Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

chore: Update Anthropic example, use ChatPromptBuilder properly #978

Merged
merged 1 commit into from
Aug 14, 2024
+10 −4
Merged

chore: Update Anthropic example, use ChatPromptBuilder properly #978

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 10 additions & 4 deletions integrations/anthropic/example/documentation_rag_with_claude.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,13 +12,19 @@

messages = [
ChatMessage.from_system("You are a prompt expert who answers questions based on the given documents."),
ChatMessage.from_user("Here are the documents: {{documents}} \\n Answer: {{query}}"),
ChatMessage.from_user(
"Here are the documents:\n"
"{% for d in documents %} \n"
" {{d.content}} \n"
"{% endfor %}"
"\nAnswer: {{query}}"
),
]

rag_pipeline = Pipeline()
rag_pipeline.add_component("fetcher", LinkContentFetcher())
rag_pipeline.add_component("converter", HTMLToDocument())
rag_pipeline.add_component("prompt_builder", ChatPromptBuilder())
rag_pipeline.add_component("prompt_builder", ChatPromptBuilder(variables=["documents"]))
rag_pipeline.add_component(
"llm",
AnthropicChatGenerator(
Expand All @@ -32,10 +38,10 @@
rag_pipeline.connect("converter", "prompt_builder")
rag_pipeline.connect("prompt_builder.prompt", "llm.messages")

question = "What are the best practices in prompt engineering?"
question = "When should we use prompt engineering and when should we fine-tune?"
rag_pipeline.run(
data={
"fetcher": {"urls": ["https://docs.anthropic.com/claude/docs/prompt-engineering"]},
"fetcher": {"urls": ["https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/overview"]},
"prompt_builder": {"template_variables": {"query": question}, "template": messages},
}
)