Duplicate from awacke1/Memory-Chat-Story-Generator-ChatGPT

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Memory Chat Story Generator ChatGPT
+emoji: 📚
+colorFrom: green
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.24.1
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: awacke1/Memory-Chat-Story-Generator-ChatGPT
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,151 @@
+import gradio as gr
+import os 
+import json 
+import requests
+
+#Streaming endpoint 
+API_URL = "https://api.openai.com/v1/chat/completions" #os.getenv("API_URL") + "/generate_stream"
+OPENAI_API_KEY= os.environ["HF_TOKEN"] # Add a token to this space .  Then copy it to the repository secret in this spaces settings panel.  os.environ reads from there.
+# Keys for Open AI ChatGPT API usage are created from here: https://platform.openai.com/account/api-keys
+
+def predict(inputs, top_p, temperature, chat_counter, chatbot=[], history=[]):  #repetition_penalty, top_k
+
+    # 1. Set up a payload
+    payload = {
+    "model": "gpt-3.5-turbo",
+    "messages": [{"role": "user", "content": f"{inputs}"}],
+    "temperature" : 1.0,
+    "top_p":1.0,
+    "n" : 1,
+    "stream": True,
+    "presence_penalty":0,
+    "frequency_penalty":0,
+    }
+
+    # 2. Define your headers and add a key from https://platform.openai.com/account/api-keys
+    headers = {
+    "Content-Type": "application/json",
+    "Authorization": f"Bearer {OPENAI_API_KEY}"
+    }
+
+    # 3. Create a chat counter loop that feeds [Predict next best anything based on last input and attention with memory defined by introspective attention over time]
+    print(f"chat_counter - {chat_counter}")
+    if chat_counter != 0 :
+        messages=[]
+        for data in chatbot:
+          temp1 = {}
+          temp1["role"] = "user" 
+          temp1["content"] = data[0] 
+          temp2 = {}
+          temp2["role"] = "assistant" 
+          temp2["content"] = data[1]
+          messages.append(temp1)
+          messages.append(temp2)
+        temp3 = {}
+        temp3["role"] = "user" 
+        temp3["content"] = inputs
+        messages.append(temp3)
+        #messages
+        payload = {
+        "model": "gpt-3.5-turbo",
+        "messages": messages, #[{"role": "user", "content": f"{inputs}"}],
+        "temperature" : temperature, #1.0,
+        "top_p": top_p, #1.0,
+        "n" : 1,
+        "stream": True,
+        "presence_penalty":0,
+        "frequency_penalty":0,
+        }
+    chat_counter+=1
+
+    # 4. POST it to OPENAI API
+    history.append(inputs)
+    print(f"payload is - {payload}")
+    # make a POST request to the API endpoint using the requests.post method, passing in stream=True
+    response = requests.post(API_URL, headers=headers, json=payload, stream=True)
+    #response = requests.post(API_URL, headers=headers, json=payload, stream=True)
+    token_counter = 0 
+    partial_words = "" 
+
+    # 5. Iterate through response lines and structure readable response
+    # TODO - make this parse out markdown so we can have similar interface
+    counter=0
+    for chunk in response.iter_lines():
+        #Skipping first chunk
+        if counter == 0:
+          counter+=1
+          continue
+        #counter+=1
+        # check whether each line is non-empty
+        if chunk.decode() :
+          chunk = chunk.decode()
+          # decode each line as response data is in bytes
+          if len(chunk) > 12 and "content" in json.loads(chunk[6:])['choices'][0]['delta']:
+              #if len(json.loads(chunk.decode()[6:])['choices'][0]["delta"]) == 0:
+              #  break
+              partial_words = partial_words + json.loads(chunk[6:])['choices'][0]["delta"]["content"]
+              if token_counter == 0:
+                history.append(" " + partial_words)
+              else:
+                history[-1] = partial_words
+              chat = [(history[i], history[i + 1]) for i in range(0, len(history) - 1, 2) ]  # convert to tuples of list
+              token_counter+=1
+              yield chat, history, chat_counter  # resembles {chatbot: chat, state: history}  
+                   
+
+def reset_textbox():
+    return gr.update(value='')
+
+title = """<h1 align="center">Memory Chat Story Generator ChatGPT</h1>"""
+description = """
+
+## ChatGPT Datasets 📚
+- WebText
+- Common Crawl
+- BooksCorpus
+- English Wikipedia
+- Toronto Books Corpus
+- OpenWebText
+
+## ChatGPT Datasets - Details 📚
+- **WebText:** A dataset of web pages crawled from domains on the Alexa top 5,000 list. This dataset was used to pretrain GPT-2.
+  - [WebText: A Large-Scale Unsupervised Text Corpus by Radford et al.](https://paperswithcode.com/dataset/webtext)
+- **Common Crawl:** A dataset of web pages from a variety of domains, which is updated regularly. This dataset was used to pretrain GPT-3.
+  - [Language Models are Few-Shot Learners](https://paperswithcode.com/dataset/common-crawl) by Brown et al.
+- **BooksCorpus:** A dataset of over 11,000 books from a variety of genres.
+  - [Scalable Methods for 8 Billion Token Language Modeling](https://paperswithcode.com/dataset/bookcorpus) by Zhu et al.
+- **English Wikipedia:** A dump of the English-language Wikipedia as of 2018, with articles from 2001-2017.
+  - [Improving Language Understanding by Generative Pre-Training](https://huggingface.co/spaces/awacke1/WikipediaUltimateAISearch?logs=build) Space for Wikipedia Search
+- **Toronto Books Corpus:** A dataset of over 7,000 books from a variety of genres, collected by the University of Toronto.
+  - [Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond](https://paperswithcode.com/dataset/bookcorpus) by Schwenk and Douze.
+- **OpenWebText:** A dataset of web pages that were filtered to remove content that was likely to be low-quality or spammy. This dataset was used to pretrain GPT-3.
+  - [Language Models are Few-Shot Learners](https://paperswithcode.com/dataset/openwebtext) by Brown et al.
+  
+  """
+
+# 6. Use Gradio to pull it all together
+with gr.Blocks(css = """#col_container {width: 1000px; margin-left: auto; margin-right: auto;}
+                #chatbot {height: 520px; overflow: auto;}""") as demo:
+
+                    
+    gr.HTML(title)
+
+                    
+    with gr.Column(elem_id = "col_container"):
+        chatbot = gr.Chatbot(elem_id='chatbot') #c
+        inputs = gr.Textbox(placeholder= "Hi there!", label= "Type an input and press Enter") #t
+        state = gr.State([]) #s
+        b1 = gr.Button()
+    
+        with gr.Accordion("Parameters", open=False):
+            top_p = gr.Slider( minimum=-0, maximum=1.0, value=1.0, step=0.05, interactive=True, label="Top-p (nucleus sampling)",)
+            temperature = gr.Slider( minimum=-0, maximum=5.0, value=1.0, step=0.1, interactive=True, label="Temperature",)
+            chat_counter = gr.Number(value=0, visible=False, precision=0)
+
+    inputs.submit( predict, [inputs, top_p, temperature,chat_counter, chatbot, state], [chatbot, state, chat_counter],)
+    b1.click( predict, [inputs, top_p, temperature, chat_counter, chatbot, state], [chatbot, state, chat_counter],)
+    b1.click(reset_textbox, [], [inputs])
+    inputs.submit(reset_textbox, [], [inputs])
+                    
+    gr.Markdown(description)
+    demo.queue().launch(debug=True)