restructuring

trials/title_summary/api.py

@@ -0,0 +1,57 @@
+import requests
+import spacy
+
+# Enter the Machine where the LLM is hosted
+LLM_MACHINE_IP = ""
+# This is the URL of text-generation-webui
+URL = f"http://{LLM_MACHINE_IP}:5000/api/v1/generate"
+
+headers = {
+        "Content-Type": "application/json"
+}
+
+
+def split_text_file(filename, token_count):
+    nlp = spacy.load('en_core_web_md')
+
+    with open(filename, 'r') as file:
+        text = file.read()
+
+    doc = nlp(text)
+    total_tokens = len(doc)
+
+    parts = []
+    start_index = 0
+
+    while start_index < total_tokens:
+        end_index = start_index + token_count
+        part_tokens = doc[start_index:end_index - 5]
+        part = ' '.join(token.text for token in part_tokens)
+        parts.append(part)
+        start_index = end_index
+
+    return parts
+
+
+final_summary = ""
+parts = split_text_file("transcript.txt", 1600)
+
+for part in parts:
+    prompt = f"""
+              ### Human:
+             Given the following text, distill the most important information 
+             into a short summary:  {part}
+
+              ### Assistant:
+              """
+    data = {
+            "prompt": prompt
+    }
+    try:
+        response = requests.post(URL, headers=headers, json=data)
+        print(response.json())
+    except Exception as e:
+        print(str(e))
+
+with open("summary.txt", "w") as sum:
+    sum.write(" ".join(final_summary))

trials/title_summary/bert.py

@@ -0,0 +1,43 @@
+import torch
+from transformers import BertTokenizer, BertModel
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+
+# Load the pre-trained BERT model and tokenizer
+model_name = "bert-base-uncased"
+model = BertModel.from_pretrained(model_name)
+tokenizer = BertTokenizer.from_pretrained(model_name)
+
+# Set the device to use
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+# Load the SentenceTransformer model
+sentence_transformer_model = SentenceTransformer('average_word_embeddings_glove.6B.300d')
+
+# Define the input text
+text = "Your input text to be summarized goes here."
+
+# Tokenize the text
+tokens = tokenizer.tokenize(text)
+input_ids = tokenizer.convert_tokens_to_ids(tokens)
+input_ids = torch.tensor([input_ids]).to(device)
+
+# Get the BERT model output
+with torch.no_grad():
+    outputs = model(input_ids)[0]  # Extract the last hidden states
+
+# Calculate sentence embeddings
+sentence_embeddings = outputs.mean(dim=1).squeeze().cpu().numpy()
+input_text_embedding = sentence_transformer_model.encode([text])[0]
+
+# Calculate cosine similarity between sentences and input text
+similarity_scores = cosine_similarity([input_text_embedding], sentence_embeddings)
+
+# Sort the sentences by similarity scores in descending order
+sorted_sentences = [sent for _, sent in sorted(zip(similarity_scores[0], sentences), reverse=True)]
+
+# Choose the top sentences as the summary
+num_summary_sentences = 2  # Adjust as needed
+summary = ". ".join(sorted_sentences[:num_summary_sentences])
+print("Summary:", summary)

trials/title_summary/gpt2.py

@@ -0,0 +1,101 @@
+# Approach 1
+from transformers import GPTNeoForCausalLM, GPT2Tokenizer
+
+model_name = 'EleutherAI/gpt-neo-1.3B'
+tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+model = GPTNeoForCausalLM.from_pretrained(model_name)
+
+conversation = """
+Summarize the following conversation in 3 key sentences:
+
+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 .
+"""
+
+input_ids = tokenizer.encode(conversation, return_tensors='pt')
+
+output = model.generate(input_ids,
+                        max_length=30,
+                        num_return_sequences=1)
+
+caption = tokenizer.decode(output[0], skip_special_tokens=True)
+print("Caption:", caption[len(input_ids):])
+
+
+# Approach 2
+import torch
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+
+model_name = "gpt2"
+tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+model = GPT2LMHeadModel.from_pretrained(model_name)
+
+model.eval()
+
+text = """
+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 . "
+"""
+
+tokenizer.pad_token = tokenizer.eos_token
+input_ids = tokenizer.encode(text,
+                             max_length=100,
+                             truncation=True,
+                             return_tensors="pt")
+attention_mask = torch.ones(input_ids.shape, dtype=torch.long)
+output = model.generate(input_ids,
+                        max_new_tokens=20,
+                        num_return_sequences=1,
+                        num_beams=2,
+                        attention_mask=attention_mask)
+
+chapter_titles = [tokenizer.decode(output[i], skip_special_tokens=True) for i in range(output.shape[0])]
+for i, title in enumerate(chapter_titles):
+    print("Caption: ", title)
+
+# Approach 3
+
+import torch
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+
+
+def generate_response(conversation, max_length=100):
+    input_text = ""
+    for entry in conversation:
+        role = entry["role"]
+        content = entry["content"]
+        input_text += f"{role}: {content}\n"
+
+    # Tokenize the entire conversation
+    input_ids = tokenizer.encode(input_text, return_tensors="pt")
+
+    # Generate text based on the entire conversation
+    with torch.no_grad():
+        output = model.generate(input_ids, pad_token_id=tokenizer.eos_token_id)
+
+    # Decode the generated text and return it
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    return response
+
+
+if __name__ == "__main__":
+
+    # Call appropriate approach from the main while experimenting
+    model_name = "gpt2"
+    model = GPT2LMHeadModel.from_pretrained(model_name)
+    tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+
+    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 . "
+    ]
+
+    conversation = [
+            {"role": "system", "content": "Summarize this text"},
+            {"role": "user", "content": " text : " + sample_chunks[0]},
+    ]
+
+    response = generate_response(conversation)
+    print("Response:", response)

trials/title_summary/incsum.py

@@ -0,0 +1,157 @@
+import spacy
+import sys
+
+
+# Observe the incremental summaries by performing summaries in chunks
+with open("transcript.txt") as f:
+    transcription = f.read()
+
+
+def split_text_file(filename, token_count):
+    nlp = spacy.load('en_core_web_md')
+
+    with open(filename, 'r') as file:
+        text = file.read()
+
+    doc = nlp(text)
+    total_tokens = len(doc)
+
+    parts = []
+    start_index = 0
+
+    while start_index < total_tokens:
+        end_index = start_index + token_count
+        part_tokens = doc[start_index:end_index]
+        part = ' '.join(token.text for token in part_tokens)
+        parts.append(part)
+        start_index = end_index
+
+    return parts
+
+
+# Set the chunk length here to split the transcript and test
+MAX_CHUNK_LENGTH = 1000
+
+chunks = split_text_file("transcript.txt", MAX_CHUNK_LENGTH)
+print("Number of chunks", len(chunks))
+
+# Write chunks to file to refer to input vs output, separated by blank lines
+with open("chunks" + str(MAX_CHUNK_LENGTH) + ".txt", "a") as f:
+    for c in chunks:
+        f.write(c + "\n\n")
+
+# If we want to run only a certain model, type the option while running
+# ex. python incsum.py 1 => will run approach 1
+# If no input, will run all approaches
+
+try:
+    index = sys.argv[1]
+except:
+    index = None
+
+# Approach 1 : facebook/bart-large-cnn
+if index == "1" or index is None:
+    SUMMARY_MODEL = "facebook/bart-large-cnn"
+    MIN_LENGTH = 5
+    MAX_LENGTH = 10
+    BEAM_SIZE = 2
+
+    print("Performing chunk summary : " + SUMMARY_MODEL)
+
+    from transformers import BartTokenizer, BartForConditionalGeneration
+
+    tokenizer = BartTokenizer.from_pretrained(SUMMARY_MODEL)
+    model = BartForConditionalGeneration.from_pretrained(SUMMARY_MODEL)
+    summaries = []
+    for c in chunks:
+        input_ids = tokenizer.encode(c,
+                                     truncation=True,
+                                     max_length=MAX_CHUNK_LENGTH,
+                                     padding="max_length",
+                                     return_tensors='pt')
+        summary_ids = model.generate(
+                input_ids,
+                num_beams=BEAM_SIZE,
+                max_length=56,
+                early_stopping=True,
+                length_penalty=1.0)
+        summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+        summaries.append(summary)
+
+    with open("bart-summaries.txt", "a") as f:
+        for summary in summaries:
+            f.write(summary + "\n\n")
+
+# Approach 2
+if index == "2" or index is None:
+    print("Performing chunk summary : " + "gpt-neo-1.3B")
+
+    import torch
+    from transformers import GPTNeoForCausalLM, GPT2Tokenizer
+
+    model = GPTNeoForCausalLM.from_pretrained("EleutherAI/gpt-neo-1.3B")
+    tokenizer = GPT2Tokenizer.from_pretrained("EleutherAI/gpt-neo-1.3B")
+    tokenizer.add_special_tokens({'pad_token': '[PAD]'})
+    summaries = []
+
+    for c in chunks:
+        input_ids = tokenizer.encode(c,
+                                     truncation=True,
+                                     return_tensors='pt')
+        input_length = input_ids.shape[1]
+        attention_mask = torch.ones(input_ids.shape, dtype=torch.long)
+
+        max_summary_length = 100
+        max_length = input_length + max_summary_length
+
+        output = model.generate(input_ids,
+                                max_length=max_length,
+                                attention_mask=attention_mask,
+                                pad_token_id=model.config.eos_token_id,
+                                num_beams=4,
+                                length_penalty=2.0,
+                                early_stopping=True)
+        summary_ids = output[0, input_length:]
+        summary = tokenizer.decode(summary_ids, skip_special_tokens=True)
+        summaries.append(summary)
+        with open("gptneo1.3B-summaries.txt", "a") as f:
+            f.write(summary + "\n\n")
+
+# Approach 3
+if index == "3" or index is None:
+    print("Performing chunk summary : " + "mpt-7B")
+
+    import torch
+    import transformers
+    from transformers import AutoTokenizer
+
+    config = transformers.AutoConfig.from_pretrained('mosaicml/mpt-7b',
+                                                     trust_remote_code=True)
+    config.attn_config['attn_impl'] = 'triton'
+    config.max_seq_len = 1024
+    config.init_device = "meta"
+
+    model = transformers.AutoModelForCausalLM.from_pretrained(
+            'mosaicml/mpt-7b',
+            trust_remote_code=True,
+            torch_dtype=torch.bfloat16
+    )
+
+    tokenizer = AutoTokenizer.from_pretrained('EleutherAI/gpt-neox-20b')
+
+    summaries = []
+    for c in chunks:
+        input_ids = tokenizer.encode(c, return_tensors="pt")
+        attention_mask = torch.ones(input_ids.shape, dtype=torch.long)
+        output = model.generate(input_ids,
+                                max_new_tokens=25,
+                                attention_mask=attention_mask,
+                                pad_token_id=model.config.eos_token_id,
+                                num_return_sequences=1)
+        summary = tokenizer.decode(output[0],
+                                   skip_special_tokens=True)
+        summaries.append(summary)
+
+    with open("mpt-7b-summaries.txt", "a") as f:
+        for summary in summaries:
+            f.write(summary + "\n\n")

