What's new

LLM guide with FREE options

You do not have permission to view the full content of this post. Log in or register now.

A large language model (LLM) is a type of artificial intelligence (AI) that has been trained on a massive dataset of text and code. This allows LLMs to generate text, translate languages, write different kinds of creative content, and answer your questions in an informative way.

LLMs are characterized by three main parameters:



  1. Accuracy
  2. Efficiency
  3. Token limits


While the first two are quite intuitive, token limits demand a discussion.

What are token limits?

Token limits are restrictions on the number of tokens that an LLM can process in a single interaction. A token is a unit of text that is used to represent a word, phrase, or other piece of text. For example, the phrase "I love you" would consist of 5 tokens: "I", "love", "you", ".", and " ".

Why are token limits relevant?

Token limits are relevant because they can affect the performance of LLMs. If the token limit is too low, the LLM may not be able to generate the desired output.

For example, if you are trying to generate a 1000-word document but the token limit is 1000, the LLM will only be able to generate the first 1000 tokens.

Whereas if it’s too high, the LLM is going to be very slow and require very high computational power.

Can we bypass token limits?

There are a few ways to do this:



  1. Break down your input into smaller chunks. This will help you stay within the token limit.
  2. Use a tokenizer to count the number of tokens in your input. This will help you to make sure that you are not exceeding the token limit.


If you want to find out more about LLMs, you can click on this You do not have permission to view the full content of this post. Log in or register now. for more details - view the Excel file.



Comparison of Various Large Language Models (LLMs) & Their Capabilities


No alt text provided for this image



1. GPT4: GPT4 is a powerful language model with a token limit of 32,768 and an estimated word count of 25,000 words. It excels in complex reasoning and creative tasks, making it ideal for advanced language processing applications. However, its main weakness lies in its slow processing speed. GPT4 cannot understand images, run code, or read files. It has an impressive parameter count of 1.7 trillion, indicating its complexity. While not open-source, GPT4 is available for use at a reasonable price of $20/month, with training data from September 2021. It supports multimodal inputs, including text and images.



2. GPT3.5: GPT3.5 is a language model with a token limit of 4,096 and an estimated word count of 3,083 words. It is suitable for tasks involving simple reasoning and providing fast answers. However, GPT3.5 can get stuck in reasoning loops and lacks current-world data. Similar to GPT4, it doesn't understand images, run code, or read files. With 175 billion parameters, it is a capable model, available for free since September 2021, but lacks fine-tuneability. GPT3.5 is unimodal and supports text inputs only.



3. Llama2: Llama2 is a language model designed for natural language processing and better comprehension of conversations. It has a token limit of 2,048 and an estimated word count of 1,563 words. While it performs well in language tasks, it may struggle with coding-related tasks. Unlike the previous models, Llama2 can understand images, but it can't run code or read files. With 70 billion parameters, it offers some fine-tuneability and is open-source. Llama2 is available for free and has training data from September 2022. It supports multimodal inputs, including images, text, and audio.



4. Claude 2: Claude 2 is a language model with an impressive token limit of 100,000 and an estimated word count of 60,000 words. It boasts stronger reasoning capabilities compared to GPT3.5, making it suitable for tasks requiring complex logic. However, Claude 2 has the downside of occasionally hallucinating and is currently available only in the US and UK. Like the previous models, it cannot understand images, run code, or read files. With 860 million parameters, it is less complex than some other models. Claude 2 is free to use and its training data is from early 2023. It is designed for unimodal text inputs.



5. PaLM: PaLM is a high-efficiency language model with a token limit of 8,000 and an estimated word count of 6,200 words. It outperforms GPT3 in certain reasoning tasks, making it valuable for specific language processing applications. However, PaLM has limited memory and token capacity, making it unsuitable for handling extensive information. Unlike the previous models, it can understand images, run code, and read files. With 540 billion parameters, PaLM offers significant fine-tuneability. It is open-source and free to use, with training data from mid-2021. PaLM supports multimodal inputs, including images, text, and audio.

No alt text provided for this image



Index of column headers

Estimated Word Count:

The estimated word count refers to the approximate number of words that can fit within the token limit or character limit of an AI language model. It is essential to consider this limit when using the model for text generation or processing, as input text that exceeds the limit may need to be truncated or split.

Best Use-Cases:

AI language models are widely used for natural language processing tasks, including but not limited to chatbots, language translation, text summarization, sentiment analysis, content generation, question answering, and language understanding tasks like sentiment analysis.

Weaknesses:

AI language models have several weaknesses, including the potential to generate plausible but incorrect responses, sensitivity to input phrasing, and susceptibility to bias learned from training data. They may also struggle with context retention beyond their token limit and may not have a true understanding of the meaning of the text.

Parameters:

Parameters in an AI language model are the variables that store its knowledge. Larger models with more parameters tend to perform better but also require more computational resources for training and inference.

Fine Tuneability:

Fine-tuneability is the capability of an AI language model to be further trained on specific data or tasks. Fine-tuning allows users to customize the model's behavior for more domain-specific or specialized use cases.

Pricing:

AI language models are typically offered under various pricing plans, which may include free tiers for limited usage and ρáíd subscriptions based on usage volume or additional features. The pricing structure can vary among different AI service providers.

Training Data Date:

The training data date indicates when the AI model's training data was last updated. More recent training data can help the model stay up-to-date with current trends and events, making it more relevant for certain applications.

Open Source:

Some AI language models are open-source, meaning their architecture and training data are publicly available for research, development, and customization. Open-source models promote transparency and encourage collaboration within the AI community.

Multimodal Capability:

Multimodal AI models can process and generate information from multiple modalities, such as text, images, and even audio. These models are valuable for tasks that involve both textual and visual content, enabling more sophisticated and context-aware applications.

For additional infos extend your search here:
You do not have permission to view the full content of this post. Log in or register now.
You do not have permission to view the full content of this post. Log in or register now.
You do not have permission to view the full content of this post. Log in or register now.
You do not have permission to view the full content of this post. Log in or register now.
You do not have permission to view the full content of this post. Log in or register now.

===============================================================================
For the best LLMs of 2024 check here:
You do not have permission to view the full content of this post. Log in or register now.
+ You do not have permission to view the full content of this post. Log in or register now.
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Be sure to visit this site to have an idea which LLM fits your needs:

You do not have permission to view the full content of this post. Log in or register now.

===============================================================================
Since you were already provided with links on how they work and where to get them based on the links, this will be a special recommendation for people who want a personal LLM using the FREE service provided by the said companies:

1. You do not have permission to view the full content of this post. Log in or register now.: Google Gemini is a family of new AI models from Google. Gemini Nano, Gemini Pro, and Gemini Ultra are Google's attempts to play catchup. All three versions are multimodal, which means that in addition to text, they can understand and work with images, audio, videos, and code.

The free version is Gemini Pro. You can utilize Gemini Pro in two ways, using You do not have permission to view the full content of this post. Log in or register now. (w/ a tuned version of it) or using its API using the full specs in Google AI Studio. You can explore all services in You do not have permission to view the full content of this post. Log in or register now.. For advanced Generative AI features of Gemini and models, you need the ρrémíùm You do not have permission to view the full content of this post. Log in or register now.. It's also free to try but you need to log in with a credit card.

NOTE: BARD AI is now replaced by Gemini playground: You do not have permission to view the full content of this post. Log in or register now.

Here's a simple guide:
1. Start You do not have permission to view the full content of this post. Log in or register now.
2. Click the You do not have permission to view the full content of this post. Log in or register now. link
3. Login with your Google email account
4. Click the "Get API" key and create your API keys for your AI project related to using Gemini Pro and Gemini Pro Vision
On your dashboard (on the left) click "Getting Started" to understand the information to get you going using the two models.
You can also utilize GP or GPV using the command prompt using the code provided of your choice by clicking "Get Code". Just input your API key to make it work. Check the documentation for clarity. If unsure, just click "Create new" and test the AI using your prompts.

