github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-04-27 19:46:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

x

Browse Source
This commit is contained in:
Eugene Yurtsev 2024-09-25 13:37:13 -04:00
parent 3ece5497ac
commit 14347acbce
1 changed files with 9 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
docs/docs/how_to/langgraph_persistence.md
View File

@ -2,20 +2,14 @@
As of the v0.3 release of LangChain, we recommend that LangChain users take advantage of [LangGraph persistence](https://langchain-ai.github.io/langgraph/concepts/persistence/) to incorporate `memory` into their LangChain application.
This how-to guide will contain links to other relevant how-to guides for specific situations.
## How-tos
## Evolution of memory in LangChain
The concept of memory has evolved significantly in LangChain since its initial release.
In LangChain 0.0.x, memory was based on the [BaseMemory](https://api.python.langchain.com/en/latest/memory/langchain_core.memory.BaseMemory.html) interface, and partially on the [BaseChatMessageHistory](https://api.python.langchain.com/en/latest/history/langchain_core.runnables.history.BaseChatMessageHistory.html) interface.
In LangChain 0.0.x, memory was based on the [BaseMemory](https://api.python.langchain.com/en/latest/memory/langchain_core.memory.BaseMemory.html) interface and the [BaseChatMessageHistory](https://api.python.langchain.com/en/latest/history/langchain_core.runnables.history.BaseChatMessageHistory.html) interface.
There were a number of [memory implementations](https://python.langchain.com/api_reference/langchain/memory.html) based
on the `BaseMemory` interface, such as [ConversationBufferMemory](https://python.langchain.com/api_reference/langchain/memory/langchain.memory.buffer.ConversationBufferMemory.html), [ConversationBufferWindowMemory](https://python.langchain.com/api_reference/langchain/memory/langchain.memory.buffer_window.ConversationBufferWindowMemory.html) etc.
While these implementations proved useful for prototyping, they were limited in their capability and not well suited for real-world conversational AI applications. The abstractions lacked built-in support for multi-user, multi-conversation scenarios, which are essential for practical conversational AI systems.
There were number of useful [memory implementations](https://python.langchain.com/api_reference/langchain/memory.html) based
on the `BaseMemory` interface (e.g.[ConversationBufferMemory](https://python.langchain.com/api_reference/langchain/memory/langchain.memory.buffer.ConversationBufferMemory.html), [ConversationBufferWindowMemory](https://python.langchain.com/api_reference/langchain/memory/langchain.memory.buffer_window.ConversationBufferWindowMemory.html)); however, these lacked built-in support for multi-user, multi-conversation scenarios, which are essential for practical conversational AI systems.
:::note
If you are relying on any deprecated memory abstractions in LangChain 0.0.x, we recommend that you follow
@ -23,19 +17,15 @@ the given steps to upgrade to the new LangGraph persistence feature in LangChain
https://python.langchain.com/docs/versions/migrating_memory/
:::
As of LangChain v0.1, we started recommending that users rely primarily on [BaseChatMessageHistory](https://python.langchain.com/api_reference/core/runnables/langchain_core.runnables.history.RunnableWithMessageHistory.html#langchain_core.runnables.history.RunnableWithMessageHistory).
As of LangChain v0.1, we started recommending that users rely primarily on [BaseChatMessageHistory](https://python.langchain.com/api_reference/core/runnables/langchain_core.runnables.history.RunnableWithMessageHistory.html#langchain_core.runnables.history.RunnableWithMessageHistory). `BaseChatMessageHistory` is a simple persistence layer for a chat history that can be used to store and retrieve messages in a conversation. At this time, the only option for orchestrating LangChain chains was via [LCEL](https://python.langchain.com/docs/how_to/#langchain-expression-language-lcel). When using `LCEL`, memory can be added using the [RunnableWithMessageHistory](https://python.langchain.com/api_reference/core/runnables/langchain_core.runnables.history.RunnableWithMessageHistory.html#langchain_core.runnables.history.RunnableWithMessageHistory) interface. While this option is sufficient for building a simple chat application, many users found the API to be unintuitive and difficult to work with.
`BaseChatMessageHistory`
As of LangChain v0.3, we are commending that new code rely on LangGraph for both orchestration and persistence.
At this stage, the only option for orchestrating LangChain chains was via [LCEL](https://python.langchain.com/docs/how_to/#langchain-expression-language-lcel). So users were expected to use `BaseChatMessageHistory` in conjunction with `LCEL` to manage memory in LangChain via the
[RunnableWithMessageHistory](https://python.langchain.com/api_reference/core/runnables/langchain_core.runnables.history.RunnableWithMessageHistory.html#langchain_core.runnables.history.RunnableWithMessageHistory) interface.
Specifically, for orchestration instead of writing `LCEL` code, users can define LangGraph [graphs](https://langchain-ai.github.io/langgraph/concepts/low_level/). This allows users to keep using `LCEL` within individual nodes when `LCEL` is needed, while
making it easy to define complex orchestration logic that is more readable and maintainable.
While this option is more than sufficient for a simple chat application, many users found the API
to be unintuitive and difficult to work with.
As of LangChain v0.3, we are recommending that any new code gets written with new LangGraph persistence in mind.
For persistence, users can use LangGraph's [persistence](https://langchain-ai.github.io/langgraph/concepts/persistence/) feature to store and retrieve data from a graph database. LangGraph persistence is extremely flexible and can support a much wider range of use cases than the `RunnableWithMessageHistory` interface.
:::important
If you have been using `RunnableWithMessageHistory` in your code, you do not need to make any changes. We do not plan on deprecating this functionality in the near future. This functionality is sufficient for simple chat applications and any code that uses `RunnableWithMessageHistory` will continue to work as expected.
If you have been using `RunnableWithMessageHistory` or `BaseChatMessageHistory`, you do not need to make any changes. We do not plan on deprecating either functionality in the near future. This functionality is sufficient for simple chat applications and any code that uses `RunnableWithMessageHistory` will continue to work as expected.
:::