First round of fixes based on user feedback #290
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: trentfowlercohere <[email protected]>
|
🌿 Preview your docs: https://cohere-preview-6341ef20-5b80-45e0-be6e-0aff85c8360d.docs.buildwithfern.com |
|
🌿 Preview your docs: https://cohere-preview-0797eac0-8b38-4661-8e68-61dba82920d8.docs.buildwithfern.com |
|
🌿 Preview your docs: https://cohere-preview-640acde5-ac86-4d18-a24c-b3ebc76c008d.docs.buildwithfern.com |
invader89
approved these changes
Dec 12, 2024
lfayoux
approved these changes
Dec 12, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This pull request introduces several updates to the documentation related to text embeddings, reranking, and prompt engineering. The changes aim to provide clearer guidance on handling large queries, managing context length, and truncating prompts.
fern/pages/text-embeddings/reranking/overview.mdxfile, the query in the example has been updated to include double quotes around the query text. This ensures that the query is treated as a string literal, improving code readability and avoiding potential issues with special characters or whitespace.fern/pages/text-embeddings/reranking/reranking-best-practices.mdxfile now mentions bothrerank-v3.5andrerank-v3.0models, indicating that both versions are available and trained with a context length of 4096 tokens. This update clarifies the supported model versions and their context length capabilities.fern/pages/text-generation/prompt-engineering/prompt-truncation.mdxfile has been modified to provide more detail about theprompt_truncationparameter. It now explains that when set toAUTO, the API will break documents into smaller chunks, rerank them based on relevance, and drop the least relevant documents to fit within the model's context length limit. This enhancement offers a more comprehensive understanding of how the API handles prompt truncation.