I've already mentioned the other options to use GP API keys on other threads so feel free to experiment:
You do not have permission to view the full content of this post. Log in or register now.

(Note that, at the moment on previous links, You do not have permission to view the full content of this post. Log in or register now.. the only advantage it has is a ~30k input token and ~2k output token limit, much faster, not to mention the decent 60 requests per minute rate. A plus for a free API compared to ChatGPT *GPT3.5-turbo) which is limited to 3 months of use yet can be used forever using the You do not have permission to view the full content of this post. Log in or register now.when you log in. The only option to use ChatGPT with a 4k input token for free with better results is to use the You do not have permission to view the full content of this post. Log in or register now. to get real-time results.)

My other option to use GP with Copilot is to use You do not have permission to view the full content of this post. Log in or register now. + You do not have permission to view the full content of this post. Log in or register now.. Just go to the Obsidian site and install the application. Open the GUI, click settings, then go to Community Plugins install Copilot, and enable it. under Copilot, set the GP API key and save settings. In the GUI. Set your LLM to Gemini Pro and that's it. you can also use other LLM APIs supported by Copilot if you have them. The best feature is you can also use custom OpenAI apis/ base URLs or endpoints. I'll discuss them later if there's a need.

1706793883201.png

It's just an option for those who research and write articles using their AI as an assistant. Quite good.
Note: Please set tokens to 2000 for this LLM before using it. The best free interfaces you can use with Gemini Pro are You do not have permission to view the full content of this post. Log in or register now., and the moddedYou do not have permission to view the full content of this post. Log in or register now. which uses ChatGPT plugins. Setting up these two is not easy, so the best option is to look for web links that deploy these "app services" (by users) as mentioned on their site or elsewhere like Vercel, Gitpod, Huggingface, etc. Be sure these deployed live servers are using the latest versions or else you can't use Gemini Pro APIs. So a collection of APIs is a must to utilize these applications whether it's new or old.

If you want a full-featured GUI with multiple support for LLMs/GPTS and has a plus feature to use ChatGPT plugins like in ChatGPT Plus, try running Librechat. Or try their full GUI You do not have permission to view the full content of this post. Log in or register now. This is their updated development. You just need to have your API keys available, like Gemini Pro. Log in with your email and try this UI. Plugins support only OpenAPI GPTs.
1707272694977.png



===============================================================================

2. MICROSOFT COPILOT:
Microsoft Copilot was formerly known as Bing Chat. The AI companion was officially rebranded, and the transition from Bing Chat to Microsoft Copilot was announced on November 15, 2023. The tool, now called Copilot, serves various purposes such as aiding in document creation, email summarization, presentation crafting, and more.
To understand more about third-party reviews, visit these sites:
You do not have permission to view the full content of this post. Log in or register now.
You do not have permission to view the full content of this post. Log in or register now.
You do not have permission to view the full content of this post. Log in or register now.

Since it's free, the only requirement is a browser (preferably Edge) and an email account.
Click any of the two to gain access and log in:
For Chrome: You do not have permission to view the full content of this post. Log in or register now.
For Edge: You do not have permission to view the full content of this post. Log in or register now.
For other platforms, scan this URL: You do not have permission to view the full content of this post. Log in or register now.

These are the things it can do:
1. You do not have permission to view the full content of this post. Log in or register now.
2. You do not have permission to view the full content of this post. Log in or register now.
3. You do not have permission to view the full content of this post. Log in or register now.
4. You do not have permission to view the full content of this post. Log in or register now.
5. You do not have permission to view the full content of this post. Log in or register now.

Note:
Some individuals may notice some doubts about where to access officially the main sites after the transition of Bing AI to the Microsoft Copilot platform. There are some differences so the best is to get the feel of what they provide. You'll see when you get there, most specifically the tokens for image generation (designer), chats, plugins, etc.

You do not have permission to view the full content of this post. Log in or register now. - official
You do not have permission to view the full content of this post. Log in or register now. - bing.com integration

other URLs to test:
You do not have permission to view the full content of this post. Log in or register now. - uses OpenAI's DALL-E 3

Based on the latest updates, Copilot (free) includes the following features:
  • Access on the web, mobile, Windows, macOS, and iPad
  • Access to GPT-4 and GPT-4 Turbo during non-peak times
  • Utilize text, voice, and images in conversational search
  • Create AI images with 15 boosts per day with Designer
  • Support for plugins and GPTs
  • The free version of Copilot will drop down to the older GPT 3.5 during peak times, whereas Copilot Pro will remain at GPT-4 and GPT-4 Turbo. Output tokens will depend on the model used.
  • The free version of Copilot comes with just 15 boosts per day
  • 30 chats per image remain in effect
  • Lifted rate limits at the moment for chats, previously at 300 requests
  • Updates may change hereafter!
Options for better utilization of the free Microsoft Copilot is use SydneyQT:
You do not have permission to view the full content of this post. Log in or register now.
It's a cross-platform desktop client for the jailbroken New Bing AI (Sydney ver.) built with Go and Wails (previously based on Python and Qt). Please go to the "Release" page for installers on supported platforms. It's easy to use. Just just copy and save your live cøøkíés.json (after logging in) into the app folder and run the application.

Note: We'll not discuss much on You do not have permission to view the full content of this post. Log in or register now.since it is assumed that everybody should be well aware of the original company that started this AI phenomenon. You have 3 months to use the free ChatGPT API (i.e. API keys for supported models) for a $5 credit. These API keys can be used on any interface or program of your choice. As mentioned, the free account could still be used on the You do not have permission to view the full content of this post. Log in or register now. even if your API expires.

3. You do not have permission to view the full content of this post. Log in or register now.:
In this repository, we explore and catalog the most intuitive, feature-rich, and innovative web interfaces for interacting with LLMs. These UIs range from simple chatbots to comprehensive platforms equipped with functionalities like PDF generation, web search, and more. Instructions on how to set up and run the listed WebUIs are provided within their respective repositories.
These apps can be run locally, either standalone offline or with online assistance, depending on where the AI service is used or deployed. My suggestion is, to try the apps or even try their "demo links" to get a feel of how AI works. It helps ease our difficulties when visiting online sites that provide similar services. It's hard at first, but it will become easy as you progress - part of the learning process.
Note: "Demo links" are live servers, and most provide free LLM/GPT service too with decent rate limits

4. You do not have permission to view the full content of this post. Log in or register now.:
This repository is a collection of awesome projects and resources related to GPT, ChatGPT, OpenAI, LLM, and other related technologies. Whether you're just getting started with GPT or you're a seasoned expert, this list has something for everyone.

GPT (Generative Pre-trained Transformers)
  • You do not have permission to view the full content of this post. Log in or register now. - OpenAI’s most advanced system, producing safer and more useful responses.
  • You do not have permission to view the full content of this post. Log in or register now. - A variant of the GPT language model that is specifically designed for generating human-like responses in conversational settings
  • You do not have permission to view the full content of this post. Log in or register now. - An AI system that can create realistic images and art from a description in natural language.
  • You do not have permission to view the full content of this post. Log in or register now. - Transcribe speech into text and translate many languages into English.
  • You do not have permission to view the full content of this post. Log in or register now. - The new Bing is like having a research assistant, personal planner, and creative partner at your side whenever you search the web.
  • You do not have permission to view the full content of this post. Log in or register now. - Create images from words with AI, powered by DALL·E.
LLM (Large Language Models)
  • You do not have permission to view the full content of this post. Log in or register now. - An experimental conversational AI service, powered by LaMDA.
  • You do not have permission to view the full content of this post. Log in or register now. - A next-generation AI assistant based on Anthropic’s research into training helpful, honest, and harmless AI systems.
  • You do not have permission to view the full content of this post. Log in or register now. - HuggingChat's goal is to provide an AI assistant with a friendly, human-like personality and the ability to understand and respond to natural language queries from users like you.
  • You do not have permission to view the full content of this post. Log in or register now. - Firefly is the new family of creative generative AI models coming to Adobe products, focusing initially on image and text effect generation.
  • You do not have permission to view the full content of this post. Log in or register now. - An artificial intelligence program and service created and hosted by a San Francisco-based independent research lab Midjourney, Inc.
  • You do not have permission to view the full content of this post. Log in or register now. - A deep learning, text-to-image model released in 2022. It is primarily used to generate detailed images conditioned on text descriptions.
  • You do not have permission to view the full content of this post. Log in or register now. - An AI chatbot service product of Baidu, based on a large language model named "Ernie 3.0-Titan".
  • You do not have permission to view the full content of this post. Log in or register now. - A chatbot service developed by Alibaba Cloud, which can interact with people, answer questions and collaborate in creation.

Developers
  • You do not have permission to view the full content of this post. Log in or register now.
  • You do not have permission to view the full content of this post. Log in or register now.
  • You do not have permission to view the full content of this post. Log in or register now.
  • You do not have permission to view the full content of this post. Log in or register now.
  • You do not have permission to view the full content of this post. Log in or register now.
  • You do not have permission to view the full content of this post. Log in or register now.
  • You do not have permission to view the full content of this post. Log in or register now. - Plugins are tools designed specifically for language models with safety as a core principle, and help ChatGPT access up-to-date information, run computations, or use third-party services.
Copilot
  • You do not have permission to view the full content of this post. Log in or register now. - Trained on billions of lines of code, GitHub Copilot turns natural language prompts into coding suggestions across dozens of languages.
  • You do not have permission to view the full content of this post. Log in or register now. - Make Windows 11 the first PC platform to announce centralized AI assistance to help people easily take action and get things done.
  • You do not have permission to view the full content of this post. Log in or register now. - Your copilot for work. It combines the power of large language models (LLMs) with your data in the Microsoft Graph and the Microsoft 365 apps to turn your words into the most powerful productivity tool on the planet.
  • You do not have permission to view the full content of this post. Log in or register now. - Copilot in both CRM and ERP, that brings next-generation AI to every line of business.
  • You do not have permission to view the full content of this post. Log in or register now. - Bringing the power of AI Copilot to both app makers and their end-users in Power Apps. With Copilot you can build an app, including the data behind it, just by describing what you need through multiple steps of conversation.
  • You do not have permission to view the full content of this post. Log in or register now. - Empower your defenders to detect hidden patterns, harden defenses, and respond to incidents faster with generative AI.
  • You do not have permission to view the full content of this post. Log in or register now. - Xmind Copilot is an intelligent product that combines Xmind mind mapping with GPT technology. It can help users organize their thoughts more efficiently, adjust content structures, and automatically generate articles using GPT technology.
Project and Tools
  • You do not have permission to view the full content of this post. Log in or register now. - An experimental open-source attempt to make GPT-4 fully autonomous.
  • You do not have permission to view the full content of this post. Log in or register now. - Enhancing Vision-language Understanding with Advanced Large Language Models.
  • You do not have permission to view the full content of this post. Log in or register now. - DeepSpeed empowers ChatGPT-like model training with a single click, offering 15x speedup over SOTA RLHF systems with unprecedented cost reduction at all scales.
  • You do not have permission to view the full content of this post. Log in or register now. - TaskMatrix connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting.
  • You do not have permission to view the full content of this post. Log in or register now. - Building applications with LLMs through composability. LangChain’s flexible abstractions and extensive toolkit enables developers to harness the power of LLMs.
  • You do not have permission to view the full content of this post. Log in or register now. - Semantic Kernel (SK) is a lightweight SDK that lets you easily mix conventional programming languages with the latest in Large Language Model (LLM) AI "prompts" with templating, chaining, and planning capabilities out-of-the-box.
  • You do not have permission to view the full content of this post. Log in or register now. - Write, edit, and chat about your code with a powerful AI.
  • You do not have permission to view the full content of this post. Log in or register now. - An AI pair programmer that helps you write better code, faster.
  • You do not have permission to view the full content of this post. Log in or register now. - An AI coding companion that generates whole line and full function code suggestions in your IDE to help you get more done faster.
  • You do not have permission to view the full content of this post. Log in or register now. - CodeGeeX is an open-source AI Coding Assistant, supporting VS Code and JetBrains IDEs.
  • You do not have permission to view the full content of this post. Log in or register now. - Tabnine uses generative AI technology to predict and suggest your next lines of code based on context & syntax. It can be run on a developer's laptop, on a server inside your firewall, or in the cloud.
  • You do not have permission to view the full content of this post. Log in or register now. - IntelliCode helps you drive accuracy and consistency with code completion that can fill in a whole line at once, supporting VS Code and VS IDE.
  • You do not have permission to view the full content of this post. Log in or register now. - Framework to create ChatGPT-like bots over your dataset.
  • You do not have permission to view the full content of this post. Log in or register now. - GPTRouter is an open-source LLM API Gateway that offers a universal API for 30+ LLMs, vision, and image models, with smart fallbacks based on uptime and latency, automatic retries, and streaming. Stay operational even when OpenAI is down.
Applications and Demos
  • You do not have permission to view the full content of this post. Log in or register now. - An Azure OpenAI API proxy tool that can convert OpenAI API requests into Azure OpenAI API requests, allowing applications that only support OpenAI to seamlessly use Azure Open AI.
  • You do not have permission to view the full content of this post. Log in or register now. - A fast code search engine written in Rust.
  • You do not have permission to view the full content of this post. Log in or register now. - Connect AI models (like ChatGPT-3.5/4.0, Baidu Yiyan, New Bing, Bard) to apps (like Wechat, public account, DingTalk, Telegram, QQ).
  • You do not have permission to view the full content of this post. Log in or register now. - AI tool to build charts based on text input.
  • You do not have permission to view the full content of this post. Log in or register now. - chat web app for teams, sass with user management and rate limit, support openai, claude model or custom model
  • You do not have permission to view the full content of this post. Log in or register now. - Integrating ChatGPT into your browser deeply, everything you need is here.
  • You do not have permission to view the full content of this post. Log in or register now. - A code review bot powered by ChatGPT.
  • You do not have permission to view the full content of this post. Log in or register now. - Integrate ChatGPT into your d-i-s-c-o-r-d bot.
  • You do not have permission to view the full content of this post. Log in or register now. - One-Click to deploy well-designed ChatGPT web UI on Vercel.
  • You do not have permission to view the full content of this post. Log in or register now. - A ChatGPT Teams Bot app to let you chat with ChatGPT in Microsoft Teams.
  • You do not have permission to view the full content of this post. Log in or register now. - Run your own GPTChat Telegram bot, with a single command.
  • You do not have permission to view the full content of this post. Log in or register now. - ChatGPT Telegram Bot: GPT-4. Fast. No daily limits. Special chat modes.
  • You do not have permission to view the full content of this post. Log in or register now. - ChatGPT WeChat Bot, based on ChatGPT API and Wechaty.
  • You do not have permission to view the full content of this post. Log in or register now. - Integrate ChatGPT into your own WeChat Public Account.
  • You do not have permission to view the full content of this post. Log in or register now. - Dingtalk + GPT-3.5.
  • You do not have permission to view the full content of this post. Log in or register now. - Feishu + (GPT-3.5, DALL·E, Whisper).
  • You do not have permission to view the full content of this post. Log in or register now. - AI-powered search engine for workplaces.
  • You do not have permission to view the full content of this post. Log in or register now. - GPT4 & LangChain Chatbot for large PDFs do
Don't forget to visit these other links for more:
You do not have permission to view the full content of this post. Log in or register now.
You do not have permission to view the full content of this post. Log in or register now.


