Sync release v0.4.1 back into master (#4741)

.github/workflows/ci.yml

@@ -7,18 +7,18 @@ on:
       - 'tests/Auto-GPT-test-cassettes'
       - 'tests/challenges/current_score.json'
   pull_request:
-    branches: [ stable, master ]
+    branches: [ stable, master, release-* ]
   pull_request_target:
-    branches: [ master, ci-test* ]
+    branches: [ master, release-*, ci-test* ]
 
 concurrency:
-  group: ${{ format('ci-{0}', github.head_ref && format('pr-{0}', github.event.pull_request.number) || github.sha) }}
-  cancel-in-progress: ${{ startsWith(github.event_name, 'pull_request') && github.event.pull_request.head.repo.fork == (github.event_name == 'pull_request_target') }}
+  group: ${{ format('ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
+  cancel-in-progress: ${{ startsWith(github.event_name, 'pull_request') }}
 
 jobs:
   lint:
-    # eliminate duplicate runs on master
-    if: github.event_name == 'push' || github.base_ref != 'master' || (github.event.pull_request.head.repo.fork == (github.event_name == 'pull_request_target'))
+    # eliminate duplicate runs
+    if: github.event_name == 'push' || (github.event.pull_request.head.repo.fork == (github.event_name == 'pull_request_target'))
 
     runs-on: ubuntu-latest
     env:
@@ -73,8 +73,8 @@ jobs:
           $cmd --check || (echo "You have unused imports or pass statements, please run '${cmd} --in-place'" && exit 1)
 
   test:
-    # eliminate duplicate runs on master
-    if: github.event_name == 'push' || github.base_ref != 'master' || (github.event.pull_request.head.repo.fork == (github.event_name == 'pull_request_target'))
+    # eliminate duplicate runs
+    if: github.event_name == 'push' || (github.event.pull_request.head.repo.fork == (github.event_name == 'pull_request_target'))
 
     permissions:
       # Gives the action the necessary permissions for publishing new

.github/workflows/docker-ci.yml

@@ -7,7 +7,7 @@ on:
       - 'tests/Auto-GPT-test-cassettes'
       - 'tests/challenges/current_score.json'
   pull_request:
-    branches: [ master, stable ]
+    branches: [ master, release-*, stable ]
 
 concurrency:
   group: ${{ format('docker-ci-{0}', github.head_ref && format('pr-{0}', github.event.pull_request.number) || github.sha) }}

.github/workflows/pr-label.yml

@@ -3,7 +3,7 @@ name: "Pull Request auto-label"
 on:
   # So that PRs touching the same files as the push are updated
   push:
-    branches: [ master ]
+    branches: [ master, release-* ]
     paths-ignore:
       - 'tests/Auto-GPT-test-cassettes'
       - 'tests/challenges/current_score.json'

BULLETIN.md

@@ -3,45 +3,25 @@ Check out *https://agpt.co*, the official news & updates site for Auto-GPT!
 The documentation also has a place here, at *https://docs.agpt.co*
 
 # For contributors 👷🏼
-Since releasing v0.3.0, we are working on re-architecting the Auto-GPT core to make
-it more extensible and to make room for structural performance-oriented R&D.
-In the meantime, we have less time to process incoming pull requests and issues,
-so we focus on high-value contributions:
- * significant bugfixes
- * *major* improvements to existing functionality and/or docs (so no single-typo fixes)
- * contributions that help us with re-architecture and other roadmapped items
-We have to be somewhat selective in order to keep making progress, but this does not
-mean you can't contribute. Check out the contribution guide on our wiki:
+Since releasing v0.3.0, whave been working on re-architecting the Auto-GPT core to make it more extensible and make room for structural performance-oriented R&D.
+
+Check out the contribution guide on our wiki:
 https://github.com/Significant-Gravitas/Auto-GPT/wiki/Contributing
 
-# 🚀 v0.4.0 Release 🚀
-Two weeks and 76 pull requests have passed since v0.3.1, and we are happy to announce
-the release of v0.4.0!
+# 🚀 v0.4.1 Release 🚀
+Two weeks and 50+ pull requests have passed since v0.4.0, and we are happy to announce the release of v0.4.1!
 
