More rearrangement

app.py

@@ -13,6 +13,7 @@ import time
 import psutil
 from sentence_transformers import SentenceTransformer
 import textwrap
+from gradio_client import Client
 
 #Imported Long Variables - comment for each move to search
 from relatively_constant_variables import *
@@ -779,13 +780,24 @@ def LinPEWFformat_prompt(current_prompt, prev_messages):
 
 #-----------------------------------------------------------------------------------------------------------------------------------
 
+def TestGradioClientQwen270b(text):
+    client = Client("Qwen/Qwen2-72B-Instruct")
+    result = client.predict(
+            query=text, #"Hello!!",
+            history=[],
+            system="You are a helpful assistant.",
+            api_name="/model_chat"
+    )
+    #print(result[1][0]) #All messages in the conversation
+    #print(result[2]) # System prompt
+    return result[1][0][1] # If supporting conversations this needs to return the last message instead
+
+#-----------------------------------------------------------------------------------------------------------------------------------
+
 with gr.Blocks() as demo:
     with gr.Accordion("Config and Asset Assistance - Click to open", open=False):
         gr.HTML("Jonas Tyroller - This problem changes your perspective on game dev - minimise the cost of exploration so you can explore more (17:00) | dont make the same game again but worse (:) <br>https://youtu.be/o5K0uqhxgsE")
         with gr.Accordion("Leaveraging LLMs"):
-            with gr.Tab("Hugging Chat"):
-                gr.HTML("https://huggingface.co/chat<br>Huggingface chat supports - State Management (Threads), Image Generation and editing, Websearch, Document parsing (PDF?), Assistants and larger models than zero gpu can support in July 2024 (Unquantised 30B and above)")
-                gr.HTML("Existing Assistants to use and planning custom assistants placeholder")
             with gr.Tab("ZeroGPU"):
                 gr.HTML("Copy paste any old config to llm and ask to remix is the easiest <br>To bake 'Moral of the story' in you have to be very deliberate")
                 gr.HTML("UI can be media and all items can have media")
@@ -845,23 +857,38 @@ with gr.Blocks() as demo:
                     with gr.Tab("Function Call as FAQ"):
                         gr.HTML("Placeholder for media task query routing as dual purpose in workflow and for user queries as psuedo RAG engine")
                         gr.HTML("https://llama.meta.com/docs/model-cards-and-prompt-formats/llama3_1/#built-in-tooling - The three built-in tools (brave_search, wolfram_alpha, and code interpreter) can be turned on using the system prompt")
+            with gr.Tab("Hugging Chat"):
+                gr.HTML("https://huggingface.co/chat<br>Huggingface chat supports - State Management (Threads), Image Generation and editing, Websearch, Document parsing (PDF?), Assistants and larger models than zero gpu can support in July 2024 (Unquantised 30B and above)")
+                gr.HTML("Existing Assistants to use and planning custom assistants placeholder")
             with gr.Tab("Embedded Spaces and gradio client"):
                 gr.HTML("In Asset Generation Tab under Text")
+            with gr.Tab("Gradio Client"):
+                gr.Interface(fn=TestGradioClientQwen270b, inputs="text", outputs="markdown", description="Single response test of gradio client - Qwen/Qwen2-72B-Instruct, Use for testing like using a space and duplicate for heavy testing")
             with gr.Tab("Preview APIs"):
                 gr.HTML("July 2024 - Gemini, Cohere and Groq rate limit free APIs")
-        gr.Markdown("# Current Workflow = Mermaid Diagram to Story to JSON (through LLM and fix JSON by hand) to Media prompts to Asset Gneration")
-        with gr.Tab("Main problem to solve - Concept combination / integration and non-linear progression planning"):
-            gr.HTML("The story and the gameplay dont have to occur at the same time - eg. ")
-            gr.Markdown("## Prompts / Mermaid diagrams to be made from the ideas for workflow")
-            with gr.Tab("Using Time as a proxy for all conepts?"):
-                gr.HTML("A timeline is the most important part of the story - once that is set you can do anything?")
+        gr.Markdown("# Current Workflow = Mermaid Diagram to (1) Story to (2) JSON (through LLM and fix JSON by hand) to (3) Media prompts to (4) Asset Generation")
+        with gr.Tab("Workflow Stages Examples"):
+            with gr.Tab("Mermaid Diagram to (1) Story"):
+                gr.HTML("Below 70B seem to struggle here")
+                gr.Code(WFStage1prompt , label="Prompt Used")
                 with gr.Row():
                     gr.Textbox(TimeRelatedMermaidStoryAttempttoRefinefrom[0], lines=30)
                     gr.Textbox(TimeRelatedMermaidStoryAttempttoRefinefrom[1], lines=30)
                     gr.Textbox(TimeRelatedMermaidStoryAttempttoRefinefrom[2], lines=30)