Note: Most of the apps at Github don't have ready-made releases like executables, and zipped files for the supported platforms. Some were made to be deployed locally using Docker or deployed on an online server like Vercel, Gitpod, Google Colab, Huggingface, etc. The rest can run locally if the code is correct using the programming language supported following the Guides. You can see the supporting programming platforms on the bottom-right corner of the main development page. Ex. for Typescript, you need to install Nodes.js, for Python, get the Python installer, etc... Each channel also provides installation of modules or requirements for the language used. (Not all provide decent guides for beginners, but most have to gain support for their app.)

Sometimes, when using Python. Some codes don't build correctly as some older modules are not supported by newer versions of Python. If that's the case, instead of uninstalling and installing versions that will work on your project, just use "virtualenv". follow this guide to make it work.
You do not have permission to view the full content of this post. Log in or register now.

Refer here for the AI information on this previous thread:

You do not have permission to view the full content of this post. Log in or register now.


Note: Don't trust the AI's yet. They are still lacking in most areas of knowledge. They are tools only to assist and not always 100% reliable. Be sure to review and fact-check their results.

===============================================================================


 

Attachments

Last edited:
Masyadong mahaba na yung first post, kaya magdagdag na lang ako ng free options sa mga interisado sa open-source method:
You do not have permission to view the full content of this post. Log in or register now. - cli-version of WebchatGPT
Medyo parehas din ito ng browser plugin na WebchafGPT. Just follow the simple guide sa link. Be sure to log in sa ChatGPT Playground, get and save the cøøkíés, and create the .env file.
(Note: Always create a virtual environment and activate para hindi ma-corrupt yung system Python environment kung sakaling mag-test kayo ng ibang apps na mag-require ng pip installation ng custom versions ng modules.)
1707392933158.png

Ito yung display after installing the requirements - re-opened console, not the pre-installation display.
Ito yung sample commands na basic to run python apps in a virtual environment. Just know when to use them as stated sa Python manuals. (This is not a step-by-step-sequence!)
python -m venv venv -- create environment
.\venv\Scripts\activate -- activate environment
.\venv\Scripts\deactivate -- deactivate environment then close cmd prompt console
pip install -r requirements.txt --use this when application requires external modules to run it
1707391901371.png

Ito yung other displays when testing again. Di masyadong pulido pa pero works fine for simple tasks without the browser.

For other better options you can try these two, na related itong app na ito. Mas maraming features pa at maraming paraan to install - easy and hard way!
You do not have permission to view the full content of this post. Log in or register now.
You do not have permission to view the full content of this post. Log in or register now.
May direct installers ito kaya iwas manu-mano he he. Parang gpt4free din yang mga yan - free and doesn't need to input api parameters. Just read the guides for other important details to run them properly.
You have to see for yourself. Pero sa akin, gpt4free is the best kung gusto ninyo ng libre talaga in one GUI using the console+browser. Or else, isa-isahin ninyo yung free providers na gamit nya to have the same effect.
 

Attachments

Last edited:
Chat with your PDF Free options using Free Gemini Pro API key

Since Gemini Pro is free to use at 60 requests/minute with no set limits (at the moment), you can chat with your PDFs using free tools at Github.
1. You do not have permission to view the full content of this post. Log in or register now.
Check their You do not have permission to view the full content of this post. Log in or register now. and decide to deploy your own by clicking "fork the app" or running it locally. Just create/edit the .env file in your root directory using your api key.)
2. You do not have permission to view the full content of this post. Log in or register now.
Check their You do not have permission to view the full content of this post. Log in or register now. and decide to deploy your own by clicking "fork the app" or running it locally. Just create/edit the .env file in your roor directory using your api key.)

Though sa Google AI Studio ay pwede nyong paglaruan yang Gemini Pro when you log in, pwede nyo rin magamit externally on your pc using these simple projects.
1. You do not have permission to view the full content of this post. Log in or register now.
2. You do not have permission to view the full content of this post. Log in or register now.
3. You do not have permission to view the full content of this post. Log in or register now.
4. You do not have permission to view the full content of this post. Log in or register now.

Ito yung mga simplest projects using Gemini Pro for Free.

Example of Free API to use in any supported Chatbot UI - like custom API from proxied or reverse engineered hosted API:
Go here
: You do not have permission to view the full content of this post. Log in or register now.
The content highlights the ChatGPT API Free Reverse Proxy, a tool allowing free access to OpenAI API. The features include using multiple OpenAI keys, built-in moderation, streaming response, and compatibility with official OpenAI libraries. Users can self-host the API or use the hosted version. The provided steps explain how to set up and use the reverse proxy, and examples are given for text completion, chat completion, and image generation using OpenAI libraries in Python and Node.js. The project is licensed under the MIT License.

For the "hosted api" you need to join his "diyescord" channel (he he). Read the server guide and channel rules. The information there is provided to get your free api key and correct endpoints to be used in their supported GUIs. Be sure to read the #Docs, #Limits and #Known-Issues to use the Free API.
(Nasa #Bots section yung option to create your API using the /key script request. Pwede yang gamitin sa You do not have permission to view the full content of this post. Log in or register now., You do not have permission to view the full content of this post. Log in or register now., NextChat, You do not have permission to view the full content of this post. Log in or register now. or You do not have permission to view the full content of this post. Log in or register now., atbp. Kapain nyo na lang sa UI. Ang importanteng parameters sa UI is the api-key, custom endpoint/base-url, at model. NextChat and BetterChatGPT have windows installers para mapadali or use their demo links.
Ito yung sample setting sa NextChat na binanggit ko sa thread:
(Dalawa yung gamit kong NextChat, yung isa yung original (You do not have permission to view the full content of this post. Log in or register now.) at yung pangalawa ay fork with plugins (You do not have permission to view the full content of this post. Log in or register now.). Plugins will only work using OpenAI API keys like requirement of LibreChat plugins, so just use the original.)
1708396751815.png

Ito yung sa BetterChatGPT. Using this endpoint, the set GPT3.5 will function using your pai-001 model. Change the endpoints provided for other UIs as instructed sa channel.
1708398165145.png

Kayo na bahala sa VenusAI at JanitorAI at di ko pa nasubukan gumamit ng api dyan. Dekada na akong nakikipag-usap sa AI at wala na akong oras para sa ganyang service he he.

Spoiler contents are visible only to Established Members.

Two models ang provided to use the OpenAI-like API. For other APIs (Embeddings, TTS, STT, Translation, Search, etc.), just look for the #API section to learn more about how to use them. I only provided you an idea on how to get some free service which you can use. It takes time to learn, but the benefits are endless since there are other similar providers like this on the net.
Good Luck.

PS. Tested in JanitorAI at VenusAI - working when set at API settings!
Use this guide kung gagamit kayo ng KoboldAI API url for the two:
You do not have permission to view the full content of this post. Log in or register now.
 

Attachments

Last edited:
Use RapidAPI apis for Free:

RapidAPI, the world's largest API hub, is used by over three million developers to find, test, and connect to thousands of APIs—all with a single API key and dashboard.

Find the APIs that you need for your project, embed the API into your app, and track usage of all your APIs through a single dashboard. If you create an API, use RapidAPI to make it available to over three million developers already using the You do not have permission to view the full content of this post. Log in or register now..

But before you proceed on its Hub, you need to read the guides and information on how to utilize the APIs here.
You do not have permission to view the full content of this post. Log in or register now.

