[DON'T MERGE] Langchain Integration #1312
Open
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
✅ Deploy Preview for hardcore-allen-f5257d ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
amandalindsay
requested changes
Oct 15, 2024
| == Updating the Vector Store | ||
|
|
||
| Once the vector store is created, you can start adding LangChain documents or string data into it. | ||
| While adding the data, you have the option to associate identifiers and metadata with them. |
There was a problem hiding this comment.
Suggested change
| While adding the data, you have the option to associate identifiers and metadata with them. | |
| While adding the data, you have the option to associate identifiers and metadata with it. |
There was a problem hiding this comment.
Data plural isn't wrong, just think this is more elegant
There was a problem hiding this comment.
Thanks Amanda,
Updated at: cfce797
| ---- | ||
|
|
||
| `Hazelcast.add_texts` method returns the IDs of the added texts. | ||
| If the IDs were not provided to the `add_texts` method, then they are automatically genereated, like in the example above. |
There was a problem hiding this comment.
Suggested change
| If the IDs were not provided to the `add_texts` method, then they are automatically genereated, like in the example above. | |
| If the IDs were not provided to the `add_texts` method, then they are automatically generated, like in the example above. |
| If the IDs were not provided to the `add_texts` method, then they are automatically genereated, like in the example above. | ||
|
|
||
| You can provide the IDs manually by passing them in the `ids` parameter. | ||
| That may be useful in case you would like to update data instead of extending the vector store. |
There was a problem hiding this comment.
Suggested change
| That may be useful in case you would like to update data instead of extending the vector store. | |
| This is useful when you want to update data instead of extending the vector store. |
| ) | ||
| ---- | ||
|
|
||
| In case you have `langchain_core.documents.Document` objects, you can use the `add_documents` methods to add them to the vector store: |
There was a problem hiding this comment.
Suggested change
| In case you have `langchain_core.documents.Document` objects, you can use the `add_documents` methods to add them to the vector store: | |
| If you have `langchain_core.documents.Document` objects, you can use the `add_documents` methods to add them to the vector store: |
| ---- | ||
|
|
||
| `Hazelcast` vector store has two class methods that combine creating the vector store and adding texts or documents to it. | ||
| Those are `Hazelcast.from_texts` and `Hazelcast.from_documents` methods respectively. |
There was a problem hiding this comment.
Suggested change
| Those are `Hazelcast.from_texts` and `Hazelcast.from_documents` methods respectively. | |
| These are the `Hazelcast.from_texts` and `Hazelcast.from_documents` methods, respectively. |
|
|
||
| `Hazelcast` vector store has two class methods that combine creating the vector store and adding texts or documents to it. | ||
| Those are `Hazelcast.from_texts` and `Hazelcast.from_documents` methods respectively. | ||
| Calling these methods return the `Hazelcast` vector store instance. |
There was a problem hiding this comment.
Suggested change
| Calling these methods return the `Hazelcast` vector store instance. | |
| Calling these methods returns the `Hazelcast` vector store instance. |
| ---- | ||
|
|
||
| To delete some or all Documents, you can use the `delete` method. | ||
| It deletes the Documents with the given IDs if one or more IDs provided, or deletes all Documents if no IDs are provided. |
There was a problem hiding this comment.
Suggested change
| It deletes the Documents with the given IDs if one or more IDs provided, or deletes all Documents if no IDs are provided. | |
| It deletes the Documents with the given IDs if one or more IDs are provided, or deletes all Documents if no IDs are provided. |
|
@amandalindsay Thanks for the review. |
|
|
||
| `langchain-hazelcast` package provides the Hazelcast `VectorStore` implementation for LangChain. | ||
|
|
||
| == Installing LangChain/Hazelcast Vector Store |
There was a problem hiding this comment.
Sometimes Vector Store uses initial caps, sometimes it's all lower case. Is it a proper name (in which case it should be 'Vector Store')?
|
|
||
| You can retrieve Documents in the vector store using the `get_by_ids` method. | ||
| This method takes a sequence of IDs and returns the corresponding Documents if they exist. | ||
| Note that, the order of the IDs and the returned Documents may not be the same: |
There was a problem hiding this comment.
Suggested change
| Note that, the order of the IDs and the returned Documents may not be the same: | |
| Note that the order of the IDs and the returned Documents may not be the same: |
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.
Adds LangChaing integration for Python docs.
I've added a top-level LangChain navigation item under "Integrate", but I will also add a LangChain tutorial later and we may have more LangChain integrations.
Can the page introduced in this PR serve as the parent page for those?