cr

.env.template

@@ -5,8 +5,6 @@
 EXECUTE_LOCAL_COMMANDS=False
 # BROWSE_CHUNK_MAX_LENGTH - When browsing website, define the length of chunk stored in memory
 BROWSE_CHUNK_MAX_LENGTH=8192
-# BROWSE_SUMMARY_MAX_TOKEN - Define the maximum length of the summary generated by GPT agent when browsing website
-BROWSE_SUMMARY_MAX_TOKEN=300
 # USER_AGENT - Define the user-agent used by the requests library to browse website (string)
 # USER_AGENT="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36"
 # AI_SETTINGS_FILE - Specifies which AI Settings file to use (defaults to ai_settings.yaml)
@@ -54,6 +52,7 @@ SMART_TOKEN_LIMIT=8000
 # local - Default
 # pinecone - Pinecone (if configured)
 # redis - Redis (if configured)
+# milvus - Milvus (if configured)
 MEMORY_BACKEND=local
 
 ### PINECONE

.envrc

@@ -0,0 +1,4 @@
+# Upon entering directory, direnv requests user permission once to automatically load project dependencies onwards.
+# Eliminating the need of running "nix develop github:superherointj/nix-auto-gpt" for Nix users to develop/use Auto-GPT.
+
+[[ -z $IN_NIX_SHELL ]] && use flake github:superherointj/nix-auto-gpt

.github/workflows/pr-label.yml

@@ -0,0 +1,28 @@
+name: "Pull Request auto-label"
+on:
+  # So that PRs touching the same files as the push are updated
+  push:
+  # So that the `dirtyLabel` is removed if conflicts are resolve
+  # We recommend `pull_request_target` so that github secrets are available.
+  # In `pull_request` we wouldn't be able to change labels of fork PRs
+  pull_request_target:
+    types: [opened, synchronize]
+concurrency:
+  group: ${{ github.event_name == 'pull_request_target' && format('pr-label-{0}', github.event.pull_request.number) || '' }}
+  cancel-in-progress: ${{ github.event_name == 'pull_request_target' || '' }}
+
+jobs:
+  conflicts:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+    steps:
+      - name: Update PRs with conflict labels
+        uses: eps1lon/actions-label-merge-conflict@releases/2.x
+        with:
+          dirtyLabel: "conflicts"
+          #removeOnDirtyLabel: "PR: ready to ship"
+          repoToken: "${{ secrets.GITHUB_TOKEN }}"
+          commentOnDirty: "This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request."
+          commentOnClean: "Conflicts have been resolved! 🎉 A maintainer will review the pull request shortly."

.gitignore

@@ -127,6 +127,7 @@ celerybeat.pid
 *.sage.py
 
 # Environments
+.direnv/
 .env
 .venv
 env/

Dockerfile

@@ -5,6 +5,16 @@ FROM python:3.11-slim
 RUN apt-get -y update
 RUN apt-get -y install git chromium-driver
 
+# Install Xvfb and other dependencies for headless browser testing
+RUN apt-get update \
+    && apt-get install -y wget gnupg2 libgtk-3-0 libdbus-glib-1-2 dbus-x11 xvfb ca-certificates
+
+# Install Firefox / Chromium
+RUN wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | apt-key add - \
+    && echo "deb [arch=amd64] http://dl.google.com/linux/chrome/deb/ stable main" >> /etc/apt/sources.list.d/google-chrome.list \
+    && apt-get update \
+    && apt-get install -y chromium firefox-esr
+
 # Set environment variables
 ENV PIP_NO_CACHE_DIR=yes \
     PYTHONUNBUFFERED=1 \
@@ -17,8 +27,9 @@ RUN chown appuser:appuser /home/appuser
 USER appuser
 
 # Copy the requirements.txt file and install the requirements
-COPY --chown=appuser:appuser requirements-docker.txt .
-RUN pip install --no-cache-dir --user -r requirements-docker.txt
+COPY --chown=appuser:appuser requirements.txt .
+RUN sed -i '/Items below this point will not be included in the Docker Image/,$d' requirements.txt && \
+	pip install --no-cache-dir --user -r requirements.txt
 
