Emmanuel Irog-irog

Hey guys maybe this could give us a clue. In flowiseai you can add a System prompt and other things to a ConversationalQA Chain 

Hey I've hadn't face this issue yet haha but my goal was to reduce the amount of documents retrieved by using compressions tried one of the first examples which used...

Tried using the embeddings_filter ``` embeddings_filter_1 = EmbeddingsFilter(embeddings=embeddings, similarity_threshold=0.76) compression_retriever_1 = ContextualCompressionRetriever(base_compressor=embeddings_filter_1, base_retriever=retriever_1) ``` It gave me an error of InvalidRequestError: This model's maximum context length is 16385 tokens. However,...

encountered this error when upgrading from v229 to v235 It works fine at v229 `chain = create_structured_output_chain(OrderID, llm=ChatOpenAI(temperature=0, model="gpt-3.5-turbo-16k"), prompt=prompt)` OUTPUT `{'order_id': 123456789}` when I run this it outputs a...

Its asking me for a app logo, a cateogry and privacy policy as well to make it live

> this env settings works for me I tried this and my experience got better but after a while (probably 20mins of use - just hitting yes on every change...

me too only Claude 3.5 is working and if I view Claude 4 in the Service qoutas its this: