Trying to make LLMs less stubborn in RAG (DSPy optimizer tested with knowledge graphs)

Рет қаралды 2,737

Күн бұрын

Пікірлер: 10

@wadejohnson4542 8 ай бұрын

Until I saw this, I was starting to think that there was something wrong with me not being able to achieve magical improvements in results by using DSPy over meticulously hand-crafted prompts targeted at the observed quirkiness of specific LLMs. Thank you for restoring my self confidence. And now I'm also going to incorporate graph databases into my RAG pipelines after watching a couple of your videos.

@rahulvb5044 8 ай бұрын

one basic doubt. def forward(self, question): # Step 1: Retrieve context based on the question context = self.retrieve(question).passages # Step 2: Generate an answer based on the context and question prediction = self.generate_answer(context=context, question=question) answer = prediction.answer # Step 3: Validate the answer type using the entity_linker function correct_question_type, original_answer_type, type_status = entity_linker(answer, question) # Optional: You can use the AnswerTypeValidityCheck signature for validation if needed validation = self.check_answer_type(entity_type=correct_question_type, question=question, answer=answer).type_status return dspy.Prediction(context=context, answer=answer, type_status=type_status) in this method, the answer returned is the one you got from self.generate_answer. That method doesnt use any entitylinker . so how is entitylinker influencing the answer ?

@pedromoya9127 8 ай бұрын

thanks great video!

@somjrgebn 8 ай бұрын

Do you know of any efforts on converting these entities and relationships further into formal logic representations? Being able to pair these graph databases with formal logic representations would definitely help improve the quality of written text, organic exploration/discovery, and understanding over time.