Skip to content

Commit

Permalink
Browse files Browse the repository at this point in the history
…experience into kate-check-meta-data-for-docs
  • Loading branch information
lampa-da committed Sep 18, 2024
2 parents c72abbf + 533c6cd commit 46debf3
Show file tree
Hide file tree
Showing 123 changed files with 663 additions and 430 deletions.
10 changes: 4 additions & 6 deletions .github/workflows/preview-docs.yml
Original file line number Diff line number Diff line change
@@ -1,21 +1,19 @@
name: preview-docs

on:
pull_request_target:
pull_request:
branches:
- main

concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true

jobs:
run:
runs-on: ubuntu-latest
permissions: write-all
steps:
- name: Checkout repository
uses: actions/checkout@v4
# with:
# ref: "${{ github.event.pull_request.merge_commit_sha }}"

- name: Setup pnpm
uses: pnpm/action-setup@v2
Expand All @@ -24,7 +22,7 @@ jobs:

- name: Install Dependencies
shell: bash
run: pnpm install
run: pnpm install

- name: Run fern check
env:
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/publish-docs.yml
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ jobs:

- name: Install Dependencies
shell: bash
run: pnpm install
run: pnpm install

- name: Publish Docs
env:
Expand Down
455 changes: 357 additions & 98 deletions cohere-openapi.yaml

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion fern/fern.config.json
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
{
"organization": "cohere",
"version": "0.41.8"
"version": "*"
}
13 changes: 7 additions & 6 deletions fern/pages/changelog/2022-02-22-larger-representation-models.mdx
Original file line number Diff line number Diff line change
@@ -1,10 +1,11 @@
---
data:
description: >-
We've released new Representation Model sizes and updated our small model
with improved text length capacity.
title: Larger Representation Models
slug: changelog/larger-representation-models
type: added
createdAt: 'Tue Feb 22 2022 19:05:00 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
We've released new Representation Model sizes and updated our small model with
improved text length support.
New Representation Model sizes and an increased token limit offer improved
performance and flexibility.
---
Representation Models are now available in the sizes of `medium-20220217` and `large-20220217` as well as an updated version of `small-20220217`. Our previous `small` model will be available as `small-20211115`. In addition, the maximum tokens length per text has increased from 512 to 1024. We recommend keeping text lengths below 128 tokens for optimal performance; for any text longer than 128 tokens, the text is spliced and the resulting embeddings of each component are then averaged and returned.
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ type: added
createdAt: 'Tue Mar 01 2022 19:03:00 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Take your NLP tasks further with our new `Extremely Large (Beta)` model, now
available for use.
Take your NLP tasks further with our new top-tier model, Extremely Large
(Beta), now available.
---
Our biggest and most performant generation model is now available. `Extremely Large (Beta)` outperforms our previous `large` model on a variety of downstream tasks including sentiment analysis, named entity recognition (NER) and common sense reasoning, as measured by our internal benchmarks. You can access `Extremely Large (Beta)` as `xlarge-20220301`. While in Beta, note that this model will have a maximum token length of 1024 tokens and maximum `num_generations` of 1.
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,6 @@ createdAt: 'Tue Mar 08 2022 18:58:00 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Classify text with Cohere's new classification endpoint, powered by generation
models. Supports few-shot classification. Learn more in our docs.
models, offering few-shot learning.
---
Classification is now available via our classification endpoint. This endpoint is currently powered by our generation models (`small` and `medium`) and supports few-shot classification. We will be deprecating support for Choose Best by May 18th. To learn more about classification at Cohere check out the docs [here](/classify-reference).
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ type: improved
createdAt: 'Tue Mar 08 2022 19:02:00 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Finetuning is now generally available to all users. Upload custom datasets to
improve performance. Read our updated policies for more information.
Fine-tune models with your own data and leverage updated policies for powerful
NLP solutions.
---
**Finetuning is Generally Available**

