Find answers from the community

Updated 2 months ago

I have a two examples of chabot

I have a two examples of chabot implementation where in first one i use GPT-3-turbo and in the second GPT-4-turbo. I am getting better results from GPT-3-turbo than from GPT-4-turbo. Context: I use Pinecone VectorDB storage and query the data using query engine. I did switch to a new embedding model like so :

Plain Text
"llm = OpenAI(model="gpt-4-turbo", temperature=0)
Settings.llm = llm

embed_model = OpenAIEmbedding(model="text-embedding-3-small")
Settings.embed_model = embed_model
#logging.info(" LLM MODEL OPENAI" + llm.model)
logging.info("Initialized OpenAI")
query_engine = loaded_index.as_query_engine(streaming=False) #, text_qa_template=text_qa_template, llm=llm)
logging.info("Initialized QueryEngine")"

The second more simpler implementation of my bot : 
# Initialize your index
pinecone_index = pc.Index(index_name)

vector_store = PineconeVectorStore(pinecone_index=pinecone_index)
loaded_index = VectorStoreIndex.from_vector_store(vector_store=vector_store)
logging.info("Index loaded from Pinecone")

query_engine = loaded_index.as_query_engine()


Is the embedding model problematic ? I used llamacloud parse and then indexed the data... I am using the newer embeding model "text-embedding-3-small" in the GPT-4-turbo version. Could this be making my GPT-4-turbo results worse ? I do have langfuse connected to better analyze the retrieve process.
W
1 comment
Can you analyse the nodes returned in both the cases.
That will help you to get an idea about the problem, Whether it is the embeding model prob or LLM prob
Add a reply
Sign up and join the conversation on Discord