Merge branch 'master' into redis-backend

.env.template

@@ -9,4 +9,6 @@ CUSTOM_SEARCH_ENGINE_ID=
 USE_AZURE=False
 OPENAI_API_BASE=your-base-url-for-azure
 OPENAI_API_VERSION=api-version-for-azure
-OPENAI_DEPLOYMENT_ID=deployment-id-for-azure
+OPENAI_DEPLOYMENT_ID=deployment-id-for-azure
+IMAGE_PROVIDER=dalle
+HUGGINGFACE_API_TOKEN=

README.md

@@ -9,7 +9,7 @@ Auto-GPT is an experimental open-source application showcasing the capabilities
 https://user-images.githubusercontent.com/22963551/228855501-2f5777cf-755b-4407-a643-c7299e5b6419.mp4
 
 
-## 💖 Help Fund Auto-GPT's Development
+<h2 align="center"> 💖 Help Fund Auto-GPT's Development 💖</h2> 
 <p align="center">
 If you can spare a coffee, you can help to cover the API costs of developing Auto-GPT and help push the boundaries of fully autonomous AI!
 A full day of development can easily cost as much as $20 in API costs, which for a free project is quite limiting.
@@ -17,14 +17,13 @@ Your support is greatly appreciated
 </p>
 
 <p align="center">
- Development of this free, open-source project is made possible by all the <a href="https://github.com/Torantulino/Auto-GPT/graphs/contributors">contributors</a> and <a href="https://github.com/sponsors/Torantulino">sponsors</a>. If you'd like to sponsor this project and have your avatar or company logo appear below <a href="https://github.com/sponsors/Torantulino">click here</a>. 💖
-<p align="center">
-<p align="center">
-<a href="https://github.com/thepok"><img src="https://github.com/thepok.png" width="50px" alt="thepok" /></a>&nbsp;&nbsp;<a href="https://github.com/SpacingLily"><img src="https://github.com/SpacingLily.png" width="50px" alt="SpacingLily" /></a>&nbsp;&nbsp;<a href="https://github.com/m"><img src="https://github.com/m.png" width="50px" alt="m" /></a>&nbsp;&nbsp;<a href="https://github.com/zkonduit"><img src="https://github.com/zkonduit.png" width="50px" alt="zkonduit" /></a>&nbsp;&nbsp;<a href="https://github.com/maxxflyer"><img src="https://github.com/maxxflyer.png" width="50px" alt="maxxflyer" /></a>&nbsp;&nbsp;<a href="https://github.com/tekelsey"><img src="https://github.com/tekelsey.png" width="50px" alt="tekelsey" /></a>&nbsp;&nbsp;<a href="https://github.com/nocodeclarity"><img src="https://github.com/nocodeclarity.png" width="50px" alt="nocodeclarity" /></a>&nbsp;&nbsp;<a href="https://github.com/tjarmain"><img src="https://github.com/tjarmain.png" width="50px" alt="tjarmain" /></a>&nbsp;&nbsp;<a href="https://github.com/alexisneuhaus"><img src="https://github.com/alexisneuhaus.png" width="50px" alt="alexisneuhaus" /></a>&nbsp;&nbsp;<a href="https://github.com/jaumebalust"><img src="https://github.com/jaumebalust.png" width="50px" alt="jaumebalust" /></a>&nbsp;&nbsp;<a href="https://github.com/robinicus"><img src="https://github.com/robinicus.png" width="50px" alt="robinicus" /></a>&nbsp;&nbsp;<a href="https://github.com/digisomni"><img src="https://github.com/digisomni.png" width="50px" alt="digisomni" /></a>&nbsp;&nbsp;
-</p>
+ Development of this free, open-source project is made possible by all the <a href="https://github.com/Torantulino/Auto-GPT/graphs/contributors">contributors</a> and <a href="https://github.com/sponsors/Torantulino">sponsors</a>. If you'd like to sponsor this project and have your avatar or company logo appear below <a href="https://github.com/sponsors/Torantulino">click here</a>.
 
