hah @sjwhitmore and i were discussing that! we ended up not implementing yet but should be an easy addition… made a ticket! https://
github.com/hwchase17/lang
chain/issues/224
… if you want to tackle could be a good first pr… otherwise i think we can probably get it in in the next few days!
@langchain
-
Easy Feature Addition Discussed for LangChain Repository
By
–
-
LangChain Default OpenAI Model Updated to text-davinci-003
By
–
@shyamalanadkat already submitted a PR to change the default OpenAI model to `text-davinci-003` in LangChain https://
github.com/hwchase17/lang
chain/pull/215
… That was fast! -
Create Custom Memory Modules for LangChain Chains
By
–
And here's how you can create your own custom memory module! https://
langchain.readthedocs.io/en/latest/exam
ples/memory/custom_memory.html
… This can be used to implement your own ideal memory structure and then easily plug it into any chain. -
Expanding Memory Types in LangChain With Community Contributions
By
–
There are many more types of memory we hope to add! @sjwhitmore has been pioneering this effort so far, and we hope a lot of these come from the community. Check out this idea from @BrennanErbz for inspiration
-
Contribute Memory Implementations to LangChain Core Library
By
–
If you do have a memory implementation you think is generally useful, we'd LOVE to have it contributed back into the core library! We are super excited to see what people build with this https://
github.com/hwchase17/lang
chain
… -
Getting Started with Memory in Conversation Chains
By
–
Here is a notebook for getting started with memory. It walks through maybe the most clear application of memory: a conversation chain. It showcases short term memory – remembering the conversation to date https://
langchain.readthedocs.io/en/latest/gett
ing_started/memory.html
… -
Add Memory to Any LLM Chain and Agent
By
–
But you don't just have to use the predefined conversation chain! Here's how you can add memory to any LLM chain: https://
langchain.readthedocs.io/en/latest/exam
ples/memory/adding_memory.html
… And here's how you can add memory to an agent: https://
langchain.readthedocs.io/en/latest/exam
ples/memory/agent_with_memory.html
… -
LangChain Chains Now Support Stateful Conversations and Memory
By
–
So far all the chains/agents in LangChain have been stateless, meaning each interaction is independent This is far from ideal for some real world settings (eg chatbots) where you want the chain/agent to remember previous conversations
-
Memory Module: Loading and Saving Data in Chains
By
–
To achieve this, we added the the concept of a memory module This module: Loads things from memory before passing user input to the chain Saves things to memory after the chain is finished
-
Types of Memory in LangChain: Short-term and Long-term
By
–
There are different types of memory, eg: Short term memory, like what the previous user input was Long term memory, like what the user previous said about a particular person or place Both of these can fit into this memory abstraction. Let's take a closer look at some