Membangun templat prompt retrieval

Sekarang dokumen Anda telah dimasukkan ke dalam basis data vektor dan siap diambil kembali, Anda perlu merancang templat prompt percakapan untuk menggabungkan potongan dokumen yang diambil dengan pertanyaan masukan pengguna.

Struktur umum prompt sudah disediakan; tujuan Anda adalah menyisipkan placeholder variabel masukan yang benar ke dalam string message dan mengonversi string tersebut menjadi templat prompt percakapan.

Latihan ini adalah bagian dari kursus

Mengembangkan Aplikasi LLM dengan LangChain

Petunjuk latihan

Lengkapi string message untuk menambahkan placeholder bagi penyisipan dinamis dokumen yang diambil bernama context dan pertanyaan masukan pengguna question.
Buat templat prompt percakapan dari message menggunakan metode .from_messages() dengan peran "human".

Latihan interaktif praktis

Cobalah latihan ini dengan menyelesaikan kode contoh berikut.

# Add placeholders to the message string
message = """
Answer the following question using the context provided:

Context:
____

Question:
____

Answer:
"""

# Create a chat prompt template from the message string
prompt_template = ChatPromptTemplate.from_messages([("____", ____)])

Edit dan Jalankan Kode

Latihan ini adalah bagian dari kursus

Mengembangkan Aplikasi LLM dengan LangChain

SkillTag.level.intermediateSkillTag.label

4.8+

Mulai Kursus Gratis

Welcome to the LangChain framework for building applications on LLMs! You'll learn about the main components of LangChain, including models, chains, agents, prompts, and parsers. You'll create chatbots using both open-source models from Hugging Face and proprietary models from OpenAI, create prompt templates, and integrate different chatbot memory strategies to manage context and resources during conversations.

Exercise 1: The LangChain ecosystem Exercise 2: OpenAI models in LangChain!Exercise 3: Hugging Face models in LangChain!Exercise 4: Prompt templates Exercise 5: Prompt templates and chaining Exercise 6: Chat prompt templates Exercise 7: Few-shot prompting Exercise 8: Creating the few-shot example set Exercise 9: Building the few-shot prompt template Exercise 10: Implementing few-shot prompting

Time to level up your LangChain chains! You'll learn to use the LangChain Expression Language (LCEL) for defining chains with greater flexibility. You'll create sequential chains, where inputs are passed between components to create more advanced applications. You'll also begin to integrate agents, which use LLMs for decision-making.

Exercise 1: Sequential chains Exercise 2: Building prompts for sequential chains Exercise 3: Sequential chains with LCEL Exercise 4: Introduction to LangChain agents Exercise 5: What's an agent?Exercise 6: ReAct agents Exercise 7: Custom tools for agents Exercise 8: Defining a function for tool use Exercise 9: Creating custom tools Exercise 10: Integrating custom tools with agents

One limitation of LLMs is that they have a knowledge cut-off due to being trained on data up to a certain point. In this chapter, you'll learn to create applications that use Retrieval Augmented Generation (RAG) to integrate external data with LLMs. The RAG workflow contains a few different processes, including splitting data, creating and storing the embeddings using a vector database, and retrieving the most relevant information for use in the application. You'll learn to master the entire workflow!

Exercise 1: Mengintegrasikan pemuat dokumen Exercise 2: Pemuatan dokumen PDF Exercise 3: Pemuat dokumen CSV Exercise 4: Pemuat dokumen HTML Exercise 5: Memecah data eksternal untuk pengambilan kembali Exercise 6: Memisah berdasarkan karakter Exercise 7: Memecah secara rekursif berdasarkan karakter Exercise 8: Membagi HTML Exercise 9: Penyimpanan dan pengambilan RAG menggunakan basis data vektor Exercise 10: Menyiapkan dokumen dan basis data vektor Exercise 11: Membangun templat prompt retrieval

Latihan Saat Ini

Exercise 12: Membuat rantai RAG Exercise 13: Penutup!