callin.io not finding internet searches with Chat GPT

The OpenAI models like “GPT-4” available through the OpenAI API do not have internet access.

You cannot use “Create a completion” with internet access because the “Internet Search” feature is exclusive to “ChatGPT Plus”.

This is a limitation imposed by OpenAI.

Do not buy ChatGPT Plus, it doesn’t work on callin.io

“ChatGPT Plus” and “OpenAI GPT-4 models” are distinct products.

You may have purchased the consumer chat “Plus” version from chat.openai.com, which is NOT compatible with callin.io.

callin.io utilizes the “OpenAI GPT-4 models,” which are exclusively accessible through the OpenAI developer platform.

Thank you for your clarification,

Caught up in work, I didn’t realize I’d opened another similar topic: Chat GPT different answers in Make - #2 by samliew
: which you can close this link

To get to the end of our thoughts on the subject. Is there a way, via an application already integrated on callin.io, to achieve this objective by carrying out internet searches ?

Thanks

Hello Quentin,

If you're still seeking an answer, I'd be happy to share my insights based on my extensive experience with this subject. I understand you might be new to this, so here's some advice for you and others in a similar situation:

Option 1: For those who can code and deploy programs on a server or cloud platform, a solution exists. A developer has shared code that effectively handles web search requests using Python and an Assistant API. This is one of the most effective methods available. You can find more details here: https://medium.com/@assafelovic/how-to-build-an-openai-assistant-with-internet-browsing-ee5ad7625661 .

Option 2: Several applications and websites offer a solution similar to Option 1 (AI online tools). These services typically require a subscription, after which you can use an HTTP application to send requests to their API. This HTTP application then manages your interactive chat requests, simplifying the process.

Option 3 (My Recommendation): Consider subscribing to Perplexity AI. They have recently introduced their online Large Language Models (LLMs), which are exceptionally well-suited for web searches. This option builds on Option 2 but provides more flexibility for customizing prompts for Perplexity and incorporates a dual AI system. It uses ChatGPT to generate queries, which are then sent via HTTP to Perplexity for research. This approach is not only innovative but also cost-effective, offering 1 million tokens/1000 requests for $5.

Option 4: A less refined but practical strategy involves using RapidAPI.com or similar platforms to locate a dependable web search API service. After subscribing, you can make an HTTP request to RapidAPI, which then functions as your personal Google search. This method allows you to instruct ChatGPT to generate responses based on web search queries. You then transmit these queries via HTTP, receive the web results, and prompt another ChatGPT session to analyze and summarize the retrieved information. This option could be the most economical, as many web search APIs provide generous free monthly quotas.

Option 4 might be particularly attractive if you're also aiming to reduce expenses, considering that web search APIs are generally more affordable. In some instances, you might not incur any charges due to their complimentary monthly allowances.

Welcome to the callin.io community! Thanks for breaking down the available options.

I think option 1 might be out of reach for most people using callin.io.

More information on option 3 can be found here.

has previously mentioned that option 4 is not suitable for their requirements here.