 --- a/www/docs/welcome.md +++ b/www/docs/welcome.md @@ -70,7 +70,7 @@ power of your data. wants to transform the way developers interact with data and unlock a world of insights at their fingertips. Welcome to the future of information interaction! -### Not sure where to start? +## Not sure where to start? Here are some ideas: