Providing few-shot examples

While structured outputs describe how you would like the data to be returned, it still leaves a lot open to interpretation when it comes to what should be returned.

The Field class allows you to provide example values that give the LLM information on what a good extraction looks like. This is an example of few-shot prompting for structured outputs.

You'll extend the Character class to contain an id field for uniquely identifying characters. You want to provide the model with two examples for it to draw from: "romeo-montague" and "lady-capulet".

Diese Übung ist Teil des Kurses

Graph RAG with LangChain and Neo4j

Anleitung zur Übung

Specify the keyword to provide example values for the id property.

Interaktive Übung

Vervollständige den Beispielcode, um diese Übung erfolgreich abzuschließen.

class Character(BaseModel):
	id: str = Field(
		"A unique identifer consisting of the Character's given name and their family name in slug case.", 
		# Provide example values of an ID
		____=["romeo-montague", "lady-capulet"]
	)
	name: str = Field("The name of the character")

chain = prompt | llm.with_structured_output(Character)

chain.invoke({"text": """JULIET.
O Romeo, Romeo, wherefore art thou Romeo? Deny thy father and refuse thy name. Or if thou wilt not, be but sworn my love, And I’ll no longer be a Capulet."""})

Code bearbeiten und ausführen

Diese Übung ist Teil des Kurses

Graph RAG with LangChain and Neo4j

Hohe SchwierigkeitSchwierigkeitsgrad

4.8+

Kurs kostenlos starten

Learn how Graph RAG can improve the accuracy and reliability of RAG applications! Store information as nodes and edges in a Neo4j database, and give your LLM the ability to query it so it can retrieve entity and relational information to provide informed answers.

Exercise 1: Graphs and RAG Exercise 2: Creating nodes Exercise 3: Creating relationships Exercise 4: Saving graph documents Exercise 5: Querying a knowledge graph Exercise 6: Writing Cypher statements Exercise 7: Running Cypher statements Exercise 8: The MERGE clause Exercise 9: Text-to-Cypher Graph RAG with Neo4j Exercise 10: Building a text-to-Cypher chain Exercise 11: Text-to-Cypher retrieval chain

Text-to-Cypher applications work well in many circumstances, but we can do better than that! Discover how to construct graph databases using different graph models including lexical and domain graphs. Create Neo4j vector indexes so that you can have the best of both worlds and run graph and vector retrieval simultaneously!

Exercise 1: Lexical graphs Exercise 2: Elements of a lexical graph Exercise 3: Splitting the play into Acts Exercise 4: Creating a hierarchical lexical graph Exercise 5: Combining lexical graphs with vector search Exercise 6: Creating text chunks Exercise 7: Creating a vector index Exercise 8: Domain graphs Exercise 9: Creating a structured output Exercise 10: Requesting a structured output Exercise 11: Providing few-shot examples

Aktuelle Übung

Exercise 12: Building a hybrid retrieval chain Exercise 13: Runnable lambdas Exercise 14: Assigning additional values to an input Exercise 15: The final link in the chain

Although Graph RAG applications are generally more reliable than vector RAG, they aren't totally infallible. In this chapter, you'll learn to evaluate your Graph RAG applications, spot incorrect or duplicate graph nodes, and integrate long-term memory so user preferences can be learned over time.

Exercise 1: Entity resolution Exercise 2: Using extracted entities Exercise 3: Graph-based entity resolution Exercise 4: Evaluating Graph RAG with RAGAS Exercise 5: Creating a Ragas evaluation Exercise 6: Evaluating context retrieval with Ragas Exercise 7: Memory graphs Exercise 8: Saving conversation memory in the graph Exercise 9: Extracting facts from conversation histories Exercise 10: Using extracted conversation facts Exercise 11: Congratulations!