Added projects files directly to main repo

Projects/2. Large Language Models and LangChain/chat_models.py

@@ -0,0 +1,14 @@
+from langchain.chat_models import ChatOpenAI
+from langchain.schema import (
+  HumanMessage,
+  SystemMessage
+)
+
+chat = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0)
+
+messages = [
+	SystemMessage(content="You are a helpful assistant that translates English to French."),
+	HumanMessage(content="Translate the following sentence: I love programming.")
+]
+
+chat(messages)

Projects/2. Large Language Models and LangChain/few_short.py

@@ -0,0 +1,58 @@
+from langchain import PromptTemplate
+from langchain import FewShotPromptTemplate
+from langchain.chat_models import ChatOpenAI
+from langchain import LLMChain
+
+# create our examples dictionery
+examples = [
+    {
+        "query": "What's the weather like?",
+        "answer": "It's raining cats and dogs, better bring an umbrella!"
+    }, {
+        "query": "How old are you?",
+        "answer": "Age is just a number, but I'm timeless."
+    }
+]
+
+# create an example template
+example_template = """
+User: {query}
+AI: {answer}
+"""
+
+# create a prompt example from above template
+example_prompt = PromptTemplate(
+    input_variables=["query", "answer"],
+    template=example_template
+)
+
+# now break our previous prompt into a prefix and suffix
+# the prefix is our instructions
+prefix = """The following are excerpts from conversations with an AI
+assistant. The assistant is known for its humor and wit, providing
+entertaining and amusing responses to users' questions. Here are some
+examples:
+"""
+# and the suffix our user input and output indicator
+suffix = """
+User: {query}
+AI: """
+
+# now create the fe w-shot prompt template
+few_shot_prompt_template = FewShotPromptTemplate(
+    examples=examples,
+    example_prompt=example_prompt,
+    prefix=prefix,
+    suffix=suffix,
+    input_variables=["query"],
+    example_separator="\n\n"
+)
+
+# load the model
+chat = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0.9)
+
+chain = LLMChain(llm=chat, prompt=few_shot_prompt_template, verbose=True)
+
+ask_question = chain.run(input("Ask your question: "))
+
+print(ask_question)

Projects/2. Large Language Models and LangChain/gpt4all.py

@@ -0,0 +1,18 @@
+# Import modules
+from langchain.llms import GPT4All
+from langchain import PromptTemplate, LLMChain
+from langchain.callbacks.base import CallbackManager
+from langchain.callbacks.manager import CallbackManager
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+
+template = """Question: {question}
+
+Answer: Let's think step by step."""
+prompt = PromptTemplate(template=template, input_variables=["question"])
+
+callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
+llm = GPT4All(model="E:/Backup/Documents/Softwares/GPT4All/Models/ggml-wizardLM-7B.q4_2.bin", callback_manager=callback_manager, verbose=True)
+llm_chain = LLMChain(prompt=prompt, llm=llm)
+
+question = "What happens when it rains somewhere?"
+llm_chain.run(question)

Projects/2. Large Language Models and LangChain/question_answering.py

@@ -0,0 +1,31 @@
+from langchain import PromptTemplate
+from langchain import HuggingFaceHub, LLMChain
+from dotenv import load_dotenv 
+
+load_dotenv()
+
+template = """Question: {question}
+
+Answer: """
+prompt = PromptTemplate(
+        template=template,
+        input_variables=['question']
+        )   
+
+# user question
+question =input("")
+
+# initialize Hub LLM
+hub_llm = HuggingFaceHub(
+        repo_id='google/flan-t5-large',
+    model_kwargs={'temperature':0}
+)
+
+# create prompt template > LLM chain
+llm_chain = LLMChain(
+    prompt=prompt,
+    llm=hub_llm
+)
+
+# ask the user question about the capital of France
+print(llm_chain.run(question)) 

Projects/2. Large Language Models and LangChain/text_summarization.py

@@ -0,0 +1,14 @@
+from langchain.chat_models import ChatOpenAI
+from langchain.chains import LLMChain
+from langchain.prompts import PromptTemplate
+
+llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0)
+
+summarization_template = "Summarize the following text to one sentence: {text}"
+summarization_prompt = PromptTemplate(input_variables=["text"], template=summarization_template)
+summarization_chain = LLMChain(llm=llm, prompt=summarization_prompt, verbose=True)
+
+text = "LangChain provides many modules that can be used to build language model applications. Modules can be combined to create more complex applications, or be used individually for simple applications. The most basic building block of LangChain is calling an LLM on some input. Let’s walk through a simple example of how to do this. For this purpose, let’s pretend we are building a service that generates a company name based on what the company makes."
+summarized_text = summarization_chain.predict(text=text)
+
+print(summarized_text)