Try to learn the "ins and outs" of RapidAPI services for ease of work.
-----------------------------------------------------------------------------------------------------------------
Ex. We'll try a Fremium ChatGPT API: You do not have permission to view the full content of this post. Log in or register now.
You need to login and subscribe to this API to use it. The guide teaches you You do not have permission to view the full content of this post. Log in or register now.. It only provides 1000 tokens per month, but this is just a trial to show how it works. There are others providing more decent free trial usage.
To be sure that the server is alive after subscribing, go to the Endpoints section and click Test Endpoint. Regardless of the set code language in the Code Snippets, make sure it shows the "200 success" response as shown - it's working!
1708756244161.png


I'm just a novice coder, so I either look for custom-made apps using this api (which is hard) or just modify the code snippets so that I can use it on my PC through command line.
Navigating to the Python (Requests) script under Code Snippets, I edited it in such a way that it will converse continuously since the basic code will just show one result.

Code:
import requests

url = "https://chat-gpt26.p.rapidapi.com/"
headers = {
    "content-type": "application/json",
    "X-RapidAPI-Key": "7e1cc27820msh7acbe07664bc13bp1ee86ajsnd8d7c7a4520c",
    "X-RapidAPI-Host": "chat-gpt26.p.rapidapi.com"
}

def send_message(message):
    payload = {
        "model": "gpt-3.5-turbo",
        "messages": [
            {
                "role": "user",
                "content": message
            }
        ]
    }
    try:
        response = requests.post(url, json=payload, headers=headers, timeout=5)  # Added timeout for handling slow responses
        response.raise_for_status()  # Raises an HTTPError if the HTTP request returned an unsuccessful status code
        return response.json()
    except requests.exceptions.RequestException as e:
        print(f"An error occurred: {e}")
        return None

while True:
    user_input = input("You: ")
    if user_input.lower() == "quit":
        break
    response = send_message(user_input)
    if response is not None:
        # Extracting the bot's response from the API response
        try:
            bot_response = response['choices'][0]['message']['content']
            print(f"Bot: {bot_response}")
        except KeyError:
            print("Bot: Response format not recognized. Check the API response structure.")
    else:
        print("Bot: No response received.")

Below is the comparison results between the original script and mine.
1708756974082.png


Through trials, errors, and practice, I already learned to edit code with the use of Free GPT as my Python tutor and on any language that is suitable for me. I use the free open-source LLM only to make it quicker and easier to use. And it's easy to improve this code with just using prompts to create a simple functioning GUI.

Forks of LLAMA2 work for me or any better ones from OpenAI. Try it in Huggingface.
(Just look for API providers in RapidAPI HUB that provide multiple requests and a much higher tokens to maximize using this trick.) Ang dami dyan totally free and almost unlimited use. Mahirap lang sa umpisa pero this site is your best bet if you're looking for free service without depending on other sources. Solo mo kasi yung service. Yung shared online is always limited, based on my experience. Rate limits are always a factor in all cases, unless your requests are only a few and intermittent.

Note: This is not recommended for beginners, but you can start trying to learn this simple craft and improve a bit later when you get used to it, as this applies to all types of AIs like TTS, STT, web scraping, image generation, etc.
RapidAPI has lots of these to choose from. It's all up to you. Good Luck.
 

Attachments

Last edited:
Updates for Gemini Pro usage as Excel add-in:

The Free Gemini Pro API account can also be used in Microsoft Excel. Even Microsoft 2013 supports it!
Just browse this link and try to study how you can use this GPT in your Excel projects for assistance.
Spoiler contents are visible only to Established Members.
So get your free API key in Google AI Studio to use it. Guides are provided in the thread to make this work.

For other benefits of Google Bard or Gemini AI, please refer to this link:
Spoiler contents are visible only to Established Members.
---------------------------------------------------------------------------------------------------------------------
May option din sa OpenAI, pero di ko ma-test dahil paso na lahat ng original API keys ko. And it doesn't support my OpenAI cloned APIs. Pero the "Add-ins" can also be used in Microsoft Excel 2013 dahil pumapasok yung cell helper commands nya. (Still trying to find ways to integrate the ChatGPT Web API.)
 
Last edited:
Latest AI introduced that is a must:

Chrome Beta with AI features: You do not have permission to view the full content of this post. Log in or register now.


1708928750783.png


1. AI-powered tab search: This feature allows users to quickly find tabs by searching for keywords or phrases in the tab bar.

2. AI-powered suggestions: Chrome beta may offer suggestions for actions or tasks based on the user's browsing history and preferences.

3. AI-powered content generation: Some experimental builds of Chrome beta have included features that can generate text, images, or code based on user input.

4. AI-powered translation: Chrome beta may offer real-time translation of web pages into different languages.

5. AI-powered privacy features: Chrome beta may include experimental features that enhance user privacy, such as the ability to block trackers or control how websites access user data.

It's important to note that these experimental AI features are still in development and may not be available in all versions of Chrome beta. Additionally, the availability and functionality of these features may change over time as they are further developed and refined.

=============================================================================
Refer to Chrome Beta website to unlock its features.
Try here: You do not have permission to view the full content of this post. Log in or register now.


Sa ibang browsers meron din silang katapat:

Brave Leo AI: You do not have permission to view the full content of this post. Log in or register now.
Opera Browser AI: You do not have permission to view the full content of this post. Log in or register now.


Some may say, i's a market strategy by competing brands in the browser category, as all know, even a simple browser can be AI intensive using compatible plugins and extensions, as if it was internally there. But there are things AI plugins can't do, like in the next real AI browser. The rest I mentioned, even Chrome has not reached yet what Microsoft did. They're all AI "cosmetics".
Microsoft Edge AI Browser: We're familiar with it too. It has been adding AI in their algorithms a long time ago like microsoft edge collections, smart copy, password monitoring. natural ai readers (read aloud feature), browser performance and vertical tab management, as well as adopting Bing as the default search engine now integrated with Microsoft Copilot. It's a decent browser I've been using side-by-side with Chrome.

=============================================================================
Microsoft Copilot in Windows 10: You do not have permission to view the full content of this post. Log in or register now.
1708930217078.png

Microsoft Copilot was introduced in Windows 11, but we can unlock it in Windows 10 too.
The link provided shows you the easiest way to do it, but the first most important part is to make sure Windows is fully updated first to install Windows Insider Preview Builds - Release Preview Channel for Windows 10.
Refer to updating your Windows to RPC using the guides on this link:
You do not have permission to view the full content of this post. Log in or register now.
Then refer to top link for the rest of the procedure just in case Copilot icon does not respond when you click at the bottom-right most section of the taskbar.

Good Luck.
 

Attachments

Last edited:
TYPINGMIND: The most advanced Web UI for AI chat.
If you want to host your own server follow this link: You do not have permission to view the full content of this post. Log in or register now.
If you want to try their interface, go here: You do not have permission to view the full content of this post. Log in or register now.

