prompts — PromptTemplate, ChatPromptTemplate, FewShot, example selectors

PromptTemplate, ChatPromptTemplate, FewShot, example selectors

Module langchain_classic/prompts/ — PromptTemplate, ChatPromptTemplate, FewShot, example selectors. Part of the Models I/O group.

🎯 Why This Module Exists

Templates plus example selectors. PromptTemplate handles f-string and Jinja; ChatPromptTemplate composes roles; FewShotPromptTemplate stitches examples; example selectors (length-based, semantic similarity) pick which examples to include given a budget.

Source files

Sub-directories

Models I/O

Architecture

flowchart LR
  subgraph Core["langchain_classic/prompts/"]
    BASE["Base abstraction"]
    IMPLS["Concrete implementations"]
    BASE --> IMPLS
  end
  subgraph Up["Upstream callers"]
    U1["chains/"]
    U2["agents/"]
  end
  subgraph Down["Downstream"]
    D1["langchain_core"]
    D2["External providers"]
  end
  Up --> Core
  Core --> Down

Data Flow

sequenceDiagram
  participant Caller as Caller
  participant Prompts as prompts
  participant Core as langchain_core
  participant Ext as External
  Caller->>Prompts: invoke(input)
  Note over Prompts: Validate & route
  Prompts->>Core: delegate primitive
  Core->>Ext: provider call
  Ext-->>Core: response
  Core-->>Prompts: typed output
  Prompts-->>Caller: result

Design Decisions

Decision	Choice Made	Alternatives	Why This Approach
Two formatters	f-string default; Jinja2 opt-in	Jinja2 only	f-string covers 95% of cases without a templating dependency
Chat vs string	ChatPromptTemplate is its own class	One class with mode flag	Different validation: chat enforces role types
Example selector ABC	Pluggable strategies (length, semantic, max marginal)	One built-in strategy	Long-tail of selection criteria
Partial variables	Template can carry default values	Always require all vars at format time	Layered chains often want to fix some vars upstream

Pairs with output_parsers/ via format_instructions: parsers contribute the parser-specific formatting hint to the template.

Step-by-Step Walkthrough

Follow a typical operation through the prompts/ module:

Caller invokes the public surface — usually .invoke(input) on a Runnable, or a legacy __call__(inputs_dict) on a Chain subclass.
Pydantic validation — every entry point is a BaseModel; constructor args, input dicts, and tool args_schema are validated before any expensive work runs. Fail-fast on type errors.
CallbackManager.configure — a fresh manager is built per call, fans on_*_start events to all subscribers (LangSmith tracer, stdout handler, custom logging), and stamps a UUID4 run_id for tree reconstruction.
prompts-specific logic — the module's core method runs: prompt rendering, retrieval, tool execution, memory load, document split, etc. See the deep-dive sections above.
Provider call — typically a single HTTP request to OpenAI/Anthropic/etc., or a local SDK call. Retries are handled by tenacity with exponential backoff and a configurable max-attempts knob.
Streaming fan-out — if the provider streams tokens, each chunk fires on_llm_new_token through the callback manager so downstream observers (UI, log, tracer) see partial output.
OutputParser pass — if a parser is attached, the raw provider output is parsed into a structured Python object; OutputParserException may trigger a retry chain (RetryWithErrorOutputParser).
Memory write-back — for chains/agents that have a BaseMemory attached, save_context(inputs, outputs) persists the turn before returning to the caller.
on_*_end fan-out — the callback manager closes the run span; tracers serialise the Run tree and ship it to LangSmith asynchronously.
Result returned — caller receives a typed object (AIMessage, dict, BaseModel, list[Document], ...) matching the module's declared output schema.

What Could Go Wrong

Failure Mode	Trigger	Detection	Recovery
Provider 5xx / rate-limit	OpenAI/Anthropic/etc. transient error	HTTP status from SDK	tenacity retries with exponential backoff up to `max_retries`; then surface to caller
Output parser failure	LLM returned malformed JSON / wrong schema	`OutputParserException` in parser	`RetryWithErrorOutputParser` re-prompts with the parser error included; or surface
Pydantic validation	Caller passes wrong-shaped dict	`ValidationError` at `__init__` / `invoke`	Surface immediately — no fallback is correct here
Callback handler exception	User-supplied tracer raises	Try/except around each fan-out	Logged and swallowed by default; `raise_error=True` to opt in to propagation
Provider auth missing	`OPENAI_API_KEY` unset	SDK `AuthenticationError`	Surface with a helpful message; no retry (would just fail again)

Performance Profile

Hot Paths

Provider HTTP round-trip dominates wall-clock time (100ms–30s depending on model and prompt length).
Pydantic validation is repeated on every invoke; cached schema parsing keeps it under 1ms for typical inputs.
Callback fan-out is synchronous by default — a slow handler will slow every call. Async tracers (LangSmith) push work to a background thread to avoid blocking.

Resource Usage

Memory: token-history buffers (in memory/) and document caches (in retrieval pipelines) are the largest steady-state allocations.
I/O: bounded by provider rate limits; vector store I/O for retrieval-flavored modules.
Concurrency: async support via a* methods; agents and parallel chains use asyncio.gather for concurrent tool calls.

Directory Map

Source tree for prompts

prompts/
├── __init__.py
├── base.py
├── chat.py
├── example_selector/
├── few_shot.py
├── few_shot_with_templates.py
├── loading.py
└── prompt.py