Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-11-10 01:10:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: integrations custom callout (#24843)

Browse Source
This commit is contained in:
Bagatur 2024-07-30 15:48:18 -07:00 committed by GitHub
parent 61ecb10a77
commit a4e940550a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 29 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docs/scripts/document_loader_feat_table.py
View File

@ -15,6 +15,14 @@ hide_table_of_contents: true
# Document loaders # Document loaders
:::info
If you'd like to write your own document loader, see [this how-to](/docs/how_to/document_loader_custom/).
If you'd like to contribute an integration, see [Contributing integrations](/docs/contributing/integrations/).
:::
## Features ## Features
The following table shows the feature support for all document loaders. The following table shows the feature support for all document loaders.

14
docs/scripts/model_feat_table.py
View File

@ -144,6 +144,13 @@ custom_edit_url:
# LLMs # LLMs
:::info
If you'd like to write your own LLM, see [this how-to](/docs/how_to/custom_llm/).
If you'd like to contribute an integration, see [Contributing integrations](/docs/contributing/integrations/).
:::
## Features (natively supported) ## Features (natively supported)
All LLMs implement the Runnable interface, which comes with default implementations of all methods, ie. `ainvoke`, `batch`, `abatch`, `stream`, `astream`. This gives all LLMs basic support for async, streaming and batch, which by default is implemented as below: All LLMs implement the Runnable interface, which comes with default implementations of all methods, ie. `ainvoke`, `batch`, `abatch`, `stream`, `astream`. This gives all LLMs basic support for async, streaming and batch, which by default is implemented as below:
- *Async* support defaults to calling the respective sync method in asyncio's default thread pool executor. This lets other async functions in your application make progress while the LLM is being executed, by moving this call to a background thread. - *Async* support defaults to calling the respective sync method in asyncio's default thread pool executor. This lets other async functions in your application make progress while the LLM is being executed, by moving this call to a background thread.
@ -169,6 +176,13 @@ hide_table_of_contents: true
## Advanced features ## Advanced features
:::info
If you'd like to write your own chat model, see [this how-to](/docs/how_to/custom_chat_model/).
If you'd like to contribute an integration, see [Contributing integrations](/docs/contributing/integrations/).
:::
The following table shows all the chat model classes that support one or more advanced features. The following table shows all the chat model classes that support one or more advanced features.
:::info :::info

7
docs/scripts/tool_feat_table.py
View File

@ -101,6 +101,13 @@ hide_table_of_contents: true
# Tools # Tools
:::info
If you'd like to write your own tool, see [this how-to](/docs/how_to/custom_tools/).
If you'd like to contribute an integration, see [Contributing integrations](/docs/contributing/integrations/).
:::
## Search Tools ## Search Tools
The following table shows tools that execute online searches in some shape or form: The following table shows tools that execute online searches in some shape or form: