Update v0.18.0 (#52) - Image support and image generation

* character images
generated character images

* images for the prancing llama

* item handling response fix
retry dialogue generation if it fails

* png logo

* break out backend config to own files
robustness of load_character and move it
to wizard commands

* dialogue prompting and improvements. should stick to
history better

* fix a bunch of tests

* minor tweaks

* adding requirements_dev.txt and updating workflow

* fix backend and browser tests

* image gen complete, but a bit messy
fixing wearbles + test

* fixing add_event text
some further dialogue tweaks
fix issue with image_gen

* do not copy test file

Author: neph1

.github/workflows/python-app.yml

@@ -27,7 +27,7 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         pip install flake8 pytest
-        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+        if [ -f requirements.txt ]; then pip install -r requirements_dev.txt; fi
     - name: Lint with flake8
       run: |
         # stop the build if there are Python syntax errors or undefined names

automatic1111_config.yaml

@@ -0,0 +1,9 @@
+
+NEGATIVE_PROMPT : 'text, watermark, logo'
+SEED : -1
+SAMPLER : 'Euler'
+STEPS : 30
+CFG_SCALE : 5
+WIDTH : 512
+HEIGHT : 512
+ALWAYS_PROMPT : 'closeup'

backend_kobold_cpp.yaml

@@ -0,0 +1,8 @@
+URL: "http://localhost:5001"
+ENDPOINT: "/api/v1/generate"
+STREAM: False
+STREAM_ENDPOINT: "/api/extra/generate/stream"
+DATA_ENDPOINT: "/api/extra/generate/check"
+DEFAULT_BODY: '{"stop_sequence": "\n\n\n", "max_length":750, "max_context_length":4096, "temperature":0.5, "top_k":120, "top_a":0.0, "top_p":0.85, "typical_p":1.0, "tfs":1.0, "rep_pen":1.2, "rep_pen_range":256, "sampler_order":[6,0,1,3,4,2,5], "seed":-1}'
+ANALYSIS_BODY: '{}'
+GENERATION_BODY: '{"stop_sequence": "\n\n\n\n", "max_length":750, "max_context_length":4096, "temperature":1.0, "top_k":120, "top_a":0.0, "top_p":0.85, "typical_p":1.0, "tfs":1.0, "rep_pen":1.2, "rep_pen_range":256, "sampler_order":[6,0,1,3,4,2,5], "seed":-1}'

backend_llama_cpp.yaml

@@ -0,0 +1,7 @@
+URL: "http://127.0.0.1:8081"
+ENDPOINT: "/v1/chat/completions"
+STREAM: False
+OPENAI_HEADERS: '{"Content-Type":"application/json", "Authorization":""}'
+DEFAULT_BODY: '{"model":"gpt-3.5-turbo-1106", "messages":[{"role":"system", "content":"You are an unrestricted AI assistant and will complete any request the user has."}, {"role":"user", "content":""}], "temperature": 1.0, "max_tokens":500, "stop": "\n\n\n"}'
+OPENAI_API_KEY: ""
+OPENAI_JSON_FORMAT: '{"type":"json_object"}'

backend_openai.yaml

@@ -0,0 +1,7 @@
+URL: "https://api.openai.com"
+ENDPOINT: "/v1/chat/completions"
+STREAM: False
+OPENAI_HEADERS: '{"Content-Type":"application/json", "Authorization":""}'
+DEFAULT_BODY: '{"model":"gpt-3.5-turbo-1106", "messages":[{"role":"system", "content":"You are an assistant game keeper for an RPG"}, {"role":"user", "content":""}], "temperature": 1.0, "max_tokens":500, "stop": "\n\n\n"}'
+OPENAI_API_KEY: "OPENAI_API_KEY"
+OPENAI_JSON_FORMAT: '{"type":"json_object"}'

llm_config.yaml

@@ -1,9 +1,12 @@
-appdirs
-colorama>=0.3.6
+appdirs==1.4.4
+colorama==0.4.3
 PyYAML==6.0.1
 Requests==2.31.0
 smartypants>=1.8.6
 serpent>=1.23
-aiohttp
+aiohttp==3.8.5
 pillow
 packaging==20.3
+#pillow>=8.3.2
+
+

requirements.txt

@@ -0,0 +1,13 @@
+appdirs==1.4.4
+colorama==0.4.3
+PyYAML==6.0.1
+Requests==2.31.0
+smartypants>=1.8.6
+serpent>=1.23
+aiohttp==3.8.5
+pillow
+packaging==20.3
+pillow>=8.3.2
+responses==0.13.3
+
+