                     gr.Textbox(TimeRelatedMermaidStoryAttempttoRefinefrom[3], lines=30)
                     gr.Textbox(TimeRelatedMermaidStoryAttempttoRefinefrom[4], lines=30)
-                    
+            with gr.Tab("Story to (2) JSON (through LLM and fix JSON by hand)"):
+                gr.HTML()
+                gr.Code(WFStage2prompt , label="Prompt Used")
+            with gr.Tab("JSON (through LLM and fix JSON by hand) to (3) Media prompts"):
+                gr.HTML()
+            with gr.Tab("Media prompts to (4) Asset Generation"):
+                gr.HTML()
+        with gr.Tab("Main problem to solve - Concept combination / integration and non-linear progression planning"):
+            gr.HTML("The story and the gameplay dont have to occur at the same time - eg. ")
+            gr.Markdown("## Prompts / Mermaid diagrams to be made from the ideas for workflow")
+            with gr.Tab("Using Time as a proxy for all conepts?"):
+                gr.HTML("A timeline is the most important part of the story - once that is set you can do anything?")
             with gr.Tab("Concept Bashing? Ideas"):
                 with gr.Row():
                     gr.Textbox(TimeRelatedConceptsForIdeaGeneration, lines=30)
@@ -1021,7 +1048,7 @@ Creating more diverse paths through the game""")
                     </div>
                 </div>""")
         with gr.Tab("Themes and Topics"):
-            gr.HTML("https://en.wikipedia.org/wiki/History#Periods https://en.wikipedia.org/wiki/Philosophy")
+            gr.HTML("https://en.wikipedia.org/wiki/History#Periods https://en.wikipedia.org/wiki/Philosophy https://en.wikipedia.org/wiki/Moral_injury")
         with gr.Tab("Old Ideas to merge"):
             gr.HTML("Random Scenario / Song to 'full game' manual or auto is end goal ")
             gr.HTML("Componets (outside Code Support for Config): Decisions (and context explanation), Nested Sections, Media (Especially to affect decisions), Replayability (GTA and Tekken type mechanics in text form), Theme integration (Modified Varibles that affect UI or config order)") 
@@ -1236,8 +1263,8 @@ Creating more diverse paths through the game""")
                     with gr.Accordion("LLM HF Spaces/Sites (Click Here to Open) - Ask for a story and suggestions based on the autoconfig", open=False):
                         with gr.Row():
                             linktochat = gr.Dropdown(choices=["--Function Calling--", "https://groq-demo-groq-tool-use.hf.space",
-                                                            "--Multiple Models--", "https://labs.perplexity.ai/", "https://chat.lmsys.org", "https://sdk.vercel.ai/docs", "https://cyzgab-catch-me-if-you-can.hf.space",
-                                                            "--70B and above--", "https://qwen-qwen-max-0428.hf.space", "https://cohereforai-c4ai-command-r-plus.hf.space", "https://qwen-qwen1-5-110b-chat-demo.hf.space", "https://snowflake-snowflake-arctic-st-demo.hf.space", "https://databricks-dbrx-instruct.hf.space", "https://qwen-qwen1-5-72b-chat.hf.space",
+                                                            "--Multiple Models--", "https://lmsys-gpt-4o-mini-battles.hf.space", "https://labs.perplexity.ai/", "https://chat.lmsys.org", "https://sdk.vercel.ai/docs", "https://cyzgab-catch-me-if-you-can.hf.space",
+                                                            "--70B and above--", "https://llamameta-llama3-1-405b.static.hf.space", "https://qwen-qwen-max-0428.hf.space", "https://cohereforai-c4ai-command-r-plus.hf.space", "https://qwen-qwen1-5-110b-chat-demo.hf.space", "https://snowflake-snowflake-arctic-st-demo.hf.space", "https://databricks-dbrx-instruct.hf.space", "https://qwen-qwen1-5-72b-chat.hf.space",
                                                             "--20B and above--", "https://gokaygokay-gemma-2-llamacpp.hf.space", "https://01-ai-yi-34b-chat.hf.space", "https://cohereforai-c4ai-command-r-v01.hf.space", "https://ehristoforu-mixtral-46-7b-chat.hf.space", "https://mosaicml-mpt-30b-chat.hf.space",
                                                             "--7B and above--", "https://vilarin-mistral-nemo.hf.space", "https://vilarin-llama-3-1-8b-instruct.hf.space", "https://ysharma-chat-with-meta-llama3-8b.hf.space", "https://qwen-qwen1-5-moe-a2-7b-chat-demo.hf.space", "https://deepseek-ai-deepseek-coder-7b-instruct.hf.space", "https://osanseviero-mistral-super-fast.hf.space", "https://artificialguybr-qwen-14b-chat-demo.hf.space", "https://huggingface-projects-llama-2-7b-chat.hf.space",
                                                             "--1B and above--", "https://huggingface.co/spaces/eswardivi/Phi-3-mini-128k-instruct", "https://eswardivi-phi-3-mini-4k-instruct.hf.space", "https://stabilityai-stablelm-2-1-6b-zephyr.hf.space",
@@ -1374,6 +1401,7 @@ Creating more diverse paths through the game""")
                     gr.HTML("Placeholder for models small enough to run on cpu here in this space that can assist")
 