-Highlights and notable changes since v0.3.0:
-
-## ⚠️ Command `send_tweet` is REMOVED
-Twitter functionality (and more) is now covered by plugins.
-
-## ⚠️ Memory backend deprecation 💾
-The Milvus, Pinecone and Weaviate memory backends were rendered incompatible
-by work on the memory system, and have been removed in `master`. The Redis
-memory store was also temporarily removed; we will merge a new implementation ASAP.
-Whether built-in support for the others will be added back in the future is subject to
-discussion, feel free to pitch in: https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280
-
-## Document support in `read_file` 📄
-Auto-GPT can now read text from document files, with support added for PDF, DOCX, CSV,
-HTML, TeX and more!
-
-## Managing Auto-GPT's access to commands ❌🔧
-You can now disable set of built-in commands through the *DISABLED_COMMAND_CATEGORIES*
-variable in .env. Specific shell commands can also be disabled using *DENY_COMMANDS*,
-or selectively enabled using *ALLOW_COMMANDS*.
+Highlights and notable changes since v0.4.0:
+- The .env.template is more readable and better explains the purpose of each environment variable.
+- More dependable search
+    - The CUSTOM_SEARCH_ENGINE_ID variable has been replaced to GOOGLE_CUSTOM_SEARCH_ENGINE_ID, make sure you update it.
+- Better read_file
+- More reliable python code execution
+- Lots of JSON error fixes
+- Directory-based plugins
 
 ## Further fixes and changes 🛠️
-Other highlights include improvements to self-feedback mode and continuous mode,
-documentation, docker and devcontainer setups, and much more. Most of the improvements
-that were made are not yet visible to users, but will pay off in the long term.
-Take a look at the Release Notes on Github for the full changelog!
+Under the hood, we've done a bunch of work improving architectures and streamlining code. Most of that won't be user-visible
+
+## Take a look at the Release Notes on Github for the full changelog!
 https://github.com/Significant-Gravitas/Auto-GPT/releases

autogpt/commands/execute_code.py

@@ -18,7 +18,7 @@ DENYLIST_CONTROL = "denylist"
 
 @command(
     "execute_python_code",
-    "Create a Python file and execute it",
+    "Creates a Python file and executes it",
     {
         "code": {
             "type": "string",
@@ -63,7 +63,7 @@ def execute_python_code(code: str, name: str, agent: Agent) -> str:
 
 @command(
     "execute_python_file",
-    "Execute an existing Python file",
+    "Executes an existing Python file",
     {
         "filename": {
             "type": "string",
@@ -191,7 +191,7 @@ def validate_command(command: str, config: Config) -> bool:
 
 @command(
     "execute_shell",
-    "Execute Shell Command, non-interactive commands only",
+    "Executes a Shell Command, non-interactive commands only",
     {
         "command_line": {
             "type": "string",
@@ -237,7 +237,7 @@ def execute_shell(command_line: str, agent: Agent) -> str:
 
 @command(
     "execute_shell_popen",
-    "Execute Shell Command, non-interactive commands only",
+    "Executes a Shell Command, non-interactive commands only",
     {
         "query": {
             "type": "string",

autogpt/commands/file_operations.py

@@ -11,6 +11,7 @@ from confection import Config
 from autogpt.agent.agent import Agent
 from autogpt.command_decorator import command
 from autogpt.commands.file_operations_utils import read_textual_file
+from autogpt.config import Config
 from autogpt.logs import logger
 from autogpt.memory.vector import MemoryItem, VectorMemory
 
@@ -175,7 +176,7 @@ def ingest_file(
 
 @command(
     "write_to_file",
-    "Write to file",
+    "Writes to a file",
     {
         "filename": {
             "type": "string",
@@ -215,7 +216,7 @@ def write_to_file(filename: str, text: str, agent: Agent) -> str:
 
 @command(
     "append_to_file",
-    "Append to file",
+    "Appends to a file",
     {
         "filename": {
             "type": "string",
@@ -260,7 +261,7 @@ def append_to_file(
 
 @command(
     "delete_file",
-    "Delete file",
+    "Deletes a file",
     {
         "filename": {
             "type": "string",
@@ -290,7 +291,7 @@ def delete_file(filename: str, agent: Agent) -> str:
 
 @command(
     "list_files",
-    "List Files in Directory",
+    "Lists Files in a Directory",
     {
         "directory": {
             "type": "string",

autogpt/commands/git_operations.py

@@ -9,7 +9,7 @@ from autogpt.url_utils.validators import validate_url
 
 @command(
     "clone_repository",
-    "Clone Repository",
+    "Clones a Repository",
     {
         "url": {
             "type": "string",

autogpt/commands/image_gen.py

@@ -16,7 +16,7 @@ from autogpt.logs import logger
 
 @command(
     "generate_image",
-    "Generate Image",
+    "Generates an Image",
     {
         "prompt": {
             "type": "string",

autogpt/commands/web_search.py

@@ -15,7 +15,7 @@ DUCKDUCKGO_MAX_ATTEMPTS = 3
 
 @command(
     "web_search",
-    "Search the web",
+    "Searches the web",
     {
         "query": {
             "type": "string",

autogpt/commands/web_selenium.py

@@ -41,7 +41,7 @@ FILE_DIR = Path(__file__).parent.parent
 
 @command(
     "browse_website",
-    "Browse Website",
+    "Browses a Website",
     {
         "url": {"type": "string", "description": "The URL to visit", "required": True},
         "question": {

autogpt/llm/api_manager.py

@@ -5,7 +5,7 @@ from typing import List, Optional
 import openai
 from openai import Model
 
-from autogpt.llm.modelsinfo import COSTS
+from autogpt.llm.base import CompletionModelInfo
 from autogpt.logs import logger
 from autogpt.singleton import Singleton
 
@@ -35,14 +35,19 @@ class ApiManager(metaclass=Singleton):
         model (str): The model used for the API call.
         """
         # the .model property in API responses can contain version suffixes like -v2
+        from autogpt.llm.providers.openai import OPEN_AI_MODELS
+
         model = model[:-3] if model.endswith("-v2") else model
+        model_info = OPEN_AI_MODELS[model]
 
         self.total_prompt_tokens += prompt_tokens
         self.total_completion_tokens += completion_tokens
-        self.total_cost += (
-            prompt_tokens * COSTS[model]["prompt"]
-            + completion_tokens * COSTS[model]["completion"]
-        ) / 1000
+        self.total_cost += prompt_tokens * model_info.prompt_token_cost / 1000
+        if issubclass(type(model_info), CompletionModelInfo):
+            self.total_cost += (
+                completion_tokens * model_info.completion_token_cost / 1000
+            )
+
         logger.debug(f"Total running cost: ${self.total_cost:.3f}")
 
     def set_total_budget(self, total_budget):

autogpt/llm/base.py

@@ -34,22 +34,27 @@ class ModelInfo:
 
     Would be lovely to eventually get this directly from APIs, but needs to be scraped from
     websites for now.
-
     """
 
     name: str
-    prompt_token_cost: float
-    completion_token_cost: float
     max_tokens: int
+    prompt_token_cost: float
 
 
 @dataclass
-class ChatModelInfo(ModelInfo):
+class CompletionModelInfo(ModelInfo):
+    """Struct for generic completion model information."""
+
+    completion_token_cost: float
+
+
+@dataclass
+class ChatModelInfo(CompletionModelInfo):
     """Struct for chat model information."""
 
 
 @dataclass
-class TextModelInfo(ModelInfo):
+class TextModelInfo(CompletionModelInfo):
     """Struct for text completion model information."""
 
