Revert "nonfunctional 404 quickstart command w/ some other typo corre…

…ctions"

This reverts commit 39fb511.

memgpt/cli/cli.py

@@ -1,6 +1,5 @@
 import typer
 import json
-import requests
 import sys
 import io
 import logging
@@ -26,34 +25,6 @@
 from memgpt.server.constants import WS_DEFAULT_PORT, REST_DEFAULT_PORT
 
 
-class QuickstartChoice(Enum):
-    # openai = "openai"
-    # azure = "azure"
-    memgpt_hosted = "memgpt"
-
-
-def quickstart(
-    type: QuickstartChoice = typer.Option("memgpt", help="Quickstart setup type"),
-):
-    """Set the base config file with a single command"""
-    if type == QuickstartChoice.memgpt_hosted:
-        # Download the latest memgpt hosted config
-        url = "https://raw.githubusercontent.com/cpacker/MemGPT/main/configs/memgpt_hosted.json"
-        response = requests.get(url)
-
-        # Check if the request was successful
-        if response.status_code == 200:
-            # Parse the response content as JSON
-            config = response.json()
-            # Output a success message and the first few items in the dictionary as a sample
-            print("JSON file downloaded and loaded into a dictionary successfully.")
-        else:
-            print(f"Failed to download config from {url}. Status code:", response.status_code)
-
-    else:
-        raise NotImplementedError(type)
-
-
 def open_folder():
     """Open a folder viewer of the MemGPT home directory"""
     try:

memgpt/local_llm/chat_completion_proxy.py

@@ -54,7 +54,7 @@ def get_chat_completion(
         # Warn the user that we're using the fallback
         if not has_shown_warning:
             print(
-                f"{CLI_WARNING_PREFIX}no wrapper specified for local LLM, using the default wrapper (you can remove this warning by specifying the wrapper with --model-wrapper)"
+                f"{CLI_WARNING_PREFIX}no wrapper specified for local LLM, using the default wrapper (you can remove this warning by specifying the wrapper with --wrapper)"
             )
             has_shown_warning = True
         if endpoint_type in ["koboldcpp", "llamacpp", "webui"]:

memgpt/local_llm/vllm/api.py

@@ -18,7 +18,7 @@ def get_vllm_completion(endpoint, model, prompt, context_window, user, settings=
     # Settings for the generation, includes the prompt + stop tokens, max length, etc
     request = settings
     request["prompt"] = prompt
-    request["max_tokens"] = 3000  # int(context_window - prompt_tokens)
+    request["max_tokens"] = int(context_window - prompt_tokens)
     request["stream"] = False
     request["user"] = user
 

memgpt/main.py

@@ -21,7 +21,7 @@
 import memgpt.agent as agent
 import memgpt.system as system
 import memgpt.constants as constants
-from memgpt.cli.cli import run, attach, version, server, open_folder, quickstart
+from memgpt.cli.cli import run, attach, version, server, open_folder
 from memgpt.cli.cli_config import configure, list, add
 from memgpt.cli.cli_load import app as load_app
 from memgpt.connectors.storage import StorageConnector
@@ -35,7 +35,6 @@
 app.command(name="add")(add)
 app.command(name="server")(server)
 app.command(name="folder")(open_folder)
-app.command(name="quickstart")(quickstart)
 # load data commands
 app.add_typer(load_app, name="load")