Constructing a RAG chain utilizing LangChain Expression Language (LCEL) | by Roshan Santhosh | Apr, 2024


QA RAG with Self Analysis II

For this variation, we make a change to the analysis process. Along with the question-answer pair, we additionally go the retrieved context to the evaluator LLM.

To perform this, we add a further itemgetter operate within the second RunnableParallel to gather the context string and go it to the brand new qa_eval_prompt_with_context immediate template.

rag_chain = ( 
RunnableParallel(context = retriever | format_docs, query = RunnablePassthrough() ) |
RunnableParallel(reply= qa_prompt | llm | retrieve_answer, query = itemgetter("query"), context = itemgetter("context") ) |
qa_eval_prompt_with_context |
llm_selfeval |
json_parser
)

Implementation Flowchart :

One of many frequent ache factors with utilizing a series implementation like LCEL is the problem in accessing the intermediate variables, which is vital for debugging pipelines. We take a look at few choices the place we will nonetheless entry any intermediate variables we have an interest utilizing manipulations of the LCEL

Utilizing RunnableParallel to hold ahead intermediate outputs

As we noticed earlier, RunnableParallel permits us to hold a number of arguments ahead to the subsequent step within the chain. So we use this skill of RunnableParallel to hold ahead the required intermediate values all the best way until the tip.

Within the beneath instance, we modify the unique self eval RAG chain to output the retrieved context textual content together with the ultimate self analysis output. The first change is that we add a RunnableParallel object to each step of the method to hold ahead the context variable.

Moreover, we additionally use the itemgetter operate to obviously specify the inputs for the next steps. For instance, for the final two RunnableParallel objects, we use itemgetter(‘enter’) to make sure that solely the enter argument from the earlier step is handed on to the LLM/ Json parser objects.

rag_chain = ( 
RunnableParallel(context = retriever | format_docs, query = RunnablePassthrough() ) |
RunnableParallel(reply= qa_prompt | llm | retrieve_answer, query = itemgetter("query"), context = itemgetter("context") ) |
RunnableParallel(enter = qa_eval_prompt, context = itemgetter("context")) |
RunnableParallel(enter = itemgetter("enter") | llm_selfeval , context = itemgetter("context") ) |
RunnableParallel(enter = itemgetter("enter") | json_parser, context = itemgetter("context") )
)

The output from this chain appears to be like like the next :

A extra concise variation:

rag_chain = ( 
RunnableParallel(context = retriever | format_docs, query = RunnablePassthrough() ) |
RunnableParallel(reply= qa_prompt | llm | retrieve_answer, query = itemgetter("query"), context = itemgetter("context") ) |
RunnableParallel(enter = qa_eval_prompt | llm_selfeval | json_parser, context = itemgetter("context"))
)

Utilizing International variables to save lots of intermediate steps

This technique primarily makes use of the precept of a logger. We introduce a brand new operate that saves its enter to a worldwide variable, thus permitting us entry to the intermediate variable via the worldwide variable

world context

def save_context(x):
world context
context = x
return x

rag_chain = (
RunnableParallel(context = retriever | format_docs | save_context, query = RunnablePassthrough() ) |
RunnableParallel(reply= qa_prompt | llm | retrieve_answer, query = itemgetter("query") ) |
qa_eval_prompt |
llm_selfeval |
json_parser
)

Right here we outline a worldwide variable known as context and a operate known as save_context that saves its enter worth to the worldwide context variable earlier than returning the identical enter. Within the chain, we add the save_context operate because the final step of the context retrieval step.

This feature permits you to entry any intermediate steps with out making main modifications to the chain.

Accessing intermediate variables utilizing world variables

Utilizing callbacks

Attaching callbacks to your chain is one other frequent technique used for logging intermediate variable values. Theres lots to cowl on the subject of callbacks in LangChain, so I might be protecting this intimately in a distinct put up.

Leave a Reply

Your email address will not be published. Required fields are marked *