Features (as stated on github channel)​

  • 🤖Support multi models:
    • ChatGPT, Claude, Gemini, Azure OpenAI, Perplexity AI, Mixtral AI, LLama
    • Adding custom endpoint, custom models (e.g., Open Router), and locally hosted models (e.g., LocalAI, Ollama)
    • Custom model parameters: Temperature, Frequency_penalty, Presence_penalty, Top_P, Top_K, etc.
  • 🚀 Advanced Features: GPT-4 Vision, Document Uploads, DALL-E 3, Web Search, Text-to-Speech, Whipsper, Plugins
  • 💬Chat Management:
    • Tags, Search, Folders, Share, Backup & Sync, Import/Export, Migrate from ChatGPT
    • Fork Chat (conversation branching), Edit Message, Pin
  • 📚 Prompt Library (with template variable support), AI Characters, Output Control, Dynamic Context Limit
  • 🔐 Secure and private by default: API keys encryption, set password, self-host
  • 🖥️Beautiful and Functional User Interface:
    • Voice Input, Text-to-Speech, Sound Notification
    • Light/Dark mode, Hotkeys, Responsive & Mobile Friendly, Wide Screen Support
  • 🧩 Integrations: Web Search, Plugins System (develop your own plugins), Search Keyword Suggestions
  • 🇺🇸Multilingual:
    • 🇺🇸 English 🇩🇪 German, 🇨🇳 Mandarin, 🇻🇳 Vietnamese, 🇬🇷 Greek, 🇫🇷 French, 🇮🇹 Italian
    • 🇷🇺 Russian, 🇺🇦 Ukrainian, 🇪🇸 Spanish, 🇵🇹 Portuguese, 🇱🇺 Luxembourgish
  • 📦 You do not have permission to view the full content of this post. Log in or register now. (for teams):
    • Host a customized version of Typing Mind with custom branding, self-host, customized UI
    • Team sharing: Prompts Library, AI Characters
    • User Management, Access Control, Connect Internal Data, APIs

👋 Overview​

Typing Mind is a Chat UI frontend that allows you to use AI chats from all popular AI models with your API key (ChatGPT, Claude, Azure OpenAI, Gemini, etc.).

By using the API key with a Chat UI frontend like Typing Mind, you unlock the following benefits:

  • You only pay for what you use (instead of a monthly subscription like ChatGPT Plus)
  • Your chat conversation will NOT be used for training by OpenAI/Claude/etc.
  • Chat with multiple models conveniently within a unified interface
  • Enjoy a professional, advanced chat UI with tons of features
Typing Mind is offline first and private by default. All your data, messages, and API keys are stored locally on your device, and no one can see them except you.

This is the Static Self-host Version of Typing Mind (You do not have permission to view the full content of this post. Log in or register now.). By running the static self-host version, you can use Typing Mind from your private server or from a local device. Typing Mind is free to use with some basic features, a license key is needed to unlock all advanced features. See our You do not have permission to view the full content of this post. Log in or register now. for more information.

🚀 Getting started​

To run the app locally on your device or private server:

  1. Clone the repo
  2. Install dependencies: yarn install or npm install
  3. Start the server: yarn start or npm run start
  4. App will run at localhost:3000 by default.
Optionally, you can use any other static web server to host the src folder.

Note: if you run the app on hostnames other than localhost, you must use HTTPS to make sure all app features work.

🔗 Connect to local models​

  1. Open the app
  2. Click the model dropdown → Model Settings → Add Custom Models
  3. Enter your custom model details: Endpoint, Model ID. Custom headers and body parameters are supported.
  4. Click "Test" and then "Add Model".
If you face CORS issue, make sure to run your local model in CORS mode.

Read the official documents:

----------------------------------------------------------------​

Go to typingmind main site to try their GUI and prepare your API keys (+ required endpoints is needed.)
-------------------------------------------------------------------------------------------------------
For other information, PLEASE read their documentation to use it properly: You do not have permission to view the full content of this post. Log in or register now..
Sinama ko ito dahil supported niya yung Gemini AI as well as you can add your own custom AI models plus use the plugins if allowed.
Some AI models require you to use the appropriate API parameters (headers, strings, value...) in order for Typingmind to make your models work in their interface. For this, you need to go to the api documentation of your models to apply them in Typingmind configuration. Examples in Typingmind will guide you. The advantage here is you can use custom plugins to improve the use of your LLM like using Web Search, Summarize or talk to PDFs and other file docs, etc. like the one provide in ChatGPTPlus account.

Bonus for interested parties:
1. Try at your own risk using the Free APIS provided on the link below. It can be used in Typingmind too.
Spoiler contents are visible only to Established Members.
I'm not sure yet if all are still alive, but you need to discover them by yourselves.
Marami dyan ay links to Free APIs and links for Free GPT online kung nyo pa kayang mag-setup.

2. Combine all you APIs into one using these tools:
Spoiler contents are visible only to Established Members.
(This is not recommended for newbies, but you can try if you understand how APIs work and a bit about using python, nodes.js, go, or any required if there are no builds released from each repository. It need a lot of reading and practice to make them work too.)
If you can use one-api in Typingmind, it will easy to use it any GUI I had mentioned on this thread like ChatALL, NextChat, BetterchatGPT, etc.

Again, Good Luck.
---------------------------------------------------------------------------------------------------------------
PAHABOL!

How to Use ChatGPT Read PDF Files in 3 Ways:​

You do not have permission to view the full content of this post. Log in or register now.

Dahil halos lahat naman siguro ay nasubukan na yang You do not have permission to view the full content of this post. Log in or register now. by logging on their You do not have permission to view the full content of this post. Log in or register now., ito yung best method to make it read PDF files and chat with it.
By following the guide on the link, UPDF will integrate with your live ChatGPT session, and its UI will show this display.
1709087163456.png


I repeat for those still do not know this condition. When you log in to for a free account in OpenAI, your free use of the API (keys) will expire after 3 months but the use to ChatGPT Playground can be used forever! The downside is, you can only use GPT-3.5-turbo (on regular daily rate limits) and you have no access to use the plugins. The only best way to improve GPT-3.5-turbo responses in real time is to install WebchatGPT plugin, or use the web api (when ChatGPT Playground is active in your browser) in other third party applications or plugins that support it for other purposes. And this one is UPDF for reading PDFs with ChatGPT!

1709087778441.png
 

Attachments

Last edited:
Updates: Chrome Beta AI features has been incorporated in latest Chrome releases.
Google Chrome version 121 introduces innovative AI features aimed at enhancing user experience and productivity:

  1. Tab Organizer: A tool leveraging AI to organize tabs efficiently[You do not have permission to view the full content of this post. Log in or register now.][You do not have permission to view the full content of this post. Log in or register now.].
  2. Generative AI Features: Three experimental features, enhancing browsing personalization and ease on both Macs and Windows PCs[You do not have permission to view the full content of this post. Log in or register now.][You do not have permission to view the full content of this post. Log in or register now.][You do not have permission to view the full content of this post. Log in or register now.].
  3. AI Writing Assistant: A feature aiding users in writing on the web, showcasing advancements in generative AI for improved content creation[You do not have permission to view the full content of this post. Log in or register now.][You do not have permission to view the full content of this post. Log in or register now.].
These updates align with Google's commitment to utilizing AI and ML technologies to enhance Chrome's functionality and user interaction[You do not have permission to view the full content of this post. Log in or register now.][You do not have permission to view the full content of this post. Log in or register now.][You do not have permission to view the full content of this post. Log in or register now.].

==============================================================

Microsoft Edge AI features:
You do not have permission to view the full content of this post. Log in or register now.
  1. Side-by-Side View: Microsoft Edge incorporates a side-by-side view, simplifying and accelerating shopping and navigation[You do not have permission to view the full content of this post. Log in or register now.].
  2. AI-Powered Bing Search: The browser integrates an AI-powered Bing search engine, aiming to provide an improved web search experience[You do not have permission to view the full content of this post. Log in or register now.].
  3. AI Features Evolution: Over time, Microsoft Edge has evolved into an 'AI browser' with continuous additions of AI features, enhancing its capabilities[You do not have permission to view the full content of this post. Log in or register now.].
  4. Developer Tools and Productivity Management: For businesses and developers, Microsoft Edge offers AI innovations, including expanding the reach of Progressive Web Apps (PWAs) with sidebar and improved DevTools[You do not have permission to view the full content of this post. Log in or register now.].
  5. Copilot Integration: The browser includes Copilot, an AI-powered assistant empowered by GPT-4, enabling users to ask questions and enhancing the overall browsing experience[You do not have permission to view the full content of this post. Log in or register now.][You do not have permission to view the full content of this post. Log in or register now.].
  6. Image Creator: Edge features an AI-powered Image Creator in its sidebar, allowing users to generate images using text prompts effortlessly[You do not have permission to view the full content of this post. Log in or register now.].
  7. Security, Real-time Analytics, and Speed: The latest AI features of Microsoft Edge focus on enhancing online security, providing real-time analytics, and increasing browsing speed[You do not have permission to view the full content of this post. Log in or register now.].
------------------------------------------------------------------------------------------

