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

_get_relevant_documents

_get_relevant_documents(
    query: str, *, run_manager
) -> List[Document]

An internal method to accomplish three tasks:

1. Get relevant documents.
2. Evaluate documents with a specified feedback function.
3. Filter out documents that do not meet the minimum threshold.

PARAMETER	DESCRIPTION
query	str - the query string to search for relevant documents. TYPE: str
run_manager	RunManager - the run manager to handle document retrieval.

Returns: - List[Document]: a list of filtered, relevant documents.

of_retriever staticmethod

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

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

The new instance will:

1. Get relevant documents (like the existing retriever its based on).
2. Evaluate documents with a specified feedback function.
3. 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.