 

autogpt/llm/modelsinfo.py

@@ -1,11 +0,0 @@
-COSTS = {
-    "gpt-3.5-turbo": {"prompt": 0.002, "completion": 0.002},
-    "gpt-3.5-turbo-0301": {"prompt": 0.002, "completion": 0.002},
-    "gpt-4-0314": {"prompt": 0.03, "completion": 0.06},
-    "gpt-4": {"prompt": 0.03, "completion": 0.06},
-    "gpt-4-0314": {"prompt": 0.03, "completion": 0.06},
-    "gpt-4-32k": {"prompt": 0.06, "completion": 0.12},
-    "gpt-4-32k-0314": {"prompt": 0.06, "completion": 0.12},
-    "text-embedding-ada-002": {"prompt": 0.0004, "completion": 0.0},
-    "text-davinci-003": {"prompt": 0.02, "completion": 0.02},
-}

autogpt/llm/providers/openai.py

@@ -9,7 +9,6 @@ from colorama import Fore, Style
 from openai.error import APIError, RateLimitError, Timeout
 from openai.openai_object import OpenAIObject
 
-from autogpt.llm.api_manager import ApiManager
 from autogpt.llm.base import (
     ChatModelInfo,
     EmbeddingModelInfo,
@@ -22,23 +21,23 @@ from autogpt.logs import logger
 OPEN_AI_CHAT_MODELS = {
     info.name: info
     for info in [
-        ChatModelInfo(
-            name="gpt-3.5-turbo",
-            prompt_token_cost=0.002,
-            completion_token_cost=0.002,
-            max_tokens=4096,
-        ),
         ChatModelInfo(
             name="gpt-3.5-turbo-0301",
-            prompt_token_cost=0.002,
+            prompt_token_cost=0.0015,
             completion_token_cost=0.002,
             max_tokens=4096,
         ),
         ChatModelInfo(
-            name="gpt-4",
-            prompt_token_cost=0.03,
-            completion_token_cost=0.06,
-            max_tokens=8192,
+            name="gpt-3.5-turbo-0613",
+            prompt_token_cost=0.0015,
+            completion_token_cost=0.002,
+            max_tokens=4096,
+        ),
+        ChatModelInfo(
+            name="gpt-3.5-turbo-16k-0613",
+            prompt_token_cost=0.003,
+            completion_token_cost=0.004,
+            max_tokens=16384,
         ),
         ChatModelInfo(
             name="gpt-4-0314",
@@ -47,10 +46,10 @@ OPEN_AI_CHAT_MODELS = {
             max_tokens=8192,
         ),
         ChatModelInfo(
-            name="gpt-4-32k",
-            prompt_token_cost=0.06,
-            completion_token_cost=0.12,
-            max_tokens=32768,
+            name="gpt-4-0613",
+            prompt_token_cost=0.03,
+            completion_token_cost=0.06,
+            max_tokens=8192,
         ),
         ChatModelInfo(
             name="gpt-4-32k-0314",
@@ -58,8 +57,25 @@ OPEN_AI_CHAT_MODELS = {
             completion_token_cost=0.12,
             max_tokens=32768,
         ),
+        ChatModelInfo(
+            name="gpt-4-32k-0613",
+            prompt_token_cost=0.06,
+            completion_token_cost=0.12,
+            max_tokens=32768,
+        ),
     ]
 }
+# Set aliases for rolling model IDs
+chat_model_mapping = {
+    "gpt-3.5-turbo": "gpt-3.5-turbo-0301",
+    "gpt-3.5-turbo-16k": "gpt-3.5-turbo-16k-0613",
+    "gpt-4": "gpt-4-0314",
+    "gpt-4-32k": "gpt-4-32k-0314",
+}
+for alias, target in chat_model_mapping.items():
+    alias_info = ChatModelInfo(**OPEN_AI_CHAT_MODELS[target].__dict__)
+    alias_info.name = alias
+    OPEN_AI_CHAT_MODELS[alias] = alias_info
 