Though Chrome is the best choice of most users, Microsoft Edge has surpassed all the available browsers when it comes to AI integration as well as its internal functions.
The downsides are the following:
  1. Lack of Features and Error Messages: Microsoft Edge has limitations such as a scarcity of features like extensions and plug-ins. Users may encounter error messages when accessing collaboration websites like Blackboard Collaborate, Zoom, or Microsoft Teams in Microsoft Edge [You do not have permission to view the full content of this post. Log in or register now.].
  2. Speed and Performance: In terms of speed and overall performance, Microsoft Edge is criticized for not being the best, especially when compared to other browsers [You do not have permission to view the full content of this post. Log in or register now.].
  3. Compatibility and Extensions: Microsoft Edge is not supported with older hardware specifications, and there is less availability of extensions, limiting its flexibility [You do not have permission to view the full content of this post. Log in or register now.].
  4. Privacy Concerns: Edge's major shortcoming is its privacy features. Although improvements are noted, it is still an area of concern [You do not have permission to view the full content of this post. Log in or register now.].
  5. Market Dominance: Microsoft Edge faces challenges in user adoption, with Google Chrome's dominance affecting its usage [You do not have permission to view the full content of this post. Log in or register now.].
To minimize these problems, the best choice is to keep your Windows Operating System and Microsoft Edge tuned to the latest updates.
 
Last edited:
For AI integrations in Microsoft Office (old and new for Free) similar to post#5 using add-ins, refer to the info links below concerning ChatGPT in Microsoft Excel, Powerpoint, and Word. The provided instructions are already there.
You do not have permission to view the full content of this post. Log in or register now.
You do not have permission to view the full content of this post. Log in or register now.

You do not have permission to view the full content of this post. Log in or register now.
(if the links disappear due to PHC policies, just Google it he he.)

Those familiar using add-ins/plugins/extensions in Microsoft Office can benefit from these tools.

Note:
I haven't tried them yet since my original OpenAI key had expired, but they still installed as directed. There's no option at the moment to install custom APis/endpoints. But the "GeminiAI-Excel" worked in Microsoft Office 2013.
For document writing with AI, the only option for me at the moment is using Obsidian GUI with Copilot plugin. It supports using custom OpenAI keys and endpoints, and Gemini AI. But if you don't have keys, you can still use AI using "AI Commander" plugin using your ChatGPT and Bing web API.
Good Luck.

Balikan ninyo from first post onwards para maliwanagan kayo kung paapaano gamitin yung mga apps na binanggit ko from the start.
 
Last edited:
My best browser plugin to summarize/translate videos/pages on any site: You do not have permission to view the full content of this post. Log in or register now.
Summarize YøùTùbé videos, web pages, and translate text with ChatGPT, helping you read and write in your mother tongue, all for free but limited to 20K tokens/month. Please read carefully the conditions for the ρáíd and free version for its other features I did not mention.
1709639917754.png

1709639960754.png

1709639990891.png

1709640008363.png


Glarity : an open-source ChatGPT Summary extension for YøùTùbé, Google, Twitter, and any webpage. It provides cross-language summaries to effortlessly summarize videos, searches, PDFs, emails, and webpages. It supports free side-by-side translations, email writing assistance, Web Content Q&A, and much more!*Powered by ChatGPT/OpenAI key/GPT4/Google Gemini API
(Chatgpt or using the free GPT-3.5-turbo at playground and the free Gemini Pro API is enough to accomplish the tasks.)

At the moment, I'm just using the ChatGPT Web API from my free OpenAI account to test - just enough for occasional summarization of videos.

=================================================================

Pero sa best free AI Tools site or playgrounds, maghanap na lang kayo dito sa dami ng pwedeng gamitin. Para kang bumasa ng ng unlimited threads to find one:
You do not have permission to view the full content of this post. Log in or register now.

Doon naman sa naghahanap ng ρrémíùm, unlimited access sa mga sites like Quillbot, Grammarly, DeepL, atbp. just look for the un-lock-ers sa github. No need to explain, since it is easy to search there, and the guides are provided as well. For AI detectors, any free service will do since it's just a tool to assist.
 

Attachments

Last edited:
Dyan sa You do not have permission to view the full content of this post. Log in or register now. link sa last post, a good example of a Free AI Playground that is easy to use is coze.com na nasubukan ko dahil sa isang thread dito.
You can use their shared prebuilt bots or create your own custom bot using their provided GPTs (GPT3.5-turbo-16k, GPT4-8K, GPT4-128K). You just need to login for free, but daily rate limits are controlled. Pero it is same as using ρrémíùm (for free).
Spoiler contents are visible only to Established Members.
 
Sa ngayon, di na kailangan pa sigurong mag-updates ng AI dahil freely available na sa net ang mga ito through various deployment - free, freemium ang ρáíd. Search engines na lang ang gamitin ninyo for online and offline pages and test which ones are suitable for you. Sobrang dami na kasi to mention dahil deregulated technology ito.
Basta for offline, just browse open-source sites like Github, Libhunt, various Git links, Sourceforge atbp. Join AI groups, d-cord/t-gram channels and get involved with developers to learn and use their apps and development. Same is true with online AI services. You have to start somewhere and try to improve using these tools.
 
Last edited:
Doon sa naghahanap ng free GPT GUI with assorted LLMs, check ninyo yung mga gpt4free threads dito sa forum. Isa ito sa compilation ng freely available LLM/GPT providers (w/ or w/out cøøkíés) na pwede ninyong gamitin :
You do not have permission to view the full content of this post. Log in or register now.
Pwede nyo rin gamitin ang gpt4free as an API, with no api key needed. Endpoint lang ay ok na.
Mapili lang siya ng UI sa ngayon di tulad dati. You can try using it in ChatGPTBox Chrome plugin. Nasa webstore naman yan.
Binanggit ko na rin yung iba na mas marami pa dyan related sa tgpt and python-tgpt - hanapin ninyo na lang. Yan yung portable na one-click lang may AI ka na he he, kung na-check at binasa nyo yung links sa github. Most use Phind by default kaya unlimited use siya same as in original website using phind-34B. Nasa inyong preference sa setting kung anong mga providers ang gusto niyong gamitin.
Kung gusto ninyo naman ng custom openai api key and endpoint, bisitahin ninyo itong You do not have permission to view the full content of this post. Log in or register now.. Translate nyo na lang sa English para mabasa ninyo yung infos. You just need to create an account sa github para mabigyan kayo ng api key nila. IP-based yan din kaya kayo na bahala sa huli kung gusto ninyong mag-create ng maraming keys for a specific IP-address and account.
You do not have permission to view the full content of this post. Log in or register now.: para makita niyo ang inyong usage dahil may rate limits sila per day for free usage
❗️Our system is only for internal evaluation and testing. Please use it commercially or for the public at your own risk.