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ type: ''
createdAt: 'Tue Mar 08 2022 19:00:00 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Newly shipped generation models with improved performance trained on a
high-quality dataset.
Try our new small, medium, and large generation models with improved
performance from our high-quality dataset.
---
We’ve shipped updated `small`, `medium`, and `large` generation models. You’ll find significant improvements in performance that come from our newly assembled high quality dataset.
4 changes: 2 additions & 2 deletions fern/pages/changelog/2022-04-25-new-extremely-large-model.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ type: added
createdAt: 'Mon Apr 25 2022 17:48:00 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Our new `xlarge` model: improved quality, 4x faster, and longer text
capabilities with frequency and presence penalties.
We're thrilled to introduce our enhanced `xlarge` model, now with superior
generation quality and speed.
---
Our new and improved `xlarge` has better generation quality and a 4x faster prediction speed. This model now supports a maximum token length of 2048 tokens and frequency and presence penalties.
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ type: improved
createdAt: 'Mon Apr 25 2022 17:54:00 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Latest updates improve model stability and fix a bug in the generation
presence & frequency penalty for more effective results.
The latest updates improve model stability and fix a bug for more effective
generation presence and frequency penalties.
---
Updated `small`, `medium`, and `large` models are more stable and resilient against abnormal inputs due to a FP16 quantization fix. We also fixed a bug in generation presence & frequency penalty, which will result in more effective penalties.
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ type: improved
createdAt: 'Tue Mar 29 2022 17:56:00 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
We've updated our models to support longer contexts and improved performance
for longer texts.
Enhance your text generation and representation with improved models, now
offering better context support and optimal performance.
---
We've retrained our `small`, `medium`, and `large` generation and representation models. Updated representation models now support contexts up to 4096 tokens (previously 1024 tokens). We recommend keeping text lengths below 512 tokens for optimal performance; for any text longer than 512 tokens, the text is spliced and the resulting embeddings of each component are then averaged and returned.
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ type: improved
createdAt: 'Thu Jul 07 2022 17:47:00 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Our API updates mean endpoints now have default models, but you can still
specify a model for more control.
Our APIs are now model-agnostic with default endpoint settings, offering
greater flexibility and control for users.
---
Our APIs no longer require a model to be specified. Each endpoint comes with great defaults. For more control, a model can still be specified by adding a model param in the request.
4 changes: 2 additions & 2 deletions fern/pages/changelog/2022-08-05-introducing-moderate-beta.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ type: added
createdAt: 'Fri Aug 05 2022 17:46:00 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Classify harmful text with [Moderate] to detect across 9 categories with
associated confidence scores. Expect performance improvements.
Access cutting-edge natural language processing tools without the need for
costly supercomputing power.
---
Use Moderate (Beta) to classify harmful text across the following categories: `profane`, `hate speech`, `violence`, `self-harm`, `sexual`, `sexual (non-consenual)`, `harassment`, `spam`, `information hazard (e.g., pii)`. Moderate returns an array containing each category and its associated confidence score. Over the coming weeks, expect performance to improve significantly as we optimize the underlying model.
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ type: improved
createdAt: 'Tue Oct 18 2022 22:27:00 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Unlock Cohere AI with Trial Keys, Production Keys, updated UI, Quickstart
Guides, improved team features, and enhanced custom model details and metrics.
Unlock new features, including production keys, flat-rate pricing, improved
UI, and enhanced team collaboration and model insights.
---
- Free, rate limited Trial Keys for experimentation, testing, and playground usage
- Production keys with no rate limit for serving Cohere in production applications
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ type: improved
createdAt: 'Thu Nov 03 2022 22:33:02 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Classify text with few-shot learning and embeddings from our Representational
model.
Improve few-shot classification with Co.classify and embeddings from our
Representational model.
---
The Co.classify endpoint now serves few-shot classification tasks using embeddings from our Representational model for the small, medium, and large default models.
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ type: added
createdAt: 'Thu Nov 03 2022 22:34:05 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Our generative models now support logit bias to prevent unwanted tokens and
encourage desired ones.
Take control of your generative models with the new logit_bias parameter to
guide token generation.
---
Our Generative models have now the option to use the new logit_bias parameter to prevent the model from generating unwanted tokens or to incentivize it to include desired tokens. Logit bias is supported in all our default Generative models.
4 changes: 2 additions & 2 deletions fern/pages/changelog/2022-11-07-new-look-for-docs.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ type: improved
createdAt: 'Mon Nov 07 2022 21:44:01 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Explore our updated docs with interactive tutorials, improved architecture,
and a UI refresh for a streamlined experience.
Explore our updated docs with interactive tutorials, improved info
architecture, and a UI refresh for a streamlined experience.
---
We've updated our docs to better suit our new developer journey! You'll have a sleeker, more streamlined documentation experience.