+<h3 align="center">Individual Sponsors</h3>
 <p align="center">
-<a href="https://github.com/alexisneuhaus"><img src="https://github.com/alexisneuhaus.png" width="30px" alt="alexisneuhaus" /></a>&nbsp;&nbsp;<a href="https://github.com/iokode"><img src="https://github.com/iokode.png" width="30px" alt="iokode" /></a>&nbsp;&nbsp;<a href="https://github.com/jaumebalust"><img src="https://github.com/jaumebalust.png" width="30px" alt="jaumebalust" /></a>&nbsp;&nbsp;<a href="https://github.com/nova-land"><img src="https://github.com/nova-land.png" width="30px" alt="nova-land" /></a>&nbsp;&nbsp;<a href="https://github.com/robinicus"><img src="https://github.com/robinicus.png" width="30px" alt="robinicus" /></a>&nbsp;&nbsp;<a href="https://github.com/Void-n-Null"><img src="https://github.com/Void-n-Null.png" width="30px" alt="Void-n-Null" /></a>&nbsp;&nbsp;<a href="https://github.com/ritesh24"><img src="https://github.com/ritesh24.png" width="30px" alt="ritesh24" /></a>&nbsp;&nbsp;<a href="https://github.com/merwanehamadi"><img src="https://github.com/merwanehamadi.png" width="30px" alt="merwanehamadi" /></a>&nbsp;&nbsp;<a href="https://github.com/raulmarindev"><img src="https://github.com/raulmarindev.png" width="30px" alt="raulmarindev" /></a>&nbsp;&nbsp;<a href="https://github.com/siduppal"><img src="https://github.com/siduppal.png" width="30px" alt="siduppal" /></a>&nbsp;&nbsp;<a href="https://github.com/goosecubedaddy"><img src="https://github.com/goosecubedaddy.png" width="30px" alt="goosecubedaddy" /></a>&nbsp;&nbsp;<a href="https://github.com/pleabargain"><img src="https://github.com/pleabargain.png" width="30px" alt="pleabargain" /></a>&nbsp;&nbsp;
+<a href="https://github.com/robinicus"><img src="https://github.com/robinicus.png" width="50px" alt="robinicus" /></a>&nbsp;&nbsp;<a href="https://github.com/prompthero"><img src="https://github.com/prompthero.png" width="50px" alt="prompthero" /></a>&nbsp;&nbsp;<a href="https://github.com/crizzler"><img src="https://github.com/crizzler.png" width="50px" alt="crizzler" /></a>&nbsp;&nbsp;<a href="https://github.com/tob-le-rone"><img src="https://github.com/tob-le-rone.png" width="50px" alt="tob-le-rone" /></a>&nbsp;&nbsp;<a href="https://github.com/FSTatSBS"><img src="https://github.com/FSTatSBS.png" width="50px" alt="FSTatSBS" /></a>&nbsp;&nbsp;<a href="https://github.com/toverly1"><img src="https://github.com/toverly1.png" width="50px" alt="toverly1" /></a>&nbsp;&nbsp;<a href="https://github.com/ddtarazona"><img