Merge pull request #96 from cpacker/cli-overhaul

CLI overhaul

.github/workflows/main.yml

@@ -23,5 +23,6 @@ jobs:
         python -m pip install --upgrade pip
         pip install -r requirements.txt
 
-    - name: Run main.py
-      run: python main.py
+    - name: Run main.py with input
+      run: |
+        echo -e "\n\n\nn" | python main.py

.gitignore

@@ -79,3 +79,6 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+
+# MemGPT config files
+configs/

README.md

@@ -77,13 +77,6 @@ Install dependencies:
 pip install -r requirements.txt
 ```
 
-Extra step for Windows:
-
-```sh
-# only needed on Windows
-pip install pyreadline3
-```
-
 Add your OpenAI API key to your environment:
 
 ```sh
@@ -117,6 +110,12 @@ python main.py --use_azure_openai
 
 To create a new starter user or starter persona (that MemGPT gets initialized with), create a new `.txt` file in [/memgpt/humans/examples](/memgpt/humans/examples) or [/memgpt/personas/examples](/memgpt/personas/examples), then use the `--persona` or `--human` flag when running `main.py`. For example:
 
+```sh
+# assuming you created a new file /memgpt/humans/examples/me.txt
+python main.py
+# Select me.txt during configuration process
+```
+-- OR --
 ```sh
 # assuming you created a new file /memgpt/humans/examples/me.txt
 python main.py --human me.txt
@@ -125,6 +124,11 @@ python main.py --human me.txt
 ### GPT-3.5 support
 You can run MemGPT with GPT-3.5 as the LLM instead of GPT-4:
 ```sh
+python main.py
+# Select gpt-3.5 during configuration process
+```
+-- OR --
+```sh
 python main.py --model gpt-3.5-turbo
 ```
 
@@ -136,6 +140,15 @@ Please report any bugs you encounter regarding MemGPT running on GPT-3.5 to  htt
 You can run MemGPT with local LLMs too. See [instructions here](/memgpt/local_llm) and report any bugs/improvements here https://github.com/cpacker/MemGPT/discussions/67.
 
 ### `main.py` flags
+```text
+--first
+  allows you to send the first message in the chat (by default, MemGPT will send the first message)
+--debug
+  enables debugging output
+```
+
+<details>
+<summary>Configure via legacy flags</summary>
 
 ```text
 --model
@@ -144,10 +157,6 @@ You can run MemGPT with local LLMs too. See [instructions here](/memgpt/local_ll
   load a specific persona file
 --human
   load a specific human file
---first
-  allows you to send the first message in the chat (by default, MemGPT will send the first message)
---debug
-  enables debugging output
 --archival_storage_faiss_path=<ARCHIVAL_STORAGE_FAISS_PATH>
   load in document database (backed by FAISS index)
 --archival_storage_files="<ARCHIVAL_STORAGE_FILES_GLOB_PATTERN>"
@@ -157,6 +166,8 @@ You can run MemGPT with local LLMs too. See [instructions here](/memgpt/local_ll
 --archival_storage_sqldb=<SQLDB_PATH>
   load in SQL database
 ```
+</details>
+
 
 ### Interactive CLI commands
 
@@ -165,8 +176,6 @@ These are the commands for the CLI, **not the Discord bot**! The Discord bot has
 While using MemGPT via the CLI (not Discord!) you can run various commands:
 
 ```text
-//
-  enter multiline input mode (type // again when done)
 /exit
   exit the CLI
 /save