For the long-term development of the project, the free API Key is limited to 150 requests/24 hours/IP&Key call frequency. That is to say, if you use multiple Keys under one IP, the total number of requests per 24 hours for all Keys cannot exceed 150; similarly, If you use a Key for multiple IPs, the number of requests for this Key per 24 hours cannot exceed 150. ( The ρáíd version API does not have this restriction )
You do not have permission to view the full content of this post. Log in or register now.: para makita ninyo yung models na gagamitin sa free api key nila
You do not have permission to view the full content of this post. Log in or register now.: ito yung kanilang api docs
May demo python script naman yan to test if you don't want to use an interface. You just need to install python or install their recommended UI like Botgem, zotero-gpt, atbp... Complete package na.
Pwede din yan gamitin sa Chatbox, NextChat, ChatAll; mga GUI na may option to use custom OpenAI api keys and endpoints (base urls). ChatGPTBox is a browser plugin that also uses custom API and Base url setting. Dyan lang sulit na kayo. Tested ko sila ngayon -still works.
In some cases, na tugma yung tagging sa app ang your pc environment, pwede nyong ilagay sa User Environmental Variables yan with a new variable name/variable value. Refer to guides here.
You do not have permission to view the full content of this post. Log in or register now.
You do not have permission to view the full content of this post. Log in or register now.
Be sure you know what you are doing in setting this, as other apps you may use may not work properly.
The guides on github and its documentation are clear and easy to follow. you just need to spend some time reading and testing to make them work. Lahat naman ng binanggit ko ay nandyan sa GH.

Good Luck.
 
Last edited:
Doon sa naghahanap ng matinong paraan to talk to documents using free options directly into Gemini (formerly Bard) or Bing, ito yung steps:
1. For Bing using either You do not have permission to view the full content of this post. Log in or register now. or You do not have permission to view the full content of this post. Log in or register now., just open the links in Edge Browser with a free account. Open your pdf at Edge browser and talk to the pdf. Instant na yan dahil may makikita kayong option for that sa taas ng page.
2. For Gemini at You do not have permission to view the full content of this post. Log in or register now.. login to your account and be sure the extension (sa settings) na Google Workspace is enable. Just open your Google Drive and upload your pdf. Make sure you copy the name since you will use it on the gemini prompt. Go back to your Gemini page and on the prompt space type @ and choose Google Drive and continue your command script on how Gemini will handle your document. (it will look like this.)
Code:
@Google Drive Summarize my <name.of file>.pdf
Sample lang yan using Google Drive. Pwede ninyong baguhin yung prompt sa kung anong gusto ninyo - structure and unstructured for adbanced users. Sa ibang Gemini features, start here:
You do not have permission to view the full content of this post. Log in or register now.

Doon pala sa familiar sa old You do not have permission to view the full content of this post. Log in or register now. 1.1.0 ni lencx, may updated version na para rin gpt4free from another thread, but you need to login sa multiple providers like You do not have permission to view the full content of this post. Log in or register now. (or You do not have permission to view the full content of this post. Log in or register now.) UI to access the AI interface for free. Try You do not have permission to view the full content of this post. Log in or register now. may installer na yan.
1712941560864.png


Kung meron naman kayong API keys sa supported providers dito, you can avail to use this commercial grade GPT app (worth 1375 pesos as of now) for free You do not have permission to view the full content of this post. Log in or register now..
You do not have permission to view the full content of this post. Log in or register now.: main site
1712942169762.png

Enjoy!
 

Attachments

Last edited:
Ito, pahabol ko na lang sa mga familiar sa Chathub browser plugin:
1712945137977.png

Ito yung binuo ko sa modified source code for v1.45.7 sa You do not have permission to view the full content of this post. Log in or register now. para at least maging ρrémíùm siya at the least. Yung chatGPT at claude ay may web access at pwedeng hanggang 6 LLM sa All-in-One. Ayos naman lahat except yung mga openLLM models sa You do not have permission to view the full content of this post. Log in or register now.. For some reason ayaw ma-detect ng web driver yung link to use the LLMs. Yung closed-source na bagong You do not have permission to view the full content of this post. Log in or register now. ay ok naman sa iabng openLLMs - pero ang free version nyan ay limited ang features. Pwede nyo naman isabay yan sa browser to compare. Mas ok pang gamitin yung unlocked na v1.45.7 he he. Doon na lang kayo mag-chat sa LMSYS site at libre naman doon.
1712945626336.png

Spoiler contents are visible only to Established Members.
Extract folder and drop at Extension page in developer mode (F12) - no need to explain he he.
 

Attachments

Last edited:
Sa post#14, kung gusto ninyong gamitin yung Google Gemini API para magamit ang inyong custom models, especially Gemini-1.5-pro. Just follow the guide You do not have permission to view the full content of this post. Log in or register now. and visit the You do not have permission to view the full content of this post. Log in or register now. sa github. It's just a simple python app. Install the requirements and edit the code if you want the new Gemini version, or else ay v1.0 ang default LLM na magagamit ninyo.
You do not have permission to view the full content of this post. Log in or register now.
You do not have permission to view the full content of this post. Log in or register now.
You do not have permission to view the full content of this post. Log in or register now.
You do not have permission to view the full content of this post. Log in or register now.
You do not have permission to view the full content of this post. Log in or register now.
You do not have permission to view the full content of this post. Log in or register now.
....Marami pang ibang apps bukod dyan. But i'm sure, at least one will do he he.
 
Last edited:
Dyan sa last post, the best (chat with doucments like pdf) app to test for accurate results isYou do not have permission to view the full content of this post. Log in or register now. since ito yung features nya:

Under the Hood​

This system leverages the power of cutting-edge AI models to understand your PDFs and answer your questions:

  • Chunking: LangChain splits your PDF into manageable sections for efficient processing.
  • Embedding: Each section receives a unique representation using "GeminiEmbeddingFunction" for better understanding.
  • Storage and Search: ChromaDB stores these embeddings, enabling rapid retrieval of relevant information.
  • Query Expansion: "models/text-bison-001" expands your query to consider various ways it might be phrased.
  • Cross-Encoder Re-ranking: "cross-encoder/ms-marco-MiniLM-L-6-v2" prioritizes the most relevant answers.
  • Response Generation: "gemini-pro" synthesizes the information into a clear and concise response.
Kung gusto ninyo ng commercial grade na similar app with extended features compared sa #3 (with builtin RAG) for FREE, use this: You do not have permission to view the full content of this post. Log in or register now.. It's either you deploy the app or just go to their You do not have permission to view the full content of this post. Log in or register now. to download and install their app. Builtin na yung ibang AI services and extra storage except sa API key ninyo sa external LLM service like Gemini, OpenAI, Mistral, etc. or LLM you run locally like Ollama, jan.ai, etc.) Pwede rin cloud-based kung gusto ninyo. High grade results ang makukuha ninyo dyan kaysa sa mga free online services na limited ang memory to store and analyze data, walang chunking and embedding, etc. Kulang-kulang ang ibibigay nyang infromation kundi nakadepende lang sa LLM/GPT internal capabilities. Maganda ito for deeper research - and it's free to use and run locally. It's a must-have for students. (Nasa feature request pa yung paggamit ng gemini-1.5-pro sa ngayon.)
1713513073445.png
 

Attachments

Doon naman sa naghahanap ng AI na merong option to input unlimited knowledge for free to create their custom AI on any preferred specialty for a start, go here:
You do not have permission to view the full content of this post. Log in or register now.
1713798041924.png

Kapain nyo na lang at di naman mahirap kung sanay na kayong gumamit ng chatbots like OpenAI. The interface is user-friendly. Create your AI, input knowledge and make it learn and do the same again ang again adding enough data as you want, then talk to it. Free version uses You do not have permission to view the full content of this post. Log in or register now. LLM model which is decent - maximum contextext size (input + output) of 32k. Mas ok gamitin kaysa GPT-3.5-turbo na 4k lang!
If you want to deploy it somewhere using your own models or run it locally, go here:
You do not have permission to view the full content of this post. Log in or register now.
Please read the info about the AI, its perks and its limitations to maximize its use.
Para mapakinabangan ninyo siya, you need to input as much data to train and make it an expert on the field you want it to excel - simple!
Mas ok ito kaysa gumamit lang ng plain GPT or LLM na nakadepende lang sa kung anong laman na pinasok sa model/s para sumagot.
 

Attachments

Back
Top