This repository contains HTML versions of various Jupyter notebooks. These files are accessible directly in a web browser, allowing for easy viewing and sharing of notebook content without requiring a Jupyter Notebook environment.
The notebooks in this repository cover a range of topics, including interactions with different language model APIs (e.g., OpenAI, Anthropic, Mistral), text generation, retrieval-augmented generation (RAG), summarization, translation, and multi-step prompt workflows. This repository serves as a reference for various NLP tasks and language model functionalities.
Below is a list of each notebook with a brief description of its content. Click the links to view each notebook.
- ANTHROPIC-CHATBOT: Demonstrates how to use the Anthropic API for chatbot interactions.
- ANTHROPIC-RAG: Shows Retrieval-Augmented Generation with Anthropic models.
- ANTHROPIC-TEXTGEN: Explores text generation capabilities with Anthropic models.
- COHERE-CHATBOT: Implements a chatbot using the Cohere API.
- COHERE-RAG: Demonstrates Retrieval-Augmented Generation with Cohere models.
- JULIA_ANTHROPIC_API: Interacts with the Anthropic API using Julia.
- JULIA_COHERE_API: Shows Cohere API usage in Julia.
- JULIA_MISTRAL_API: Demonstrates Mistral API interaction in Julia.
- JULIA_OPENAI_API: Provides OpenAI API interaction examples in Julia.
- LLM_FLOW_1: Introduces a modular framework for interacting with various LLM APIs, covering text generation and embedding retrieval.
- LLM_FLOW_2: Expands on the multi-step framework, demonstrating semantic search and advanced workflows.
- MISTRAL-CHATBOT: Builds a chatbot using the Mistral API.
- MISTRAL-RAG: Implements Retrieval-Augmented Generation with Mistral models.
- MISTRAL-TEXTGEN: Explores text generation capabilities with Mistral models.
- OPENAI-CHAT: Creates a chatbot using the OpenAI API.
- OPENAI-RAG: Demonstrates Retrieval-Augmented Generation with OpenAI models.
- OPENAI-TEXTGEN: Showcases text generation with OpenAI models.
- OPENAI_PROMPTING: Covers techniques for effective prompt engineering with OpenAI models.
- OPENAI_REFERENCE_RAG: Uses reference materials for enhanced Retrieval-Augmented Generation.
- OPENAI_VECTOR_EMB: Explores vector embedding retrieval and similarity search with OpenAI models.
- PDF_CHUNK_SUMMARIZATION: Summarizes PDF content by chunking and analyzing text segments.
- PYTHON_ANTHROPIC_API: Interacts with the Anthropic API in Python.
- PYTHON_COHERE_API: Shows usage of the Cohere API in Python.
- PYTHON_MISTRAL_API: Demonstrates Mistral API interaction in Python.
- PYTHON_OPENAI_API: Covers OpenAI API calls and parameters in Python.
- QA_llm_function: Demonstrates question-answering using language models, providing answers based on context or a document.
- R_ANTHROPIC_API: Uses the Anthropic API in R.
- R_COHERE_API: Interacts with the Cohere API in R.
- R_MISTRAL_API: Demonstrates Mistral API interaction in R.
- R_OPENAI_API: Uses the OpenAI API in R.
- fewshot_llm_function: Demonstrates few-shot learning with LLMs, providing a limited number of examples to guide model responses.
- generate_llm_function: Explores text generation tasks using various LLMs.
- summarize_llm_function: Implements summarization of text input.
- translate_llm_function: Provides language translation capabilities using LLMs.
This repository is licensed under the MIT License.