smith — LangSmith dataset evaluation runner (legacy)

LangSmith dataset evaluation runner (legacy)

Module langchain_classic/smith/ — LangSmith dataset evaluation runner (legacy). Part of the Cross-cutting group.

🎯 Why This Module Exists

Legacy harness for running an LLM/agent against a LangSmith dataset, scoring results with evaluators, and pushing the run back to LangSmith. Most of this is now superseded by the langsmith SDK's own evaluate() function; smith/ stays for users still on the run_on_dataset API.

Source files

Sub-directories

Cross-cutting

Architecture

flowchart LR
  subgraph Core["langchain_classic/smith/"]
    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 Smith as smith
  participant Core as langchain_core
  participant Ext as External
  Caller->>Smith: invoke(input)
  Note over Smith: Validate & route
  Smith->>Core: delegate primitive
  Core->>Ext: provider call
  Ext-->>Core: response
  Core-->>Smith: typed output
  Smith-->>Caller: result

Design Decisions

Decision	Choice Made	Alternatives	Why This Approach
Pluggable evaluator factory	Build evaluators from string keys or callables	One built-in evaluator	Same dataset usually gets multiple metrics
Concurrency model	ThreadPoolExecutor with progress callback	Sync only	Datasets routinely have hundreds of examples
Run linking	Each example gets its own run_id; results are pushed back to LangSmith	Local-only	LangSmith UI is the consumption surface

Mostly thin glue between evaluation/ evaluators and the langsmith SDK.

Step-by-Step Walkthrough

Follow a typical operation through the smith/ 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.
smith-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 smith

smith/
├── __init__.py
└── evaluation/