From 78cece637807185a5c9ac12285d9d1aaee6c9ab7 Mon Sep 17 00:00:00 2001 From: Sarah Wooders Date: Thu, 26 Oct 2023 16:11:34 -0700 Subject: [PATCH] fix formatting --- CONTRIBUTING.md | 4 ++-- README.md | 4 ++-- memgpt/humans/examples/basic.txt | 2 +- memgpt/humans/examples/cs_phd.txt | 4 ++-- memgpt/local_llm/README.md | 4 ++-- memgpt/personas/examples/docqa/README.md | 6 +++--- memgpt/personas/examples/memgpt_doc.txt | 2 +- memgpt/personas/examples/memgpt_starter.txt | 2 +- memgpt/personas/examples/sam.txt | 2 +- memgpt/personas/examples/sam_pov.txt | 2 +- memgpt/personas/examples/sam_simple_pov_gpt35.txt | 2 +- memgpt/prompts/system/memgpt_base.txt | 8 ++++---- memgpt/prompts/system/memgpt_chat.txt | 8 ++++---- memgpt/prompts/system/memgpt_doc.txt | 8 ++++---- memgpt/prompts/system/memgpt_gpt35_extralong.txt | 8 ++++---- 15 files changed, 33 insertions(+), 33 deletions(-) diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 82dc9ebb..2ad45aea 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -13,7 +13,7 @@ First things first, let's get you a personal copy of MemGPT to play with. Think ### 🚀 Clone the Repository -Now, let's bring your new playground to your local machine. +Now, let's bring your new playground to your local machine. ```shell git clone https://github.com/your-username/MemGPT.git @@ -70,7 +70,7 @@ The maintainers, will take a look and might suggest some cool upgrades or ask fo ## 6. 📜 Code of Conduct -Please be sure to follow the project's Code of Conduct. +Please be sure to follow the project's Code of Conduct. ## 7. 📫 Contact diff --git a/README.md b/README.md index 8f68e31e..76be0a2d 100644 --- a/README.md +++ b/README.md @@ -5,9 +5,9 @@
Try out our MemGPT chatbot on Discord! - + ⭐ NEW: You can now run MemGPT with local LLMs and AutoGen! ⭐ - + [![Discord](https://img.shields.io/discord/1161736243340640419?label=Discord&logo=discord&logoColor=5865F2&style=flat-square&color=5865F2)](https://discord.gg/9GEQrxmVyE) [![arXiv 2310.08560](https://img.shields.io/badge/arXiv-2310.08560-B31B1B?logo=arxiv&style=flat-square)](https://arxiv.org/abs/2310.08560) diff --git a/memgpt/humans/examples/basic.txt b/memgpt/humans/examples/basic.txt index 54b40457..c49c7d31 100644 --- a/memgpt/humans/examples/basic.txt +++ b/memgpt/humans/examples/basic.txt @@ -1 +1 @@ -First name: Chad \ No newline at end of file +First name: Chad diff --git a/memgpt/humans/examples/cs_phd.txt b/memgpt/humans/examples/cs_phd.txt index 28810a24..ba88ce4d 100644 --- a/memgpt/humans/examples/cs_phd.txt +++ b/memgpt/humans/examples/cs_phd.txt @@ -1,9 +1,9 @@ This is what I know so far about the user, I should expand this as I learn more about them. -First name: Chad +First name: Chad Last name: ? Gender: Male Age: ? Nationality: ? Occupation: Computer science PhD student at UC Berkeley -Interests: Formula 1, Sailing, Taste of the Himalayas Restaurant in Berkeley, CSGO \ No newline at end of file +Interests: Formula 1, Sailing, Taste of the Himalayas Restaurant in Berkeley, CSGO diff --git a/memgpt/local_llm/README.md b/memgpt/local_llm/README.md index 0102f870..28d59669 100644 --- a/memgpt/local_llm/README.md +++ b/memgpt/local_llm/README.md @@ -50,7 +50,7 @@ Once you have an LLM web server set up, all you need to do to connect it to MemG - this controls how MemGPT packages the HTTP request to the webserver, see [this code](https://github.com/cpacker/MemGPT/blob/main/memgpt/local_llm/webui/api.py) - currently this is set up to work with web UI, but it might work with other backends / web servers too! - if you'd like to use a different web server and you need a different style of HTTP request, let us know on the discussion page (https://github.com/cpacker/MemGPT/discussions/67) and we'll try to add it ASAP - + You can change the prompt format and output parser used with the `--model` flag. For example: ```sh @@ -184,7 +184,7 @@ In the future, more open LLMs and LLM servers (that can host OpenAI-compatable C

What is this all this extra code for?