src="https://github.com/ddtarazona.png" width="50px" alt="ddtarazona" /></a>&nbsp;&nbsp;<a href="https://github.com/Nalhos"><img src="https://github.com/Nalhos.png" width="50px" alt="Nalhos" /></a>&nbsp;&nbsp;<a href="https://github.com/Kazamario"><img src="https://github.com/Kazamario.png" width="50px" alt="Kazamario" /></a>&nbsp;&nbsp;<a href="https://github.com/pingbotan"><img src="https://github.com/pingbotan.png" width="50px" alt="pingbotan" /></a>&nbsp;&nbsp;<a href="https://github.com/indoor47"><img src="https://github.com/indoor47.png" width="50px" alt="indoor47" /></a>&nbsp;&nbsp;<a href="https://github.com/AuroraHolding"><img src="https://github.com/AuroraHolding.png" width="50px" alt="AuroraHolding" /></a>&nbsp;&nbsp;<a href="https://github.com/kreativai"><img src="https://github.com/kreativai.png" width="50px" alt="kreativai" /></a>&nbsp;&nbsp;<a href="https://github.com/hunteraraujo"><img src="https://github.com/hunteraraujo.png" width="50px" alt="hunteraraujo" /></a>&nbsp;&nbsp;<a href="https://github.com/Explorergt92"><img src="https://github.com/Explorergt92.png" width="50px" alt="Explorergt92" /></a>&nbsp;&nbsp;<a href="https://github.com/judegomila"><img src="https://github.com/judegomila.png" width="50px" alt="judegomila" /></a>&nbsp;&nbsp;
+<a href="https://github.com/thepok"><img src="https://github.com/thepok.png" width="50px" alt="thepok" /></a>
+&nbsp;&nbsp;<a href="https://github.com/SpacingLily"><img src="https://github.com/SpacingLily.png" width="50px" alt="SpacingLily" /></a>&nbsp;&nbsp;<a href="https://github.com/merwanehamadi"><img src="https://github.com/merwanehamadi.png" width="50px" alt="merwanehamadi" /></a>&nbsp;&nbsp;<a href="https://github.com/m"><img src="https://github.com/m.png" width="50px" alt="m" /></a>&nbsp;&nbsp;<a href="https://github.com/zkonduit"><img src="https://github.com/zkonduit.png" width="50px" alt="zkonduit" /></a>&nbsp;&nbsp;<a href="https://github.com/maxxflyer"><img src="https://github.com/maxxflyer.png" width="50px" alt="maxxflyer" /></a>&nbsp;&nbsp;<a href="https://github.com/tekelsey"><img src="https://github.com/tekelsey.png" width="50px" alt="tekelsey" /></a>&nbsp;&nbsp;<a href="https://github.com/digisomni"><img src="https://github.com/digisomni.png" width="50px" alt="digisomni" /></a>&nbsp;&nbsp;<a href="https://github.com/nocodeclarity"><img src="https://github.com/nocodeclarity.png" width="50px" alt="nocodeclarity" /></a>&nbsp;&nbsp;<a href="https://github.com/tjarmain"><img src="https://github.com/tjarmain.png" width="50px" alt="tjarmain" /></a>
 </p>
 
