trulens.apps.langchain.guardrails¶

trulens.apps.langchain.guardrails ¶

Classes¶

WithFeedbackFilterDocuments ¶

Bases: VectorStoreRetriever

Attributes¶

threshold `instance-attribute` ¶

threshold: float

A VectorStoreRetriever that filters documents using a minimum threshold on a feedback function before returning them.

PARAMETER	DESCRIPTION
`feedback`	use this feedback function to score each document.
`threshold`	and keep documents only if their feedback value is at least this threshold.

Example: "Using TruLens guardrail context filters with Langchain"

```python
from trulens.apps.langchain import WithFeedbackFilterDocuments

# note: feedback function used for guardrail must only return a score, not also reasons
feedback = Feedback(provider.context_relevance).on_input().on(context)

filtered_retriever = WithFeedbackFilterDocuments.of_retriever(
    retriever=retriever,
    feedback=feedback,
    threshold=0.5
)

rag_chain = {"context": filtered_retriever | format_docs, "question": RunnablePassthrough()} | prompt | llm | StrOutputParser()

tru_recorder = TruChain(rag_chain,
    app_name='ChatApplication',
    app_version='filtered_retriever',
)

with tru_recorder as recording:
    llm_response = rag_chain.invoke("What is Task Decomposition?")
```

Functions¶

of_retriever `staticmethod` ¶

of_retriever(
    retriever: VectorStoreRetriever, **kwargs: Any
)

Create a new instance of WithFeedbackFilterDocuments based on an existing retriever.

The new instance will:

Get relevant documents (like the existing retriever its based on).
Evaluate documents with a specified feedback function.
Filter out documents that do not meet the minimum threshold.

PARAMETER	DESCRIPTION
`retriever`	VectorStoreRetriever - the base retriever to use. TYPE: `VectorStoreRetriever`
`**kwargs`	additional keyword arguments. TYPE: `Any` DEFAULT: `{}`

Returns: - WithFeedbackFilterDocuments: a new instance of WithFeedbackFilterDocuments.