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ type: added
createdAt: 'Tue Nov 08 2022 16:43:50 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Introducing new and improved Medium and XLarge models, outperforming previous
versions on various tasks. Learn more about our Command model too!
Introducing new and improved Medium and XLarge models, plus a Command model
for precise responses to commands.
---
**New & Improved Medium & Extremely Large**

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ type: improved
createdAt: 'Fri Dec 02 2022 16:28:42 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Important update: As of Dec 2, 2022, we are consolidating our generative
models. Learn more here.
We're updating our generative AI models to offer improved Medium and X-Large
options.
---
Effective December 2, 2022, we will be consolidating our generative models and only serving our Medium (focused on speed) and X-Large (focused on quality). We will also be discontinuing support for our Medium embedding model.

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ type: added
createdAt: 'Mon Dec 12 2022 15:52:44 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Unlock multilingual semantic search with Cohere's new model, and easily detect
languages with the `co.detect_language()` endpoint.
Cohere's multilingual model now supports semantic search across 100 languages
with a single index.
---
Cohere's multilingual text understanding model is now available! The `multilingual-22-12` model can be used to semantically search within a single language, as well as across languages. Compared to keyword search, where you often need separate tokenizers and indices to handle different languages, the deployment of the multilingual model for search is trivial: no language-specific handling is needed — everything can be done by a single model within a single index.

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ type: improved
createdAt: 'Tue Jan 17 2023 20:24:25 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Stay up-to-date with our Common models' nightly versions, offering improved
performance and fast response for all your chatbot needs.
Get improved performance with our new nightly versions of Command models, now
available in medium and x-large sizes.
---
Nightly versions of our Common models are now available. This means that every week, you can expect the performance of command-nightly to improve as we continually retrain them.

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ type: ''
createdAt: 'Thu Apr 04 2024 15:11:00 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Unlock dynamic, accurate, and complex responses with Command R+, our new large
language model, optimized for conversational AI.
Explore Command R+, Cohere's powerful language model, excelling in multi-step
tool use and complex conversational AI tasks.
---
We're pleased to announce the release of [Command R+](/docs/command-r-plus), our newest and most performant large language model. Command R+ is optimized for conversational interaction and long-context tasks, and it is the recommended model for use cases requiring high performance and accuracy.

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ type: improved
createdAt: 'Wed Jan 25 2023 04:02:31 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Cohere's co.classify endpoint now supports multilingual embedding with the
`multilingual-22-12` model.
The co.classify endpoint now supports multilingual capabilities with the new
multilingual-22-12 model.
---
The co.classify endpoint now supports the use of Cohere's multilingual embedding model. The `multilingual-22-12 model` is now a valid model input in the co.classify call.
4 changes: 2 additions & 2 deletions fern/pages/changelog/2023-04-26-model-names-are-changing.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ type: improved
createdAt: 'Wed Apr 26 2023 19:44:46 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
We've updated our model names for simplicity. Check out our new names and
backwards-compatible previous names.
We've updated our model names for simplicity and consistency, and old names
will work for now.
---

We are updating the names of our models to bring consistency and simplicity to our product offerings. As of today, you will be able to call Cohere’s models via our API and SDK with the new model names, and all of our documentation has been updated to reflect the new naming convention.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ type: ''
createdAt: 'Fri Jun 23 2023 14:28:33 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
We've updated how the maximum number of documents is calculated for co.rerank.
See the new calculation here.
Stay up to date with our latest changes to co.rerank, now with an improved
maximum document limit.
---
We have updated how the maximum number of documents is calculated for co.rerank. The endpoint will error if `len(documents) * max_chunks_per_doc >10,000` where `max_chunks_per_doc` is set to 10 as default.
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ type: added
createdAt: 'Wed Jun 28 2023 15:50:46 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Latest Command model update brings code & conversation improvements. New:
co.rerank() API, streaming in Co.generate(), billing table filters.
The latest Command model update brings enhanced code, conversation, and
reasoning, along with new API features and usage/billing improvements.
---
**Command Model Updated**
The Command model has been updated. Expect improved code and conversational capabilities, as well as reasoning skills on various tasks.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ type: ''
createdAt: 'Sat Aug 05 2023 01:24:15 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Unlock improved reasoning, conversation, and Okta SSO support with Cohere's
Command Model update and Finetuning SDK.
Unlock improved reasoning and conversation with Command R+, now featuring Okta
OIDC support and an enhanced finetuning SDK.
---
**Command Model Updated**
The Command model has been updated. Expect improvements in reasoning and conversational capabilities.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,8 @@ type: ''
createdAt: 'Wed Sep 27 2023 17:09:56 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Explore co.chat() and Cohere's Chat + RAG Playground, offering improved AI
generation, grounded in verifiability and enhanced by retrieval augmented
generation.
Experience the future of generative AI with co.chat() and explore the power of
retrieval-augmented generation for grounded and timely outputs.
---
**We're Releasing co.chat() and the Chat + RAG Playground**

