Custom GPTs refuses web browsing

Starting from yesterday, I received several refusals from my own Custom Chat GPT to perform web browsing. Today, when I used the Custom GPT developed by OpenAI named ‘Text Extractor’, it refused twice. Both of them - my GPT and ‘Text Extractor’ - stated that:
'As of my last update in April 2023, customizing a GPT model like ChatGPT directly with external data,’
‘I don’t have the capability to browse the internet or access external databases, including the OpenAI documentation, in real-time. My responses are based on the knowledge I was trained on, which includes information available up until April 2023.’
Has anyone else experienced the same issues recently?
What might be the reason for the refusals of web browsing?
Before that, when I asked Chat GPT or Custom GPTs to check the web, they did not refuse.

зображення

Here also the link to the chat were it refuses web browsing:

Welcome to the developer forums @gardetsky

The issue with OAI’s Text Extractor refusing web browsing is that they likely have it disabled in the GPT’s capabilities because web browsing is not required to perform the extraction. For your own GPT, ensure it is toggled on in the configure pane.

Here are chat examples of both the base ChatGPT model and a custom GPT performing the same query:

1 Like

Thank you. It is clear with Extractor now. Yesterday my Custom GPT sharply and suddenly changed behavior and stared to work like it’s very broken. So maybe it’s the reason why it refused web browsing. I have all three boxes checked so my issue definitely had different reasons.

1 Like

In that case, I would just be patient. Since the launch of the GPT store, there have been a lot of bugs getting worked out and changes happening each day. I have had random issues with GPTs since the store launched and some resolve themselves in minutes and others hours/days.

1 Like

I’ve been getting similar “refusals”. I uploaded an Excel sheet and it was able to extract information from it. But then in a second attempt, it told me it couldn’t access the file . I replied, “YES, YOU CAN!” and then it did! LOL Uhhh…ok?

3 Likes

Bhaskara Reddy S

Failure Points In RAG Systems

Anyone who has tried to deploy an RAG system knows that there are several failure modes to watch out for

While RAG helps you reduce hallucinations and create custom ChatLLM, there can be several failure points, given the complexity of the system.

The paper “Seven Failure Points When Engineering a Retrieval Augmented Generation System” (link in alt) makes a comprehensive list of places where failure can occur.

Here is the list of failure points they present and note on each point based on real-world use cases.

Missing Content - This is one of the biggest issues in real-world production cases. A user assumes that the answer to a particular question exists in the knowledge base. It doesn’t, and the system doesn’t respond with “I don’t know.”. Instead, it presents a plausible wrong answer, which can be extremely frustrating.

Missed the Top Ranked Documents - Retrievers are mini-search systems and non-trivial to get right. A simple embedding look-up rarely does the trick. Sometimes, the right answer is not present in the top K documents returned by the retriever, causing failure.

Not in Context - Sometimes, you may get too many documents back, and you have to trim the documents you send in context. This means the response to the question is not in the context. Sometimes, this causes the model to hallucinate unless the system prompt explicitly instructs the model not to return results that are not in context.

Not Extracted - When the LLM fails to extract the answer from the context. This tends to be an issue when you stuff the context and the LLM gets confused. Different LLMs have different levels of context understanding as well.

Wrong Format - While the paper lists this as a failure mode, this type of functionality doesn’t really come out of the box with LLMs. You have to do a lot of system prompting and write code in order to generate the information in a certain format. If this is an important feature, it will require software development and testing. For example, using Abacus AI, you can create an agent to output code in a certain format and generate Word docs with tables, paragraphs, bold text, etc.

Incorrect Specificity - This happens when the response is not at the right level of specificity, and the answer can be very vague or high level. Typically, a follow-up question solves this problem. The other reason this failure can happen is if the answer is in a different

Overall, this means that RAG systems must be tested thoroughly for robustness before putting them into production, and you can easily shoot yourself in the foot by releasing an agent or a chatbot that hasn’t gone through beta testing.

Read paper : https://arxiv.org/abs/2401.05856

In prompt engineering, seeing what works, and adjusting to make the model and conducive to the query and honestly easier for it to find the right answer.

I don’t think I can bear this anymore. Over the past month or so, GPT has been driven crazy by the knowledge they have been trying to force GPT to use, which has ruined the art of using knowledge from being able to be used as a whole process. Determining priority from storage status There are also problems with enforcing knowledge. In the end, I recently had an email conversation with the team and talked about the problem that they were too clingy. until creating usage problems I chose to find a solution. I removed knowkedge and put the text on the web page, adding links to it as knowledge. Many of the problems disappeared. In addition to the problem of knowledge, finally someone will do some research so we can stop being crazy.

But in the end, OpenAI came to block the use of links… What’s infuriating is that he knows the problem. He knows I have a solution. But he turned it off. How infuriating.





2 Likes


@JayKeelz This was the most important part of that image, ChatGPT has no way of knowing current situations or updates to itself.

In your screenshot it has hallucinated the response.

Browsing might truly be down at the time of asking, but you can never assume what it says is accurate.

1 Like