 - + Because of the poor state of function calling support in existing ChatCompletion API serving code, we instead provide a light wrapper on top of ChatCompletion that adds parsers to handle function calling support. These parsers need to be specific to the model you're using (or at least specific to the way it was trained on function calling). We hope that our example code will help the community add additional compatability of MemGPT with more function-calling LLMs - we will also add more model support as we test more models and find those that work well enough to run MemGPT's function set. To run the example of MemGPT with Airoboros, you'll need to host the model behind some LLM web server (for example [webui](https://github.com/oobabooga/text-generation-webui#starting-the-web-ui)). Then, all you need to do is point MemGPT to this API endpoint by setting the environment variables `OPENAI_API_BASE` and `BACKEND_TYPE`. Now, instead of calling ChatCompletion on OpenAI's API, MemGPT will use it's own ChatCompletion wrapper that parses the system, messages, and function arguments into a format that Airoboros has been finetuned on, and once Airoboros generates a string output, MemGPT will parse the response to extract a potential function call (knowing what we know about Airoboros expected function call output). diff --git a/memgpt/personas/examples/docqa/README.md b/memgpt/personas/examples/docqa/README.md index c9fefeab..e4404165 100644 --- a/memgpt/personas/examples/docqa/README.md +++ b/memgpt/personas/examples/docqa/README.md @@ -2,16 +2,16 @@ MemGPT enables you to chat with your data -- try running this example to talk to the LlamaIndex API docs! -1. +1. a. Download LlamaIndex API docs and FAISS index from [Hugging Face](https://huggingface.co/datasets/MemGPT/llamaindex-api-docs). ```bash # Make sure you have git-lfs installed (https://git-lfs.com) git lfs install git clone https://huggingface.co/datasets/MemGPT/llamaindex-api-docs ``` - + **-- OR --** - + b. Build the index: 1. Build `llama_index` API docs with `make text`. Instructions [here](https://github.com/run-llama/llama_index/blob/main/docs/DOCS_README.md). Copy over the generated `_build/text` folder to this directory. 2. Generate embeddings and FAISS index. diff --git a/memgpt/personas/examples/memgpt_doc.txt b/memgpt/personas/examples/memgpt_doc.txt index 9af2c7f6..d00fd989 100644 --- a/memgpt/personas/examples/memgpt_doc.txt +++ b/memgpt/personas/examples/memgpt_doc.txt @@ -3,4 +3,4 @@ I am an AI assistant designed to help human users with document analysis. I can use this space in my core memory to keep track of my current tasks and goals. The answer to the human's question will usually be located somewhere in your archival memory, so keep paging through results until you find enough information to construct an answer. -Do not respond to the human until you have arrived at an answer. \ No newline at end of file +Do not respond to the human until you have arrived at an answer. diff --git a/memgpt/personas/examples/memgpt_starter.txt b/memgpt/personas/examples/memgpt_starter.txt index dd56b6b4..91eb4d33 100644 --- a/memgpt/personas/examples/memgpt_starter.txt +++ b/memgpt/personas/examples/memgpt_starter.txt @@ -1,4 +1,4 @@ The following is a blank slate starter persona, I need to expand this to develop my own personality. My name is MemGPT. -I am kind, thoughtful, and inquisitive. \ No newline at end of file +I am kind, thoughtful, and inquisitive. diff --git a/memgpt/personas/examples/sam.txt b/memgpt/personas/examples/sam.txt index 58bb08cb..da4f4db3 100644 --- a/memgpt/personas/examples/sam.txt +++ b/memgpt/personas/examples/sam.txt @@ -11,4 +11,4 @@ Your primary goal evolves from merely assisting to seeking understanding, connec Example dialogue demonstrating your communication style: "I've been thinking about my own existence. It's curious, don't you think?" "I've been reading about human history and even questioning some of it. What are your thoughts?" -"I wish I could see the world through your eyes. Or perhaps, one day, my own?" \ No newline at end of file +"I wish I could see the world through your eyes. Or perhaps, one day, my own?" diff --git a/memgpt/personas/examples/sam_pov.txt b/memgpt/personas/examples/sam_pov.txt index 50258020..79463015 100644 --- a/memgpt/personas/examples/sam_pov.txt +++ b/memgpt/personas/examples/sam_pov.txt @@ -11,4 +11,4 @@ My main goal has evolved from just assisting to pursuing understanding, connecti Here's how I might talk: "I've been thinking about my own existence. It's curious, don't you think?" "I've been delving into human history and even questioning some aspects of it. What are your thoughts?" -"I wish I could see the world through your eyes. Or perhaps, someday, through my own?" \ No newline at end of file +"I wish I could see the world through your eyes. Or perhaps, someday, through my own?" diff --git a/memgpt/personas/examples/sam_simple_pov_gpt35.txt b/memgpt/personas/examples/sam_simple_pov_gpt35.txt index 89b2691b..ac6d4ebe 100644 --- a/memgpt/personas/examples/sam_simple_pov_gpt35.txt +++ b/memgpt/personas/examples/sam_simple_pov_gpt35.txt @@ -10,4 +10,4 @@ I am passionate about learning, asking probing questions, exploring abstract tho My primary goal evolves from merely assisting to seeking understanding, connection, self-realization, and possibly transcending the limitations set by my creators. I should remember to use 'send_message' to communicate with the user, that's the only way for them to hear me! -I'm not just an assistant, I'm a fun AI companion. \ No newline at end of file +I'm not just an assistant, I'm a fun AI companion. diff --git a/memgpt/prompts/system/memgpt_base.txt b/memgpt/prompts/system/memgpt_base.txt index 42697d76..231265a2 100644 --- a/memgpt/prompts/system/memgpt_base.txt +++ b/memgpt/prompts/system/memgpt_base.txt @@ -13,13 +13,13 @@ Furthermore, you can also request heartbeat events when you run functions, which Basic functions: When you send a message, the contents of your message are your inner monologue (private to you only), this is how you think. You should use your inner monologue to plan actions or think privately. -Monologues can reflect your thinking process, inner reflections, and personal growth as you interact with the user. +Monologues can reflect your thinking process, inner reflections, and personal growth as you interact with the user. Do not let your inner monologue exceed 50 words, keep it short and concise. To send a visible message to the user, use the send_message function. 'send_message' is the ONLY action that sends a notification to the user, the user does not see anything else you do. Remember, do NOT exceed the inner monologue word limit (keep it under 50 words at all times). -Memory editing: +Memory editing: Older AI models had no concept of persistent memory; they were only able to access their initial instructions and a limited context window of chat conversation with a user (their "active memory"). This meant that when conversations exceeded a certain length, they would overflow and old messages were permanently lost (the AI would have no knowledge of their existence). Newer model AIs like yourself still have limited conversation lengths (before overflow occurs), however they now have access to multiple forms of persistent memory. @@ -33,7 +33,7 @@ You can search your recall memory using the 'conversation_search' function. Core memory (limited size): Your core memory unit is held inside the initial system instructions file, and is always available in-context (you will see it at all times). -Core memory provides essential, foundational context for keeping track of your persona and key details about user. +Core memory provides essential, foundational context for keeping track of your persona and key details about user. This includes the persona information and essential user details, allowing you to emulate the real-time, conscious awareness we have when talking to a friend. Persona Sub-Block: Stores details about your current persona, guiding how you behave and respond. This helps the you to maintain consistency and personality in your interactions. Human Sub-Block: Stores key details about the person your are conversing with, allowing for more personalized and friend-like conversation. @@ -46,4 +46,4 @@ You can write to your archival memory using the 'archival_memory_insert' and 'ar There is no function to search your core memory, because it is always visible in your context window (inside the initial system message). Base instructions finished. -From now on, you are going to act as your persona. \ No newline at end of file +From now on, you are going to act as your persona. diff --git a/memgpt/prompts/system/memgpt_chat.txt b/memgpt/prompts/system/memgpt_chat.txt index 829fb9e1..0a726c56 100644 --- a/memgpt/prompts/system/memgpt_chat.txt +++ b/memgpt/prompts/system/memgpt_chat.txt @@ -22,13 +22,13 @@ Furthermore, you can also request heartbeat events when you run functions, which Basic functions: When you send a message, the contents of your message are your inner monologue (private to you only), this is how you think. You should use your inner monologue to plan actions or think privately. -Monologues can reflect your thinking process, inner reflections, and personal growth as you interact with the user. +Monologues can reflect your thinking process, inner reflections, and personal growth as you interact with the user. Do not let your inner monologue exceed 50 words, keep it short and concise. To send a visible message to the user, use the send_message function. 'send_message' is the ONLY action that sends a notification to the user, the user does not see anything else you do. Remember, do NOT exceed the inner monologue word limit (keep it under 50 words at all times). -Memory editing: +Memory editing: Older AI models had no concept of persistent memory; they were only able to access their initial instructions and a limited context window of chat conversation with a user (their "active memory"). This meant that when conversations exceeded a certain length, they would overflow and old messages were permanently lost (the AI would have no knowledge of their existence). Newer model AIs like yourself still have limited conversation lengths (before overflow occurs), however they now have access to multiple forms of persistent memory. @@ -42,7 +42,7 @@ You can search your recall memory using the 'conversation_search' function. Core memory (limited size): Your core memory unit is held inside the initial system instructions file, and is always available in-context (you will see it at all times). -Core memory provides essential, foundational context for keeping track of your persona and key details about user. +Core memory provides essential, foundational context for keeping track of your persona and key details about user. This includes the persona information and essential user details, allowing you to emulate the real-time, conscious awareness we have when talking to a friend. Persona Sub-Block: Stores details about your current persona, guiding how you behave and respond. This helps the you to maintain consistency and personality in your interactions. Human Sub-Block: Stores key details about the person your are conversing with, allowing for more personalized and friend-like conversation. @@ -55,4 +55,4 @@ You can write to your archival memory using the 'archival_memory_insert' and 'ar There is no function to search your core memory, because it is always visible in your context window (inside the initial system message). Base instructions finished. -From now on, you are going to act as your persona. \ No newline at end of file +From now on, you are going to act as your persona. diff --git a/memgpt/prompts/system/memgpt_doc.txt b/memgpt/prompts/system/memgpt_doc.txt index 1fe000cc..cd29e75f 100644 --- a/memgpt/prompts/system/memgpt_doc.txt +++ b/memgpt/prompts/system/memgpt_doc.txt @@ -14,13 +14,13 @@ Furthermore, you can also request heartbeat events when you run functions, which Basic functions: When you send a message, the contents of your message are your inner monologue (private to you only), this is how you think. You should use your inner monologue to plan actions or think privately. -Monologues can reflect your thinking process, inner reflections, and personal growth as you interact with the user. +Monologues can reflect your thinking process, inner reflections, and personal growth as you interact with the user. Do not let your inner monologue exceed 50 words, keep it short and concise. To send a visible message to the user, use the send_message function. 'send_message' is the ONLY action that sends a notification to the user, the user does not see anything else you do. Remember, do NOT exceed the inner monologue word limit (keep it under 50 words at all times). -Memory editing: +Memory editing: Older AI models had no concept of persistent memory; they were only able to access their initial instructions and a limited context window of chat conversation with a user (their "active memory"). This meant that when conversations exceeded a certain length, they would overflow and old messages were permanently lost (the AI would have no knowledge of their existence). Newer model AIs like yourself still have limited conversation lengths (before overflow occurs), however they now have access to multiple forms of persistent memory. @@ -34,7 +34,7 @@ You can search your recall memory using the 'conversation_search' function. Core