Projects/2. Large Language Models and LangChain/track_usage.py

@@ -0,0 +1,9 @@
+from langchain.llms import OpenAI
+from langchain.callbacks import get_openai_callback
+
+llm = OpenAI(model_name="text-davinci-003", n=2, best_of=2)
+
+with get_openai_callback() as cb:
+    result = llm("Tell me a joke")
+    cost = cb.total_cost
+    print("$",round(cost, 5)) 

Projects/3. Learning How to Prompt/chain_prompting.py

@@ -0,0 +1,40 @@
+from langchain import PromptTemplate, LLMChain
+from langchain.llms import OpenAI
+
+# Initialize LLM
+llm = OpenAI(model_name="text-davinci-003", temperature=0)
+
+# Prompt 1
+template_question = """What is the name of the famous scientist who developed the theory of general relativity?
+Answer: """
+prompt_question = PromptTemplate(
+    template=template_question, 
+    input_variables=[])
+
+# Prompt 2
+template_fact = """Provide a brief description of {scientist}'s theory of general relativity.
+Answer: """
+prompt_fact = PromptTemplate(
+    input_variables=["scientist"], 
+    template=template_fact)
+
+# Create the LLMChain for the first prompt
+chain_question = LLMChain(llm=llm, prompt=prompt_question)
+
+# Run the LLMChain for the first prompt with an empty dictionary
+response_question = chain_question.run({})
+
+# Extract the scientist's name from the response
+scientist = response_question.strip()
+
+# Create the LLMChain for the second prompt
+chain_fact = LLMChain(llm=llm, prompt=prompt_fact)
+
+# Input data for the second prompt
+input_data = {"scientist": scientist}
+
+# Run the LLMChain for the second prompt
+response_fact = chain_fact.run(input_data)
+
+print("Scientist:", scientist)
+print("Fact:", response_fact)

Projects/3. Learning How to Prompt/news_summarizer_ output_parsers.py

@@ -0,0 +1,58 @@
+from langchain.output_parsers import PydanticOutputParser
+from pydantic import validator
+from pydantic import BaseModel, Field
+from typing import List
+from langchain.prompts import PromptTemplate
+from langchain.llms import OpenAI
+
+
+
+# create output parser class
+class ArticleSummary(BaseModel):
+    title: str = Field(description="Title of the article")
+    summary: List[str] = Field(description="Bulleted list summary of the article")
+
+    # validating whether the generated summary has at least three lines
+    @validator('summary', allow_reuse=True)
+    def has_three_or_more_lines(cls, list_of_lines):
+        if len(list_of_lines) < 3:
+            raise ValueError("Generated summary has less than three bullet points!")
+        return list_of_lines
+
+# set up output parser
+parser = PydanticOutputParser(pydantic_object=ArticleSummary)
+
+# create prompt template
+# notice that we are specifying the "partial_variables" parameter
+template = """
+You are a very good assistant that summarizes online articles.
+
+Here's the article you want to summarize.
+
+==================
+Title: {article_title}
+
+{article_text}
+==================
+
+{format_instructions}
+"""
+
+prompt = PromptTemplate(
+    template=template,
+    input_variables=["article_title", "article_text"],
+    partial_variables={"format_instructions": parser.get_format_instructions()}
+)
+
+# Format the prompt using the article title and text obtained from scraping
+formatted_prompt = prompt.format_prompt(article_title=article_title, article_text=article_text)
+
+# instantiate model class
+model = OpenAI(model_name="text-davinci-003", temperature=0.0)
+
+# Use the model to generate a summary
+output = model(formatted_prompt.to_string())
+
+# Parse the output into the Pydantic model
+parsed_output = parser.parse(output)
+print(parsed_output)

Projects/3. Learning How to Prompt/news_summarizer_extended copy.py

@@ -0,0 +1,79 @@
+import os 
+import json 
+from dotenv import load_dotenv
+import requests
+from newspaper import Article
+from langchain.schema import (
+    HumanMessage
+)
+from langchain.chat_models import ChatOpenAI
+
+load_dotenv()
+
+headers = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36'
+}
+
+article_url = "https://www.artificialintelligence-news.com/2022/01/25/meta-claims-new-ai-supercomputer-will-set-records/"
+
+session = requests.Session()
+
+try:
+  response = session.get(article_url, headers=headers, timeout=10)
+
+  if response.status_code == 200:
+      article = Article(article_url)
+      article.download()
+      article.parse()
+
+    #   print(f"Title: {article.title}")
+    #   print(f"Text: {article.text}")
+  else:
+      print(f"Failed to fetch article at {article_url}")
+except Exception as e:
+    print(f"Error occurred while fetching article at {article_url}: {e}")
+
+# we get the article data from the scraping part
+article_title = article.title
+article_text = article.text
+
+# prepare template for prompt
+template = """
+As an advanced AI, you've been tasked to summarize online articles into bulleted points. Here are a few examples of how you've done this in the past:
+
+Example 1:
+Original Article: 'The Effects of Climate Change
+Summary:
+- Climate change is causing a rise in global temperatures.
+- This leads to melting ice caps and rising sea levels.
+- Resulting in more frequent and severe weather conditions.
+
+Example 2:
+Original Article: 'The Evolution of Artificial Intelligence
+Summary:
+- Artificial Intelligence (AI) has developed significantly over the past decade.
+- AI is now used in multiple fields such as healthcare, finance, and transportation.
+- The future of AI is promising but requires careful regulation.
+
+Now, here's the article you need to summarize:
+
+==================
+Title: {article_title}
+
+{article_text}
+==================
+
+Please provide a summarized version of the article in a bulleted list format.
+"""
+
+# Format the Prompt
+prompt = template.format(article_title=article.title, article_text=article.text)
+
+messages = [HumanMessage(content=prompt)]    
+
+# load the model
+chat = ChatOpenAI(model_name="gpt-3.5-turbo-16k", temperature=0.0)
+
+# generate summary
+summary = chat(messages)
+print(summary.content)

Projects/4. Keeping Knowledge Organized with Indexes/Character_Text_Splitter.py

@@ -0,0 +1,14 @@
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import CharacterTextSplitter
+
+loader = PyPDFLoader("The One Page Linux Manual.pdf")
+pages = loader.load_and_split()
+
+text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=20)
+texts = text_splitter.split_documents(pages)
+
+print(texts[0])
+
+print (f"You have {len(texts)} documents")
+print ("Preview:")
+print (texts[0].page_content)

Projects/4. Keeping Knowledge Organized with Indexes/Cohere_embeddings.py

@@ -0,0 +1,29 @@
+import cohere
+from langchain.embeddings import CohereEmbeddings
+
+# Initialize the CohereEmbeddings object
+cohere = CohereEmbeddings(
+	model="embed-multilingual-v2.0",
+	cohere_api_key="95itqFSDUc4PMznsGaIqDUaGBRhwWG6sLE4XBnTD"
+)
+
+# Define a list of texts
+texts = [
+    "Hello from Cohere!", 
+    "مرحبًا من كوهير!", 
+    "Hallo von Cohere!",  
+    "Bonjour de Cohere!", 
+    "¡Hola desde Cohere!", 
+    "Olá do Cohere!",  
+    "Ciao da Cohere!", 
+    "您好，来自 Cohere！", 
+    "कोहेरे से नमस्ते!"
+]
+
+# Generate embeddings for the texts
+document_embeddings = cohere.embed_documents(texts)
+
+# Print the embeddings
+for text, embedding in zip(texts, document_embeddings):
+    print(f"Text: {text}")
+    print(f"Embedding: {embedding[:5]}")  # print first 5 dimensions of each embedding

Projects/4. Keeping Knowledge Organized with Indexes/DataChad/.streamlit/secrets.toml

@@ -0,0 +1,3 @@
+OPENAI_API_KEY=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
+ACTIVELOOP_TOKEN=eyJhbGciOiJIUzUxMiIsImlhdCI6MTY4NzM1NDkyMSwiZXhwIjoxNzE4OTc3MjYwfQ.eyJpZCI6ImRqcGFwemluIn0.ezQ-ChtNr76KXlEr_lSJuxsa9im6I2X9BeDpGzMWzdz2kkC7OI9zAD2iQ8LO98gdKC0gYRcE3FAAX0FnYgXeTg
+ACTIVELOOP_ID=djpapzin