Moved all server files to server/

server/trials/finetuning/inference_fine_tuned.py

@@ -0,0 +1,24 @@
+# Steps to prepare data and submit/check OpenAI finetuning
+# import subprocess
+# subprocess.run("openai tools fine_tunes.prepare_data -f " + "finetuning_dataset.jsonl")
+# export OPENAI_API_KEY=
+# openai api fine_tunes.create -t <TRAIN_FILE_ID_OR_PATH> -m <BASE_MODEL>
+# openai api fine_tunes.list
+
+
+import openai
+
+# Use your OpenAI API Key
+openai.api_key = ""
+
+sample_chunks = ["You all just came off of your incredible Google Cloud next conference where you released a wide variety of functionality and features and new products across artisan television and also across the entire sort of cloud ecosystem . You want to just first by walking through , first start by walking through all the innovations that you sort of released and what you 're excited about when you come to Google Cloud ? Now our vision is super simple .  If you look at what smartphones did for a consumer , you know they took a computer and internet browser , a communication device , and a camera , and made it so that it 's in everybody 's pocket , so it really brought computation to every person . We feel that , you know , our , what we 're trying to do is take all the technological innovation that Google 's doing , but make it super simple so that everyone can consume it . And so that includes our global data center footprint , all the new types of hardware and large-scale systems we work on , the software that we 're making available for people to do high-scale computation , tools for data processing , tools for cybersecurity , processing , tools for cyber security , tools for machine learning , but make it so simple that everyone can use it . And every step that we do to simplify things for people , we think adoption can grow . And so that 's a lot of what we 've done these last three , four years , and we made a number of announcements that next in machine learning and AI in particular , you know , we look at our work as four elements , how we take our large-scale compute systems that were building for AI and how we make that available to everybody .  Second , what we 're doing with the software stacks and top of it , things like jacks and other things and how we 're making those available to everybody . Third is advances because different people have different levels of expertise . Some people say I need the hardware to build my own large language model or algorithm . Other people say , look , I really need to use a building block . You guys give me .  So , 30s we 've done a lot with AutoML and we announce new capability for image , video , and translation to make it available to everybody .  And then lastly , we 're also building completely packaged solutions for some areas and we announce some new stuff . -> ",
+                 " We 're joined next by Thomas Curian , CEO of Google Cloud , and Alexander Wang , CEO and founder of Scale AI . Thomas joined Google in November 2018 as the CEO of Google Cloud . Prior to Google , Thomas spent 22 years at Oracle , where most recently he was president of product development . Before that , Thomas worked at McKinsey as a business analyst and engagement manager . His nearly 30 years of experience have given him a deep knowledge of engineering enterprise relationships and leadership of large organizations . Thomas 's degrees include an MBA in administration and management from Stanford University , as an RJ Miller scholar and a BSEE in electrical engineering and computer science from Princeton University , where he graduated suma cum laude .  Thomas serves as a member of the Stanford graduate School of Business Advisory Council and Princeton University School of Engineering Advisory Council . Please welcome to the stage , Thomas Curian and Alexander Wang . This is a super exciting conversation . Thanks for being here , Thomas . - > "]
+
+# Give your finetuned model name here
+# "davinci:ft-personal-2023-07-14-10-43-51"
+model_name = ""
+response = openai.Completion.create(
+    model=model_name,
+    prompt=sample_chunks[0])
+
+print(response)

server/trials/finetuning/youtube_scraping.py

@@ -0,0 +1,98 @@
+import json
+import yt_dlp as youtube_dl
+from whisper_jax import FlaxWhisperPipline
+import jax.numpy as jnp
+
+# Function to extract chapter information from a YouTube video URL
+def get_youtube_chapters(video_id):
+    video_url = "https://www.youtube.com/watch?v=" + video_id
+    ydl_opts = {
+        'extract_flat': 'in_playlist',
+        'skip_download': True,
+        'quiet': True,
+    }
+
+    with youtube_dl.YoutubeDL(ydl_opts) as ydl:
+        video_info = ydl.extract_info(video_url, download=False)
+
+    chapters = []
+
+    if 'chapters' in video_info:
+        for chapter in video_info['chapters']:
+            start_time = chapter['start_time']
+            end_time = chapter['end_time']
+            title = chapter['title']
+
+            chapters.append({
+                'start': start_time,
+                'end': end_time,
+                'title': title
+            })
+
+    return chapters
+
+
+# Function to extract video transcription using yt_dlp
+def get_youtube_transcription(video_id):
+    ydl_opts = {
+            'format': 'bestaudio/best',
+            'postprocessors': [{
+                    'key': 'FFmpegExtractAudio',
+                    'preferredcodec': 'mp3',
+                    'preferredquality': '192',
+            }],
+            'outtmpl': './artefacts/audio',  # Specify output file path and name
+    }
+
+    # Download the audio
+    with youtube_dl.YoutubeDL(ydl_opts) as ydl:
+        ydl.download(["https://www.youtube.com/watch?v=" + video_id])
+    media_file = "./artefacts/audio.mp3"
+
+    pipeline = FlaxWhisperPipline("openai/whisper-" + "tiny",
+                                  dtype=jnp.float16,
+                                  batch_size=16)
+    whisper_result = pipeline(media_file, return_timestamps=True)
+    return whisper_result["chunks"]
+
+
+
+# Function to scrape YouTube video transcripts and chapter information
+def scrape_youtube_data(video_id):
+    transcript_text = get_youtube_transcription(video_id)
+    chapters = get_youtube_chapters(video_id)
+    print("transcript_text", transcript_text)
+    print("chapters", chapters)
+    return transcript_text, chapters
+
+
+# Function to generate fine-tuning dataset from YouTube data
+def generate_finetuning_dataset(video_ids):
+    prompt_completion_pairs = []
+    for video_id in video_ids:
+        transcript_text, chapters = scrape_youtube_data(video_id)
+        if transcript_text is not None and chapters is not None:
+            for chapter in chapters:
+                start_time = chapter["start"]
+                end_time = chapter["end"]
+                chapter_text = chapter["title"]
+
+                prompt = ""
+                for transcript in transcript_text:
+                    if transcript["timestamp"][0] >= start_time and transcript["timestamp"][1] < end_time:
+                        prompt += transcript["text"]
+
+                if prompt is not None:
+                    completion = chapter_text
+                    prompt_completion_pairs.append({"prompt": prompt, "completion": completion})
+
+    return prompt_completion_pairs
+
+
+# Add all the video ids here, the videos must have captions [chapters]
+video_ids = ["yTnSEZIwnkU"]
+dataset = generate_finetuning_dataset(video_ids)
+
+with open("finetuning_dataset.jsonl", "w", encoding="utf-8") as file:
+    for example in dataset:
+        file.write(json.dumps(example) + "\n")