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ type: ''
createdAt: 'Tue Jan 02 2024 19:15:05 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Get the latest on Cohere AI's new features: Connectors, fine-tuning, Embed
Jobs API, and more language support in the SDK.
Discover new AI capabilities with Cohere's latest features, including improved
fine-tuning, Embed Jobs API, and multi-language SDK support.
---
## Apply Cohere's AI with Connectors!

Expand Down
4 changes: 2 additions & 2 deletions fern/pages/changelog/2024-03-20-python-sdk-v500.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ type: ''
createdAt: 'Wed Mar 20 2024 18:37:00 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Keep your Python SDK integrations up-to-date with our latest release. Check
the migration guide for detailed instructions.
Stay up-to-date with our latest Python SDK release and learn about deprecated
functions and migration instructions.
image: ../../assets/images/739010f-cohere_meta_image.jpg
---
With the release of our latest Python SDK, there are a number of functions that are no longer supported, including `create_custom_models`.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ type: ''
createdAt: 'Thu Mar 21 2024 18:39:00 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Explore Cohere's Python SDK update, which now includes fine_tuning with a
range of supported functions.
Stay up-to-date with Cohere's Python SDK by checking out the new `fine_tuning`
feature and its functions.
image: ../../assets/images/f97bb24-cohere_meta_image.jpg
---
In place of `custom_models`, `fine_tuning` has been added to the Python SDK. See this Python [github repository](https://github.com/cohere-ai/cohere-python/tree/main/src/cohere/finetuning) for the full list of supported functions!
4 changes: 2 additions & 2 deletions fern/pages/changelog/2024-04-03-python-sdk-v520-release.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ type: ''
createdAt: 'Wed Apr 03 2024 18:53:00 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
We've updated our Python SDK with a local tokenizer. Learn more about these
changes and how to use them.
Stay up to date with our Python SDK update, including local tokenizer defaults
and new required fields.
image: ../../assets/images/090bdae-cohere_meta_image.jpg
---
We've released an additional update for our Python SDK! Here are the highlights.
Expand Down
4 changes: 2 additions & 2 deletions fern/pages/changelog/2024-04-09-advanced-retrieval-launch.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ type: ''
createdAt: 'Tue Apr 09 2024 02:53:14 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Rerank 3: Our newest ranking model with 4096 context length, SOTA performance,
and faster inference speed for all document lengths.
Rerank 3 offers improved performance and inference speed for long and short
documents with a context length of 4096.
---
We're pleased to announce the release of [Rerank 3](/docs/rerank-2) our newest and most performant foundational model for ranking. Rerank 3 boast a context length of 4096, SOTA performance on Code Retrieval, Long Document, and Semi-Structured Data. In addition to quality improvements, we've improved inference speed by a factor of 2x for short documents (doc length \< 512 tokens) and 3x for long documents (doc length ~4096 tokens).
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ type: ''
createdAt: 'Mon Jun 10 2024 16:06:00 GMT+0000 (Coordinated Universal Time)'
hidden: false
description: >-
Discover updates to Cohere's tool use, docs, and billing policies, including
new multi-step tool use and improved SDK cloud support.
Get started with multi-step tool use, explore new docs, and learn about
billing changes in Cohere's Chat API.
image: ../../assets/images/d6d2d1c-cohere_meta_image.jpg
---
## Multi-step tool use now default in Chat API
Expand Down
Loading

0 comments on commit 46debf3

Please sign in to comment.