             with gr.Tab("3rd Party - Asset Generation"):
+                gr.HTML("Image - https://www.midjourney.com/showcase")
                 gr.HTML("Audio - https://www.udio.com/home")
                 gr.HTML("Video - https://klingai.com/")
 

relatively_constant_variables.py

@@ -1862,8 +1862,7 @@ Technological limitations: Time travel devices could have cooldown periods, limi
 Ethical dilemmas: Present players with morally ambiguous choices that have far-reaching consequences across time.
 """
 
-TimeRelatedMermaidStoryAttempttoRefinefrom =  ("""gpt-4o
-Use this to write a story and explain how it represents the structure -
+WFStage1prompt = """Use this to write a story and explain how it represents the structure -
 
 graph TD
 subgraph "Actual Timeline"
@@ -1905,10 +1904,10 @@ H3 -.- A4
 H4 -.- A1
 H4 -.- A2
 H4 -.- A3
-H4 -.- A4
-
-
+H4 -.- A4"""
 
+TimeRelatedMermaidStoryAttempttoRefinefrom =  ("""gpt-4o
+                                               
 Once upon a time in a land where time flowed like a river with hidden currents, there was a story that unfolded across three intertwined timelines: the Actual Timeline, the Narrative Timeline, and the Hidden Timeline.
 
 Actual Timeline
@@ -1994,52 +1993,6 @@ Elena’s repeated visits to each location allow her to uncover additional layer
 
 """meta-llama-3.1-405b-instruct
 
-Use this to write a story and explain how it represents the structure -
-
-graph TD
-subgraph "Actual Timeline"
-A1[Location 1 - First Visit]
-A2[Location 2 - First Visit]
-A3[Location 3 - First Visit]
-A4[Location 4 - First Visit]
-A1 --> A2 --> A3 --> A4
-end
-subgraph "Narrative Timeline"
-N1[Location 2 - Story Event 1]
-N2[Location 4 - Story Event 2]
-N3[Location 1 - Story Event 3]
-N4[Location 3 - Story Event 4]
-N1 --> N2 --> N3 --> N4
-end
-subgraph "Hidden Timeline"
-H1[Hidden Event 1]
-H2[Hidden Event 2]
-H3[Hidden Event 3]
-H4[Hidden Event 4]
-end
-A1 -.-> N3
-A2 -.-> N1
-A3 -.-> N4
-A4 -.-> N2
-H1 -.- A1
-H1 -.- A2
-H1 -.- A3
-H1 -.- A4
-H2 -.- A1
-H2 -.- A2
-H2 -.- A3
-H2 -.- A4
-H3 -.- A1
-H3 -.- A2
-H3 -.- A3
-H3 -.- A4
-H4 -.- A1
-H4 -.- A2
-H4 -.- A3
-H4 -.- A4
-
-
-
 Here's a story based on the graph structure:
 
 Emily had always been fascinated by the mysterious disappearances that had taken place in the four locations she was about to visit. She packed her bags, said goodbye to her family, and set off on her journey.
@@ -2121,52 +2074,6 @@ N
 
 """mistral-large-2407
 
-Use this to write a story and explain how it represents the structure -
-
-graph TD
-subgraph "Actual Timeline"
-A1[Location 1 - First Visit]
-A2[Location 2 - First Visit]
-A3[Location 3 - First Visit]
-A4[Location 4 - First Visit]
-A1 --> A2 --> A3 --> A4
-end
-subgraph "Narrative Timeline"
-N1[Location 2 - Story Event 1]
-N2[Location 4 - Story Event 2]
-N3[Location 1 - Story Event 3]
-N4[Location 3 - Story Event 4]
-N1 --> N2 --> N3 --> N4
-end
-subgraph "Hidden Timeline"
-H1[Hidden Event 1]
-H2[Hidden Event 2]
-H3[Hidden Event 3]
-H4[Hidden Event 4]
-end
-A1 -.-> N3
-A2 -.-> N1
-A3 -.-> N4
-A4 -.-> N2
-H1 -.- A1
-H1 -.- A2
-H1 -.- A3
-H1 -.- A4
-H2 -.- A1
-H2 -.- A2
-H2 -.- A3
-H2 -.- A4
-H3 -.- A1
-H3 -.- A2
-H3 -.- A3
-H3 -.- A4
-H4 -.- A1
-H4 -.- A2
-H4 -.- A3
-H4 -.- A4
-
-
-
 Story: The Unraveling of Time
 Actual Timeline
 In the quaint town of Harborside, four locations form the backbone of daily life: the Library (Location 1), the Market (Location 2), the Park (Location 3), and the Lighthouse (Location 4). The story unfolds as the protagonist, Emily, visits these locations in sequence.
@@ -2245,52 +2152,6 @@ Actual Timeline: This represents the chronological order
 