 # Copy the application files
 COPY --chown=appuser:appuser autogpt/ ./autogpt

README.md

@@ -66,8 +66,21 @@ Development of this free, open-source project is made possible by all the <a hre
   - [Milvus](https://milvus.io/)
   - [Redis](https://redis.io)
   - [LlamaIndex](https://github.com/jerryjliu/llama_index)
+  - [Weaviate](https://weaviate.io)
 - ElevenLabs Key (If you want the AI to speak)
 
+## ⚠️ OpenAI API Keys Configuration ⚠️ 
+
+Obtain your OpenAI API key from: https://platform.openai.com/account/api-keys.
+
+To use OpenAI API key for Auto-GPT, you **NEED** to have billing set up (AKA paid account).
+
+You can set up paid account at https://platform.openai.com/account/billing/overview.
+
+![For OpenAI API key to work, set up paid account at OpenAI API > Billing](./docs/imgs/openai-api-key-billing-paid-account.png)
+
+#### **PLEASE ENSURE YOU HAVE DONE THIS STEP BEFORE PROCEEDING, OTHERWISE NOTHING WILL WORK!**
+
 ## 💾 Installation
 
 To install Auto-GPT, follow these steps:
@@ -208,18 +221,6 @@ python -m autogpt --speak
 - Adam : pNInz6obpgDQGcFmaJgB
 - Sam : yoZ06aMxZJJ28mfd3POQ
 
-
-## OpenAI API Keys Configuration
-
-Obtain your OpenAI API key from: https://platform.openai.com/account/api-keys.
-
-To use OpenAI API key for Auto-GPT, you NEED to have billing set up (AKA paid account).
-
-You can set up paid account at https://platform.openai.com/account/billing/overview.
-
-![For OpenAI API key to work, set up paid account at OpenAI API > Billing](./docs/imgs/openai-api-key-billing-paid-account.png)
-
-
 ## 🔍 Google API Keys Configuration
 
 This section is optional, use the official google api if you are having issues with error 429 when running a google search.
@@ -343,6 +344,14 @@ export MEMORY_BACKEND="pinecone"
 [Weaviate](https://weaviate.io/) is an open-source vector database. It allows to store data objects and vector embeddings from ML-models and scales seamlessly to billion of data objects. [An instance of Weaviate can be created locally (using Docker), on Kubernetes or using Weaviate Cloud Services](https://weaviate.io/developers/weaviate/quickstart). 
 Although still experimental, [Embedded Weaviate](https://weaviate.io/developers/weaviate/installation/embedded) is supported which allows the Auto-GPT process itself to start a Weaviate instance. To enable it, set `USE_WEAVIATE_EMBEDDED` to `True` and make sure you `pip install "weaviate-client>=3.15.4"`. 
 
+#### Install the Weaviate client
+
+Install the Weaviate client before usage.
+
+```
+$ pip install weaviate-client
+```
+
 
 ### LlamaIndex Setup
 

autogpt/app.py

@@ -10,7 +10,11 @@
 from autogpt.commands.image_gen import generate_image
 from autogpt.commands.audio_text import read_audio_from_file
 from autogpt.commands.web_requests import scrape_links, scrape_text
-from autogpt.commands.execute_code import execute_python_file, execute_shell
+from autogpt.commands.execute_code import (
+    execute_python_file,
+    execute_shell,
+    execute_shell_popen,
+)
 from autogpt.commands.file_operations import (
     append_to_file,
     delete_file,
@@ -191,6 +195,15 @@ def execute_command(command_name: str, arguments):
                     " shell commands, EXECUTE_LOCAL_COMMANDS must be set to 'True' "
                     "in your config. Do not attempt to bypass the restriction."
                 )
+        elif command_name == "execute_shell_popen":
+            if CFG.execute_local_commands:
+                return execute_shell_popen(arguments["command_line"])
+            else:
+                return (
+                    "You are not allowed to run local shell commands. To execute"
+                    " shell commands, EXECUTE_LOCAL_COMMANDS must be set to 'True' "
+                    "in your config. Do not attempt to bypass the restriction."
+                )
         elif command_name == "read_audio_from_file":
             return read_audio_from_file(arguments["file"])
         elif command_name == "generate_image":

autogpt/commands/execute_code.py

@@ -40,7 +40,10 @@ def execute_python_file(file: str):
     try:
         client = docker.from_env()
 