 OPEN_AI_TEXT_MODELS = {
     info.name: info
@@ -78,8 +94,7 @@ OPEN_AI_EMBEDDING_MODELS = {
     for info in [
         EmbeddingModelInfo(
             name="text-embedding-ada-002",
-            prompt_token_cost=0.0004,
-            completion_token_cost=0.0,
+            prompt_token_cost=0.0001,
             max_tokens=8191,
             embedding_dimensions=1536,
         ),
@@ -95,6 +110,8 @@ OPEN_AI_MODELS: dict[str, ChatModelInfo | EmbeddingModelInfo | TextModelInfo] =
 
 def meter_api(func):
     """Adds ApiManager metering to functions which make OpenAI API calls"""
+    from autogpt.llm.api_manager import ApiManager
+
     api_manager = ApiManager()
 
     openai_obj_processor = openai.util.convert_to_openai_object

autogpt/llm/utils/token_counter.py

@@ -24,32 +24,28 @@ def count_message_tokens(
     Returns:
         int: The number of tokens used by the list of messages.
     """
-    try:
-        encoding = tiktoken.encoding_for_model(model)
-    except KeyError:
-        logger.warn("Warning: model not found. Using cl100k_base encoding.")
-        encoding = tiktoken.get_encoding("cl100k_base")
-    if model == "gpt-3.5-turbo":
-        # !Note: gpt-3.5-turbo may change over time.
-        # Returning num tokens assuming gpt-3.5-turbo-0301.")
-        return count_message_tokens(messages, model="gpt-3.5-turbo-0301")
-    elif model == "gpt-4":
-        # !Note: gpt-4 may change over time. Returning num tokens assuming gpt-4-0314.")
-        return count_message_tokens(messages, model="gpt-4-0314")
-    elif model == "gpt-3.5-turbo-0301":
+    if model.startswith("gpt-3.5-turbo"):
         tokens_per_message = (
             4  # every message follows <|start|>{role/name}\n{content}<|end|>\n
         )
         tokens_per_name = -1  # if there's a name, the role is omitted
-    elif model == "gpt-4-0314":
+        encoding_model = "gpt-3.5-turbo"
+    elif model.startswith("gpt-4"):
         tokens_per_message = 3
         tokens_per_name = 1
+        encoding_model = "gpt-4"
     else:
         raise NotImplementedError(
-            f"num_tokens_from_messages() is not implemented for model {model}.\n"
+            f"count_message_tokens() is not implemented for model {model}.\n"
             " See https://github.com/openai/openai-python/blob/main/chatml.md for"
             " information on how messages are converted to tokens."
         )
+    try:
+        encoding = tiktoken.encoding_for_model(encoding_model)
+    except KeyError:
+        logger.warn("Warning: model not found. Using cl100k_base encoding.")
+        encoding = tiktoken.get_encoding("cl100k_base")
+
     num_tokens = 0
     for message in messages:
         num_tokens += tokens_per_message

autogpt/speech/base.py

@@ -1,5 +1,6 @@
 """Base class for all voice classes."""
 import abc
+import re
 from threading import Lock
 
 from autogpt.config import Config
@@ -30,6 +31,11 @@ class VoiceBase(AbstractSingleton):
             text (str): The text to say.
             voice_index (int): The index of the voice to use.
         """
+        text = re.sub(
+            r"\b(?:https?://[-\w_.]+/?\w[-\w_.]*\.(?:[-\w_.]+/?\w[-\w_.]*\.)?[a-z]+(?:/[-\w_.%]+)*\b(?!\.))",
+            "",
+            text,
+        )
         with self._mutex:
             return self._speech(text, voice_index)
 

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "agpt"
-version = "0.4.0"
+version = "0.4.1"
 authors = [
   { name="Torantulino", email="support@agpt.co" },
 ]

tests/integration/test_provider_openai.py

@@ -2,7 +2,7 @@ from unittest.mock import MagicMock, patch
 
 import pytest
 
-from autogpt.llm.api_manager import COSTS, ApiManager
+from autogpt.llm.api_manager import ApiManager
 from autogpt.llm.providers import openai
 
 api_manager = ApiManager()
@@ -14,19 +14,6 @@ def reset_api_manager():
     yield
 