 """gpt-4o-mini-2024-07-18
 
-Use this to write a story and explain how it represents the structure -
-
-graph TD
-subgraph "Actual Timeline"
-A1[Location 1 - First Visit]
-A2[Location 2 - First Visit]
-A3[Location 3 - First Visit]
-A4[Location 4 - First Visit]
-A1 --> A2 --> A3 --> A4
-end
-subgraph "Narrative Timeline"
-N1[Location 2 - Story Event 1]
-N2[Location 4 - Story Event 2]
-N3[Location 1 - Story Event 3]
-N4[Location 3 - Story Event 4]
-N1 --> N2 --> N3 --> N4
-end
-subgraph "Hidden Timeline"
-H1[Hidden Event 1]
-H2[Hidden Event 2]
-H3[Hidden Event 3]
-H4[Hidden Event 4]
-end
-A1 -.-> N3
-A2 -.-> N1
-A3 -.-> N4
-A4 -.-> N2
-H1 -.- A1
-H1 -.- A2
-H1 -.- A3
-H1 -.- A4
-H2 -.- A1
-H2 -.- A2
-H2 -.- A3
-H2 -.- A4
-H3 -.- A1
-H3 -.- A2
-H3 -.- A3
-H3 -.- A4
-H4 -.- A1
-H4 -.- A2
-H4 -.- A3
-H4 -.- A4
-
-
-
 Title: The Hidden Threads of Time
 
 Story:
@@ -2347,52 +2208,6 @@ Hidden Timeline: This timeline consists of events and truths that remain obscure
 
 """athene-70b
 
-Use this to write a story and explain how it represents the structure -
-
-graph TD
-subgraph "Actual Timeline"
-A1[Location 1 - First Visit]
-A2[Location 2 - First Visit]
-A3[Location 3 - First Visit]
-A4[Location 4 - First Visit]
-A1 --> A2 --> A3 --> A4
-end
-subgraph "Narrative Timeline"
-N1[Location 2 - Story Event 1]
-N2[Location 4 - Story Event 2]
-N3[Location 1 - Story Event 3]
-N4[Location 3 - Story Event 4]
-N1 --> N2 --> N3 --> N4
-end
-subgraph "Hidden Timeline"
-H1[Hidden Event 1]
-H2[Hidden Event 2]
-H3[Hidden Event 3]
-H4[Hidden Event 4]
-end
-A1 -.-> N3
-A2 -.-> N1
-A3 -.-> N4
-A4 -.-> N2
-H1 -.- A1
-H1 -.- A2
-H1 -.- A3
-H1 -.- A4
-H2 -.- A1
-H2 -.- A2
-H2 -.- A3
-H2 -.- A4
-H3 -.- A1
-H3 -.- A2
-H3 -.- A3
-H3 -.- A4
-H4 -.- A1
-H4 -.- A2
-H4 -.- A3
-H4 -.- A4
-
-
-
 Story: The Cartographer's Enigma
 
 Protagonist Emilia, a skilled cartographer, receives a cryptic atlas from her reclusive mentor, featuring four locations: Ravenshire, Luminaria, Celestia's Peak, and Argentum Falls. The atlas hints at a centuries-old conspiracy, weaving together seemingly unrelated events across these sites.
@@ -2422,6 +2237,26 @@ Interconnectedness: The graph visually demonstrates how each location, narrative
 
 )
 
+WFStage2prompt =  """Please use the below config as a template to covert the story to config format:
+
+{
+  "masterlocation1": {
+    "location1": {
+      "description": "UI - Experience Bar",
+      "events": [],
+      "choices": [
+        "continue"
+      ],
+      "transitions": {
+        "continue": "masterlocation1_location2"
+      },
+      "media": [],
+      "developernotes": []
+    },
+
+"""
+
+
 TimeRelatedMermaidStoryAttempttoRefinefromtoJSON = (
 """
 {