trials/title_summary/openai_endpoint.py

@@ -0,0 +1,37 @@
+# Use OpenAI API endpoint to send data to OpenAI
+# along with prompts to caption/summarize the conversation
+
+import openai
+
+openai.api_key = ""
+
+# to caption, user prompt used : "caption this conversation"
+#             max_tokens=20
+
+# to incremental summarize, user prompt used : "summarize this conversation in a few sentences by taking key points"
+#               max_tokens=300
+
+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 ."]
+
+conversation = [
+        {"role": "system",
+         "content": sample_chunks[1]},
+        {"role": "user",
+         "content": "summarize this conversation in a few sentences by taking key points"}
+]
+
+model = "gpt-3.5-turbo"
+response = openai.ChatCompletion.create(model=model,
+                                        messages=conversation,
+                                        n=1,
+                                        max_tokens=300)
+
+# Try fine tuned model
+# model = "davinci:ft-personal-2023-07-14-10-43-51"
+# response = openai.Completion.create(model=model,
+#                                         prompt=sample_chunks[0] + " -> ")
+
+caption = response.choices[0]
+print(caption)

trials/title_summary/pegasus.py

@@ -0,0 +1,33 @@
+from transformers import PegasusForConditionalGeneration, PegasusTokenizer
+import torch
+# Load the Pegasus model and tokenizer
+model_name = "google/pegasus-large"
+model = PegasusForConditionalGeneration.from_pretrained(model_name)
+tokenizer = PegasusTokenizer.from_pretrained(model_name)
+
+# Set the device to use
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+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 ."]
+
+
+# Define the input text for summarization
+text = sample_chunks[1]
+
+inputs = tokenizer(text, truncation=True, padding="longest", return_tensors="pt").to(device)
+
+# Generate the summary
+summary_ids = model.generate(
+    inputs["input_ids"],
+    attention_mask=inputs["attention_mask"],
+    max_length=200,
+    num_beams=4,
+    length_penalty=2.0,
+    early_stopping=True,
+)
+
+# Decode and print the summary
+summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+print("Summary:", summary)

trials/title_summary/t5.py

@@ -0,0 +1,27 @@
+from transformers import T5ForConditionalGeneration, T5Tokenizer
+import torch
+# Load the T5 model and tokenizer
+model_name = "t5-base"
+model = T5ForConditionalGeneration.from_pretrained(model_name)
+tokenizer = T5Tokenizer.from_pretrained(model_name)
+
+# Set the device to use
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+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 ."]
+
+
+# Define the input text for summarization
+text = "Summarize the following text in 3 key points. text : " + sample_chunks[1]
+
+# Tokenize the input text
+inputs = tokenizer.encode(text, return_tensors="pt").to(device)
+
+# Generate the summary
+summary_ids = model.generate(inputs, max_length=1000, num_beams=4, early_stopping=True)
+
+# Decode and print the summary
+summary = tokenizer.decode(summary_ids.squeeze(), skip_special_tokens=True)
+print("Summary:", summary)

trials/title_summary/vicuna.py

@@ -0,0 +1,44 @@
+from gpt4all import GPT4All
+
+model = GPT4All("/Users/gokulmohanarangan/Library/Application Support/nomic.ai/GPT4All/ggml-vicuna-13b-1.1-q4_2.bin")
+
+import spacy
+
+
+def split_text_file(filename, token_count):
+    nlp = spacy.load('en_core_web_md')
+
+    with open(filename, 'r') as file:
+        text = file.read()
+
+    doc = nlp(text)
+    total_tokens = len(doc)
+
+    parts = []
+    start_index = 0
+
+    while start_index < total_tokens:
+        end_index = start_index + token_count
+        part_tokens = doc[start_index:end_index]
+        part = ' '.join(token.text for token in part_tokens)
+        parts.append(part)
+        start_index = end_index
+
+    return parts
+
+parts = split_text_file("transcript.txt", 1800)
+final_summary = []
+for part in parts:
+       prompt = f"""
+              ### Human:
+              Summarize the following text without missing any key points and action items.
+                     
+              {part}
+              ### Assistant:
+              """
+       output = model.generate(prompt)
+       final_summary.append(output)
+
+
+with open("sum.txt", "w") as sum:
+       sum.write(" ".join(final_summary))