Duplicate from Shad0ws/Meeting-Summarizer

Co-authored-by: Shahnab Ahmed <[email protected]>

.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: Meeting Summarizer
+emoji: 🏢
+colorFrom: yellow
+colorTo: purple
+sdk: gradio
+sdk_version: 3.20.1
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: Shad0ws/Meeting-Summarizer
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,103 @@
+import gradio as gr
+import openai
+import tiktoken
+from multiprocessing.pool import ThreadPool
+
+enc = tiktoken.get_encoding("cl100k_base")
+
+MODES = {
+    "Short summary": "Succintly summarize the following meeting transcript in a single paragraph.",
+    "Detailed summary": "Summarize the following meeting transcript. The summary should include all the important points discussed in the meeting.",
+    "Action points": "Summarize the following meeting transcript in form of action points.",
+    "Further actions": "Who and what should be done next? Summarize the following meeting transcript in form of action points.",
+    "Custom": "",
+}
+
+SUMMARY_PROMPT = "Summarize the following meeting in very great detail. The summary should include all the important points discussed in the meeting."
+
+def summarize_part(text, api_key):
+    response = openai.ChatCompletion.create(
+        model="gpt-3.5-turbo",
+        messages=[
+        { "role": "system", "content": f"You are a meeting organizer. You want to summarize a meeting. You are given the following transcript of the meeting. {SUMMARY_PROMPT}" },
+        { "role": "user", "content": text },
+        ],
+        api_key=api_key,
+    )
+    return response["choices"][0]["message"]["content"]
+
+def shorten_text(text, api_key):
+    # Split into chunks so that each chunk is less than 3000 words (not characters!)
+    # Overlap by halves.
+    chunks = []
+    words = text.split()
+    for i in range(0, len(words), 1500):
+        chunk = ""
+        while len(enc.encode(chunk)) < 4000 and i < len(words):
+            chunk += words[i] + " "
+            i += 1
+        chunks.append(chunk)
+
+    with ThreadPool(4) as pool:
+        shortened = pool.starmap(summarize_part, zip(chunks, [api_key]*len(chunks)))
+    
+    return "".join(shortened)
+
+def modify_text(text, api_key, command, custom_command=None):
+    if command == "Custom":
+        prompt = custom_command
+    else:
+        prompt = MODES[command]
+
+    if len(enc.encode(text)) < 4096:
+        response = openai.ChatCompletion.create(
+            model="gpt-3.5-turbo",
+            messages=[
+            { "role": "system", "content": f"You are a meeting organizer. You want to summarize a meeting. You are given the following transcript of the meeting. {prompt}" },
+            { "role": "user", "content": text },
+            ],
+            api_key=api_key,
+        )
+        return response["choices"][0]["message"]["content"]
+    else:
+        prompt = prompt.replace("meeting transcript", "meeting parts")
+        shortened = text
+        while len(enc.encode(shortened)) > 4096:
+            shortened = shorten_text(shortened, api_key)
+        response = openai.ChatCompletion.create(
+            model="gpt-3.5-turbo",
+            messages=[
+            { "role": "system", "content": f"You are a meeting organizer. You want to summarize a meeting. You are given the following summary of the meeting parts. {prompt}" },
+            { "role": "user", "content": shortened },
+            ],
+            api_key=api_key,
+        )
+        return response["choices"][0]["message"]["content"]
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Meeting Summarizer")
+    gr.Markdown("#### Short Summary | Detailed Summary | Action points | Further Actions | Custom Command")
+    gr.Markdown("###### Turbo-charged by GPT-3.5-turbo")
+    with gr.Row():
+        with gr.Column():
+            api_key = gr.Textbox(lines=1,type='password', label="OpenAI API Key")
+            input_text = gr.Textbox(lines=15, label="Meeting Transcript")
+        with gr.Column():
+            command = gr.Dropdown(list(MODES.keys()), label="Command", value="Short summary")
+            custom_command = gr.Textbox(lines=2, label="Custom command", visible=False, value="Summarize the following meeting transcript in a single paragraph. The summary should include all the important points discussed in the meeting.")
+            output_text = gr.Textbox(lines=10, label="Summary")
+
+
+    def show_command(command):
+        if command == "Custom":
+            return {custom_command: gr.update(visible=True)}
+        else:
+            return {custom_command: gr.update(visible=False)}
+        
+    command.change(show_command, command, custom_command)
+
+    button = gr.Button(label="Process")
+    button.click(modify_text, [input_text, api_key, command, custom_command], output_text)
+
+demo.title = "Meeting Summarizer-Demo"
+demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+openai
+tiktoken==0.3.0