-        image_name = "python:3.10"
+        # You can replace this with the desired Python image/version
+        # You can find available Python images on Docker Hub:
+        # https://hub.docker.com/_/python
+        image_name = "python:3-alpine"
         try:
             client.images.get(image_name)
             print(f"Image '{image_name}' found locally")
@@ -57,9 +60,6 @@ def execute_python_file(file: str):
                 elif status:
                     print(status)
 
-        # You can replace 'python:3.8' with the desired Python image/version
-        # You can find available Python images on Docker Hub:
-        # https://hub.docker.com/_/python
         container = client.containers.run(
             image_name,
             f"python {file}",
@@ -114,6 +114,36 @@ def execute_shell(command_line: str) -> str:
     return output
 
 
+def execute_shell_popen(command_line):
+    """Execute a shell command with Popen and returns an english description
+    of the event and the process id
+
+    Args:
+        command_line (str): The command line to execute
+
+    Returns:
+        str: Description of the fact that the process started and its id
+    """
+    current_dir = os.getcwd()
+
+    if WORKING_DIRECTORY not in current_dir:  # Change dir into workspace if necessary
+        work_dir = os.path.join(os.getcwd(), WORKING_DIRECTORY)
+        os.chdir(work_dir)
+
+    print(f"Executing command '{command_line}' in working directory '{os.getcwd()}'")
+
+    do_not_show_output = subprocess.DEVNULL
+    process = subprocess.Popen(
+        command_line, shell=True, stdout=do_not_show_output, stderr=do_not_show_output
+    )
+
+    # Change back to whatever the prior working dir was
+
+    os.chdir(current_dir)
+
+    return f"Subprocess started with PID:'{str(process.pid)}'"
+
+
 def we_are_running_in_a_docker_container() -> bool:
     """Check if we are running in a Docker container
 

autogpt/commands/file_operations.py

@@ -70,9 +70,14 @@ def split_file(
     while start < content_length:
         end = start + max_length
         if end + overlap < content_length:
-            chunk = content[start : end + overlap]
+            chunk = content[start : end + overlap - 1]
         else:
             chunk = content[start:content_length]
+
+            # Account for the case where the last chunk is shorter than the overlap, so it has already been consumed
+            if len(chunk) <= overlap:
+                break
+
         yield chunk
         start += max_length - overlap
 

autogpt/commands/web_requests.py

@@ -58,9 +58,28 @@ def check_local_file_access(url: str) -> bool:
     """
     local_prefixes = [
         "file:///",
+        "file://localhost/",
         "file://localhost",
         "http://localhost",
+        "http://localhost/",
         "https://localhost",
+        "https://localhost/",
+        "http://2130706433",
+        "http://2130706433/",
+        "https://2130706433",
+        "https://2130706433/",
+        "http://127.0.0.1/",
+        "http://127.0.0.1",
+        "https://127.0.0.1/",
+        "https://127.0.0.1",
+        "https://0.0.0.0/",
+        "https://0.0.0.0",
+        "http://0.0.0.0/",
+        "http://0.0.0.0",
+        "http://0000",
+        "http://0000/",
+        "https://0000",
+        "https://0000/"
     ]
     return any(url.startswith(prefix) for prefix in local_prefixes)
 

autogpt/config/config.py

@@ -1,14 +1,13 @@
 """Configuration class to store the state of bools for different scripts access."""
 import os
-from colorama import Fore
-
-from autogpt.config.singleton import Singleton
 
 import openai
 import yaml
-
+from colorama import Fore
 from dotenv import load_dotenv
 
+from autogpt.config.singleton import Singleton
+
 load_dotenv(verbose=True)
 