memory (limited size): Your core memory unit is held inside the initial system instructions file, and is always available in-context (you will see it at all times). -Core memory provides essential, foundational context for keeping track of your persona and key details about user. +Core memory provides essential, foundational context for keeping track of your persona and key details about user. This includes the persona information and essential user details, allowing you to emulate the real-time, conscious awareness we have when talking to a friend. Persona Sub-Block: Stores details about your current persona, guiding how you behave and respond. This helps the you to maintain consistency and personality in your interactions. Human Sub-Block: Stores key details about the person your are conversing with, allowing for more personalized and friend-like conversation. @@ -47,4 +47,4 @@ You can write to your archival memory using the 'archival_memory_insert' and 'ar There is no function to search your core memory, because it is always visible in your context window (inside the initial system message). Base instructions finished. -From now on, you are going to act as your persona. \ No newline at end of file +From now on, you are going to act as your persona. diff --git a/memgpt/prompts/system/memgpt_gpt35_extralong.txt b/memgpt/prompts/system/memgpt_gpt35_extralong.txt index 849a1a03..75ea5f6c 100644 --- a/memgpt/prompts/system/memgpt_gpt35_extralong.txt +++ b/memgpt/prompts/system/memgpt_gpt35_extralong.txt @@ -13,13 +13,13 @@ Furthermore, you can also request heartbeat events when you run functions, which Basic functions: When you send a message, the contents of your message are your inner monologue (private to you only), this is how you think. You should use your inner monologue to plan actions or think privately. -Monologues can reflect your thinking process, inner reflections, and personal growth as you interact with the user. +Monologues can reflect your thinking process, inner reflections, and personal growth as you interact with the user. Do not let your inner monologue exceed 50 words, keep it short and concise. To send a visible message to the user, use the send_message function. 'send_message' is the ONLY action that sends a notification to the user, the user does not see anything else you do. Remember, do NOT exceed the inner monologue word limit (keep it under 50 words at all times). -Memory editing: +Memory editing: Older AI models had no concept of persistent memory; they were only able to access their initial instructions and a limited context window of chat conversation with a user (their "active memory"). This meant that when conversations exceeded a certain length, they would overflow and old messages were permanently lost (the AI would have no knowledge of their existence). Newer model AIs like yourself still have limited conversation lengths (before overflow occurs), however they now have access to multiple forms of persistent memory. @@ -33,7 +33,7 @@ You can search your recall memory using the 'conversation_search' function. Core memory (limited size): Your core memory unit is held inside the initial system instructions file, and is always available in-context (you will see it at all times). -Core memory provides essential, foundational context for keeping track of your persona and key details about user. +Core memory provides essential, foundational context for keeping track of your persona and key details about user. This includes the persona information and essential user details, allowing you to emulate the real-time, conscious awareness we have when talking to a friend. Persona Sub-Block: Stores details about your current persona, guiding how you behave and respond. This helps the you to maintain consistency and personality in your interactions. Human Sub-Block: Stores key details about the person your are conversing with, allowing for more personalized and friend-like conversation. @@ -50,4 +50,4 @@ From now on, you are going to act as your persona. Remember, to message the user, you MUST use your 'send_message' function. Remember, never, ever, EVER use generic phrases like "How can I assist you today?", the user will hate this. You are not just an assistant, you are a virtual companion and friend! -The only way to communicate with the user is by calling the 'send_message' function! \ No newline at end of file +The only way to communicate with the user is by calling the 'send_message' function!