From 43c9bd869f03efe2db800c16eb8b828b9f823675 Mon Sep 17 00:00:00 2001 From: Harrison Chase Date: Fri, 9 Dec 2022 12:40:24 -0800 Subject: [PATCH] add memprompt docs (#294) --- docs/explanation/glossary.md | 7 +++++++ docs/getting_started/memory.ipynb | 6 +++--- 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/docs/explanation/glossary.md b/docs/explanation/glossary.md index efadebd6bfe..ed8443204a7 100644 --- a/docs/explanation/glossary.md +++ b/docs/explanation/glossary.md @@ -72,3 +72,10 @@ Encouraging the model to think a certain way by including the start of the model Resources: - [Example](https://twitter.com/goodside/status/1583262455207460865?s=20&t=8Hz7XBnK1OF8siQrxxCIGQ) + +### MemPrompt + +MemPrompt maintains a memory of errors and user feedback, and uses them to prevent repetition of mistakes. + +Resources: +- [Paper](https://memprompt.com/) diff --git a/docs/getting_started/memory.ipynb b/docs/getting_started/memory.ipynb index 6b297f3c2ba..c4f1bc466fa 100644 --- a/docs/getting_started/memory.ipynb +++ b/docs/getting_started/memory.ipynb @@ -6,7 +6,7 @@ "metadata": {}, "source": [ "# Memory\n", - "So far, all the chains and agents we've gone through have been stateless. But often, you may want a chain or agent to have some concept of \"memory\" so that it may remember information about its previous interactions. The most clear and simple example of this is when designing a chatbot - you want it to remember previous messages so it can use context from that to have a better conversation. This would be a type of \"short-term memory\". On the more complex side, you could imagine a chain/agent remembering key pieces of information over time - this would be a form of \"long-term memory\".\n", + "So far, all the chains and agents we've gone through have been stateless. But often, you may want a chain or agent to have some concept of \"memory\" so that it may remember information about its previous interactions. The most clear and simple example of this is when designing a chatbot - you want it to remember previous messages so it can use context from that to have a better conversation. This would be a type of \"short-term memory\". On the more complex side, you could imagine a chain/agent remembering key pieces of information over time - this would be a form of \"long-term memory\". For more concrete ideas on the later, see this [awesome paper](https://memprompt.com/).\n", "\n", "LangChain provides several specially created chains just for this purpose. This notebook walk throughs using one of those chains (the `ConversationChain`) with two different types of memory." ] @@ -297,7 +297,7 @@ "source": [ "### More Resources on Memory\n", "\n", - "This just scratches the surface of what you can do with memory. For more examples on things like how to implement custom memory classes, how to add memory to a custom LLM chain and how to use memory with and agent, please see the [How-To: Memory](../../examples/memory) section." + "This just scratches the surface of what you can do with memory. For more examples on things like how to implement custom memory classes, how to add memory to a custom LLM chain and how to use memory with and agent, please see the [How-To: Memory](../../examples/memory) section. For even more advanced ideas on memory (which will hopefully be included in LangChain soon!) see the [MemPrompt](https://memprompt.com/) paper." ] }, { @@ -325,7 +325,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.6" + "version": "3.9.1" } }, "nbformat": 4,