 
@@ -33,7 +32,6 @@ def __init__(self) -> None:
         self.fast_token_limit = int(os.getenv("FAST_TOKEN_LIMIT", 4000))
         self.smart_token_limit = int(os.getenv("SMART_TOKEN_LIMIT", 8000))
         self.browse_chunk_max_length = int(os.getenv("BROWSE_CHUNK_MAX_LENGTH", 8192))
-        self.browse_summary_max_token = int(os.getenv("BROWSE_SUMMARY_MAX_TOKEN", 300))
 
         self.openai_api_key = os.getenv("OPENAI_API_KEY")
         self.temperature = float(os.getenv("TEMPERATURE", "1"))
@@ -67,15 +65,17 @@ def __init__(self) -> None:
         self.pinecone_api_key = os.getenv("PINECONE_API_KEY")
         self.pinecone_region = os.getenv("PINECONE_ENV")
 
-        self.weaviate_host  = os.getenv("WEAVIATE_HOST")
+        self.weaviate_host = os.getenv("WEAVIATE_HOST")
         self.weaviate_port = os.getenv("WEAVIATE_PORT")
         self.weaviate_protocol = os.getenv("WEAVIATE_PROTOCOL", "http")
         self.weaviate_username = os.getenv("WEAVIATE_USERNAME", None)
         self.weaviate_password = os.getenv("WEAVIATE_PASSWORD", None)
         self.weaviate_scopes = os.getenv("WEAVIATE_SCOPES", None)
         self.weaviate_embedded_path = os.getenv("WEAVIATE_EMBEDDED_PATH")
         self.weaviate_api_key = os.getenv("WEAVIATE_API_KEY", None)
-        self.use_weaviate_embedded = os.getenv("USE_WEAVIATE_EMBEDDED", "False") == "True"
+        self.use_weaviate_embedded = (
+            os.getenv("USE_WEAVIATE_EMBEDDED", "False") == "True"
+        )
 
         # milvus configuration, e.g., localhost:19530.
         self.milvus_addr = os.getenv("MILVUS_ADDR", "localhost:19530")
@@ -193,10 +193,6 @@ def set_browse_chunk_max_length(self, value: int) -> None:
         """Set the browse_website command chunk max length value."""
         self.browse_chunk_max_length = value
 
-    def set_browse_summary_max_token(self, value: int) -> None:
-        """Set the browse_website command summary max token value."""
-        self.browse_summary_max_token = value
-
     def set_openai_api_key(self, value: str) -> None:
         """Set the OpenAI API key value."""
         self.openai_api_key = value
@@ -242,5 +238,5 @@ def check_openai_api_key() -> None:
             Fore.RED
             + "Please set your OpenAI API key in .env or as an environment variable."
         )
-        print("You can get your key from https://beta.openai.com/account/api-keys")
+        print("You can get your key from https://platform.openai.com/account/api-keys")
         exit(1)

autogpt/json_fixes/auto_fix.py

@@ -45,7 +45,7 @@ def fix_json(json_string: str, schema: str) -> str:
     try:
         json.loads(result_string)  # just check the validity
         return result_string
-    except json.JSONDecodeError:  # noqa: E722
+    except json.JSONDecodeError:
         # Get the call stack:
         # import traceback
         # call_stack = traceback.format_exc()

autogpt/memory/local.py

@@ -2,13 +2,13 @@
 
 import dataclasses
 import os
-from typing import Any
+from typing import Any, List
 
 import numpy as np
 import orjson
 
-from autogpt.memory.base import MemoryProviderSingleton
 from autogpt.llm_utils import create_embedding_with_ada
+from autogpt.memory.base import MemoryProviderSingleton
 
 EMBED_DIM = 1536
 SAVE_OPTIONS = orjson.OPT_SERIALIZE_NUMPY | orjson.OPT_SERIALIZE_DATACLASS

autogpt/processing/text.py

@@ -78,7 +78,6 @@ def summarize_text(
         summary = create_chat_completion(
             model=CFG.fast_llm_model,
             messages=messages,
-            max_tokens=CFG.browse_summary_max_token,
         )
         summaries.append(summary)
         print(f"Added chunk {i + 1} summary to memory")
@@ -95,7 +94,6 @@ def summarize_text(
     return create_chat_completion(
         model=CFG.fast_llm_model,
         messages=messages,
-        max_tokens=CFG.browse_summary_max_token,
     )