datawhalechina/prompt-engineering-for-developers

Features

• Prompt Engineering - Serves as a technical curriculum for mastering the design and refinement of prompts to optimize LLM performance.
• Prompt Engineering Guides - Offers comprehensive resources for mastering the design and optimization of prompts to improve language model output quality.
• Knowledge Base Retrieval - Implements systems that retrieve enterprise knowledge from vector databases to provide context for AI responses.
• LLM Application Orchestration - Provides a comprehensive guide to chaining model calls and managing complex agentic workflows for AI applications.
• Retrieval-Augmented Generation - Implements the retrieval-to-generation pipeline to ground model responses in factual external context.
• Instructional Prompting - Provides techniques for using direct commands and constraints to guide model behavior.
• Language Model Fine-Tuning - Details the use of memory-efficient training methods to adjust pre-trained language models for specific tasks.
• Large Language Model Fine-Tuning Frameworks - Provides a comprehensive guide to adapting pre-trained large language models to specific domain tasks.
• Language Model Fine-Tuning - Covers specialized workflows for adapting pre-trained language models to specific tasks or datasets.
• Model Fine-Tuning - Details procedures for adapting pre-trained open source models using domain-specific datasets to improve specialized task performance.
• Parameter Adaptation Techniques - Details the process of updating model weights using domain-specific examples for specialized task improvement.
• Prompt Engineering Workflows - Implements methodologies for developing and testing prompt-based instructions for summarization, inference, and data transformation.
• RAG Frameworks - Provides a development environment for building applications that integrate LLMs with private data.
• Semantic Search - Integrates search functionality that understands intent and context via numerical embeddings.
• Example-Based Prompting - Teaches how to structure textual patterns and example pairs to achieve predictable model results.
• Semantic Search Engines - Implements vector embeddings to retrieve information based on conceptual meaning within private data stores.
• AI Application Frameworks - Guides the creation of AI-native applications by combining orchestration frameworks and user interfaces.
• AI Workflow Orchestrators - Provides frameworks for managing and automating multi-step reasoning chains in language model applications.
• Automated Output Evaluation - Provides systematic methods for judging and validating the accuracy and reliability of AI outputs.
• Fine-Tuning Tutorials - Offers detailed tutorials and code examples for adapting pre-trained models to specific datasets.
• AI Evaluation Frameworks - Ships a systematic approach for assessing generative AI outputs and reasoning quality through comparative analysis.
• AI Observability and Evaluation - Offers tools and methods for tracing, benchmarking, and monitoring the output quality of LLM applications.
• Educational Courses - Provides a technical curriculum for developers to master the discipline of prompt engineering.
• RAG Tutorials - Includes instructional guides for implementing retrieval-augmented generation to ground model responses in private information.
• Workflow Orchestration - Uses specialized frameworks to define and execute complex data flows and conditional logic in AI pipelines.
• Workflow Orchestrators - Provides techniques for managing multi-step reasoning and data processing pipelines.
• Evaluation Benchmarks - Implements systematic methods for measuring model performance and reasoning capabilities using benchmark datasets.
• Model Evaluation and Benchmarking - Implements frameworks and suites for validating and comparing the performance of language models.
• AI Development Guides - Provides a technical walkthrough and best practices for building full-scale AI workflows and agentic capabilities.
• Model Fine-Tuning Guides - Provides educational guides on the implementation techniques for fine-tuning machine learning models on custom domain tasks.
• Educational Resources - Chinese-language courses covering prompt engineering and application development.
• Prompt Engineering - Chinese translation of professional courses on prompt engineering techniques.

Star history