-
Notifications
You must be signed in to change notification settings - Fork 130
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Integrations page #2254
Integrations page #2254
Conversation
Hi @erika-cardenas is this a feature branch to collect changes for integration docs? |
Add Compute Infrastructure Companies
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hi @erika-cardenas a couple of thoughts
- I added a link to staging in the comments
- The branch needs to be refreshed. It's easier to do that locally. I'm not sure if you have other changes coming so I haven't refreshed it.
- The Data Platforms page shows up in the ToC twice. I think this page is in the wrong directory: /developers/integrations/data-platforms/confluent-cloud
- These pages are missing content. Consider adding an underscore to the file names to hide them if you need to publish the rest before you have content.
/developers/integrations/data-pipeline/firecrawl
/developers/integrations/data-pipeline/spark
developers/integrations/data-pipeline/unstructured
Similarly, it's probably a good idea to comment out the observability section, llamaindex semantic kernel, and langchain
Hey @daveatweaviate, |
Operations section
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@erika-cardenas Here are some comments on the operations sections.
I'll send LLM frameworks next
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks @erika-cardenas
Data platforms next (maybe that's not new?)
developers/integrations/llm-frameworks/llamaindex/LlamaIndex.md
Outdated
Show resolved
Hide resolved
developers/integrations/llm-frameworks/semantic-kernel/semantic-kernel.md
Outdated
Show resolved
Hide resolved
developers/integrations/llm-frameworks/semantic-kernel/semantic-kernel.md
Outdated
Show resolved
Hide resolved
developers/integrations/llm-frameworks/semantic-kernel/semantic-kernel.md
Outdated
Show resolved
Hide resolved
developers/integrations/llm-frameworks/semantic-kernel/semantic-kernel.md
Outdated
Show resolved
Hide resolved
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@erika-cardenas Here's the next one.
I think we already did the compute infrastructure and cloud hyperscalers. Let me know if there are any changes I should look at there.
developers/integrations/data-platforms/confluent-cloud/index.md
Outdated
Show resolved
Hide resolved
developers/integrations/data-platforms/confluent-cloud/index.md
Outdated
Show resolved
Hide resolved
Thank you so much @daveatweaviate! Just made the final edits. 🙂 |
@erika-cardenas thanks for all the updates, this is a big project! I fixed the merge conflict and made a couple of tiny tweaks. This LGTM - you can merge whenever you want, or else I can merge it when we get back on Tuesday. Just me know. |
It allows you to easily crawl and extract clean, structured data from websites. It is an API service that converts a URL into clean markdown or structured data. | ||
|
||
## Firecrawl and Weaviate | ||
Firecrawl handles the complexities of web scraping like proxies, caching, rate limits, and dynamic content. It produces markdown or JSON formatted output that is ready to be ingested into vector databases like Weaviate. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Firecrawl handles the complexities of web scraping like proxies, caching, rate limits, and dynamic content. It produces markdown or JSON formatted output that is ready to be ingested into vector databases like Weaviate. | |
Firecrawl handles the complexities of web scraping like proxies, caching, rate limits, and dynamic content. It produces markdown or JSON formatted output that is ready to be ingested into vector databases like Weaviate. |
## Spark and Weaviate | ||
The Spark connector enables you to easily ingest data from Spark data structures into Weaviate. | ||
|
||
Learn more about the connector in the Weaviate[ Spark connector repository](https://github.com/weaviate/spark-connector). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Learn more about the connector in the Weaviate[ Spark connector repository](https://github.com/weaviate/spark-connector). | |
Learn more about the connector in the Weaviate [Spark connector repository](https://github.com/weaviate/spark-connector). |
[Modal](https://modal.com/) provides a serverless platform that has on-demand access to GPUs and a custom high-performance container runtime. Use Modal to easily deploy and automatically scale high-performance applications. | ||
|
||
## Modal and Weaviate | ||
Weaviate leverages Modal's serverless infrastructure for fast embedding generation and for fast generative model calls. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The words "for fast" are repetitive.
Weaviate leverages Modal's serverless infrastructure for fast embedding generation and for fast generative model calls. | |
Weaviate leverages Modal's serverless infrastructure for fast embedding generation and quick generative model calls. |
## Context Data and Weaviate | ||
Weaviate is a [target connection](https://context-data.gitbook.io/context-data-1/adding-target-connections#add-a-weaviate-target-connection) in Context Data. | ||
|
||
To connect to ContextData, open the console and input your Weaviate instance's URL and authentication credentials when prompted. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
To connect to ContextData, open the console and input your Weaviate instance's URL and authentication credentials when prompted. | |
To connect to Context Data, open the console and input your Weaviate instance's URL and authentication credentials when prompted. |
Hi, sorry for hijacking the PR. I'm really glad to see this coming as I raised an issue #1715 some time ago. It would be great to see the libraries listed there in this section. I can also contribute |
…nto integrations-page
…ate-io into integrations-page
Thank you @network-charles for looking this over! @eddumelendez Your excitement for this makes me super happy! I'm merging this PR into main soon; I hope you like the format and content. |
It’s a pleasure, @erika-cardenas. |
@network-charles thank you for your suggestions! We'd like to give you credit for the suggestions. In order to include them, we need to verify that you have accepted our Contributor license agreement Would you open a new PR against our main branch for your suggestions? If you accept the Contributor license, please say so in the PR comments. Thanks! |
Feature branch to gather changes for an integrations section
Type of change:
How Has This Been Tested?
yarn start