 
-@pytest.fixture(autouse=True)
-def mock_costs():
-    with patch.dict(
-        COSTS,
-        {
-            "gpt-3.5-turbo": {"prompt": 0.002, "completion": 0.002},
-            "text-embedding-ada-002": {"prompt": 0.0004, "completion": 0},
-        },
-        clear=True,
-    ):
-        yield
-
-
 class TestProviderOpenAI:
     @staticmethod
     def test_create_chat_completion_debug_mode(caplog):

tests/unit/test_api_manager.py

@@ -1,8 +1,10 @@
 from unittest.mock import patch
 
 import pytest
+from pytest_mock import MockerFixture
 
-from autogpt.llm.api_manager import COSTS, ApiManager
+from autogpt.llm.api_manager import ApiManager
+from autogpt.llm.providers.openai import OPEN_AI_CHAT_MODELS, OPEN_AI_EMBEDDING_MODELS
 
 api_manager = ApiManager()
 
@@ -14,26 +16,27 @@ def reset_api_manager():
 
 
 @pytest.fixture(autouse=True)
-def mock_costs():
-    with patch.dict(
-        COSTS,
-        {
-            "gpt-3.5-turbo": {"prompt": 0.002, "completion": 0.002},
-            "text-embedding-ada-002": {"prompt": 0.0004, "completion": 0},
-        },
-        clear=True,
-    ):
-        yield
+def mock_costs(mocker: MockerFixture):
+    mocker.patch.multiple(
+        OPEN_AI_CHAT_MODELS["gpt-3.5-turbo"],
+        prompt_token_cost=0.0013,
+        completion_token_cost=0.0025,
+    )
+    mocker.patch.multiple(
+        OPEN_AI_EMBEDDING_MODELS["text-embedding-ada-002"],
+        prompt_token_cost=0.0004,
+    )
+    yield
 
 
 class TestApiManager:
     def test_getter_methods(self):
         """Test the getter methods for total tokens, cost, and budget."""
-        api_manager.update_cost(60, 120, "gpt-3.5-turbo")
+        api_manager.update_cost(600, 1200, "gpt-3.5-turbo")
         api_manager.set_total_budget(10.0)
-        assert api_manager.get_total_prompt_tokens() == 60
-        assert api_manager.get_total_completion_tokens() == 120
-        assert api_manager.get_total_cost() == (60 * 0.002 + 120 * 0.002) / 1000
+        assert api_manager.get_total_prompt_tokens() == 600
+        assert api_manager.get_total_completion_tokens() == 1200
+        assert api_manager.get_total_cost() == (600 * 0.0013 + 1200 * 0.0025) / 1000
         assert api_manager.get_total_budget() == 10.0
 
     @staticmethod
@@ -45,7 +48,7 @@ class TestApiManager:
         assert api_manager.get_total_budget() == total_budget
 
     @staticmethod
-    def test_update_cost():
+    def test_update_cost_completion_model():
         """Test if updating the cost works correctly."""
         prompt_tokens = 50
         completion_tokens = 100
@@ -53,9 +56,24 @@ class TestApiManager:
 
         api_manager.update_cost(prompt_tokens, completion_tokens, model)
 
-        assert api_manager.get_total_prompt_tokens() == 50
-        assert api_manager.get_total_completion_tokens() == 100
-        assert api_manager.get_total_cost() == (50 * 0.002 + 100 * 0.002) / 1000
+        assert api_manager.get_total_prompt_tokens() == prompt_tokens
+        assert api_manager.get_total_completion_tokens() == completion_tokens
+        assert (
+            api_manager.get_total_cost()
+            == (prompt_tokens * 0.0013 + completion_tokens * 0.0025) / 1000
+        )
+
+    @staticmethod
+    def test_update_cost_embedding_model():
+        """Test if updating the cost works correctly."""
+        prompt_tokens = 1337
+        model = "text-embedding-ada-002"
+
+        api_manager.update_cost(prompt_tokens, 0, model)
+
+        assert api_manager.get_total_prompt_tokens() == prompt_tokens
+        assert api_manager.get_total_completion_tokens() == 0
+        assert api_manager.get_total_cost() == (prompt_tokens * 0.0004) / 1000
 
     @staticmethod
     def test_get_models():