 
@@ -43,6 +42,7 @@ Your support is greatly appreciated
     - [Setting up environment variables](#setting-up-environment-variables)
   - [💀 Continuous Mode ⚠️](#-continuous-mode-️)
   - [GPT3.5 ONLY Mode](#gpt35-only-mode)
+  - [🖼 Image Generation](#image-generation)
   - [⚠️ Limitations](#️-limitations)
   - [🛡 Disclaimer](#-disclaimer)
   - [🐦 Connect with Us on Twitter](#-connect-with-us-on-twitter)
@@ -203,6 +203,7 @@ Or you can set them in the `.env` file.
 
 1. View memory usage by using the `--debug` flag :)
 
+
 ## 💀 Continuous Mode ⚠️
 Run the AI **without** user authorisation, 100% automated.
 Continuous mode is not recommended. 
@@ -221,6 +222,15 @@ If you don't have access to the GPT4 api, this mode will allow you to use Auto-G
 python scripts/main.py --gpt3only
 ```
 
+## 🖼 Image Generation
+By default, Auto-GPT uses DALL-e for image generation. To use Stable Diffusion, a [HuggingFace API Token](https://huggingface.co/settings/tokens) is required.
+
+Once you have a token, set these variables in your `.env`:
+```
+IMAGE_PROVIDER=sd
+HUGGINGFACE_API_TOKEN="YOUR_HUGGINGFACE_API_TOKEN"
+```
+
 ## ⚠️ Limitations
 This experiment aims to showcase the potential of GPT-4 but comes with some limitations:
 

requirements.txt

@@ -13,4 +13,5 @@ duckduckgo-search
 google-api-python-client #(https://developers.google.com/custom-search/v1/overview)
 pinecone-client==2.2.1
 redis
-orjson
+orjson
+Pillow

scripts/ai_config.py

@@ -1,6 +1,6 @@
 import yaml
 import data
-
+import os
 
 class AIConfig:
     def __init__(self, ai_name="", ai_role="", ai_goals=[]):
@@ -9,7 +9,7 @@ class AIConfig:
         self.ai_goals = ai_goals
 
     # Soon this will go in a folder where it remembers more stuff about the run(s)
-    SAVE_FILE = "../ai_settings.yaml"
+    SAVE_FILE = os.path.join(os.path.dirname(__file__), '..', 'ai_settings.yaml')
 
     @classmethod
     def load(cls, config_file=SAVE_FILE):

scripts/commands.py

@@ -9,6 +9,7 @@ import ai_functions as ai
 from file_operations import read_file, write_to_file, append_to_file, delete_file, search_files
 from execute_code import execute_python_file
 from json_parser import fix_and_parse_json
+from image_gen import generate_image
 from duckduckgo_search import ddg
 from googleapiclient.discovery import build
 from googleapiclient.errors import HttpError
@@ -103,6 +104,8 @@ def execute_command(command_name, arguments):
             return ai.write_tests(arguments["code"], arguments.get("focus"))
         elif command_name == "execute_python_file":  # Add this command
             return execute_python_file(arguments["file"])
+        elif command_name == "generate_image":
+            return generate_image(arguments["prompt"])
         elif command_name == "task_complete":
             shutdown()
         else:

scripts/config.py

@@ -58,6 +58,9 @@ class Config(metaclass=Singleton):
         self.pinecone_api_key = os.getenv("PINECONE_API_KEY")
         self.pinecone_region = os.getenv("PINECONE_ENV")
 
+        self.image_provider = os.getenv("IMAGE_PROVIDER")
+        self.huggingface_api_token = os.getenv("HUGGINGFACE_API_TOKEN")
+
         # User agent headers to use when browsing web
         # Some websites might just completely deny request with an error code if no user agent was found.
         self.user_agent_header = {"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"}

scripts/data/prompt.txt

@@ -23,6 +23,7 @@ COMMANDS:
 17. Write Tests: "write_tests", args: "code": "<full_code_string>", "focus": "<list_of_focus_areas>"
 18. Execute Python File: "execute_python_file", args: "file": "<file>"
 19. Task Complete (Shutdown): "task_complete", args: "reason": "<reason>"
+20. Generate Image: "generate_image", args: "prompt": "<prompt>"
 
 RESOURCES:
 

scripts/image_gen.py

@@ -0,0 +1,57 @@
+import requests
+import io
+import os.path
+from PIL import Image
+from config import Config
+import uuid
+import openai
+from base64 import b64decode
+
+cfg = Config()
+
+working_directory = "auto_gpt_workspace"
+
+def generate_image(prompt):
+
+    filename = str(uuid.uuid4()) + ".jpg"
+    
+    # DALL-E
+    if cfg.image_provider == 'dalle':
+
+        openai.api_key = cfg.openai_api_key
+
+        response = openai.Image.create(
+            prompt=prompt,
+            n=1,
+            size="256x256",
+            response_format="b64_json",
+        )
+
+        print("Image Generated for prompt:" + prompt)
+
+        image_data = b64decode(response["data"][0]["b64_json"])
+
+        with open(working_directory + "/" + filename, mode="wb") as png:
+            png.write(image_data)
+
+        return "Saved to disk:" + filename
+
+    # STABLE DIFFUSION
+    elif cfg.image_provider == 'sd':
+
+        API_URL = "https://api-inference.huggingface.co/models/CompVis/stable-diffusion-v1-4"
+        headers = {"Authorization": "Bearer " + cfg.huggingface_api_token}
+
+        response = requests.post(API_URL, headers=headers, json={
+            "inputs": prompt,
+        })
+
+        image = Image.open(io.BytesIO(response.content))
+        print("Image Generated for prompt:" + prompt)
+
+        image.save(os.path.join(working_directory, filename))
+
+        return "Saved to disk:" + filename
+
+    else:
+        return "No Image Provider Set"