Linux 软件免费装
Banner图

S2B AI Assistant - ChatBot, ChatGPT, OpenAI, Content & Image Generator

开发者 oc3dots
更新时间 2024年11月12日 04:02
PHP版本: 7.0 及以上
WordPress版本: 6.7
版权: GPLv2 or later
版权网址: 版权信息

标签

chatbot AI content generator openai gpt

下载

1.1.2 1.3.2 1.3.3 1.4.2 1.3.1 1.2.1 1.4.1 1.5.1 1.5.4 1.5.5 1.5.8 1.2.2 1.5.2 1.5.9 1.6.2 1.5.3 1.6.1 1.6.4 1.6.3

详情介绍:

Develop multiple AI chatbots with different styles and behaviors on different pages of your website, including using content-aware functionality OpenAI Assistant API and RAG. You can personalize the appearance of the chatbot: colors, styles, text; Personalize its position on the screen, window size, chatbot behavior by choosing: model, instruction, temperature, tokens, etc. You have the option to choose whether the chatbot will be visible only to registered visitors or not. The plugin allows you to update models directly from OpenAI and independently choose the model to use. You can record and save chat conversations between users and the chatbot. Additionally, it allows you to create/modify content and images as well as generate code using the ChatGPT API. The API provides access to large language models. With this plugin, you can not only edit and generate code, but also perform various content manipulations using OpenAI ChatGPT . You can use plugin for generate images using Dall-E2 and Dall-E3 AI systems. One of the features is the ability to create a database of instructions, which you can easily refer back to whenever needed. Moreover, you have the flexibility to choose from a wide range of models available in the OpenAI ChatBot API, ensuring that your requests are tailored to your specific needs. S2B AI Assistant is plugin for WordPress powered by any model you can choose from OpenAI API platform https://platform.openai.com/docs/models . You can log conversations between AI chatbot and visitors of your website. Features

安装:

Quick setup: -Open account at OpenAI and get API key -Go to /wp-admin/admin.php?page=s2baia_settings page of this plugin. Input copied API key in the 'Open AI Key:' field of the ChatGPT tab. You can copy API key on api keys page -Switch to Models tab. Click on the 'Refresh from OpenAI' button. It updates models from OpenAI server. Select Models which you want to use. Select the Edit checkbox for models that will be used with chatbots and text manipulation. Select the Expert checkbox for models to be used in the Expert playground. Finally click the Save button. You can now use the S2B AI Assistant plugin. -You can customize the position, appearance, behavior of the chatbot on the ChatBot configuration page /wp-admin/admin.php?page=s2baia_chatbot. On this page, you can create many chatbots that differ in their appearance, position and behavior. -To get the chatbot operational, simply insert the shortcode [s2baia_chatbot] to any post or page -If you want to use different chatbots on different pages, add a shortcode in the format [s2baia_chatbot bot_id=generated_hashcode] to any page or post. -To add content aware feature using OpenAI Assistant API you need to go to Chatbot page, then click on Assistant API and follows 3 steps: 1.Upload file that will be used as knowledge base by ChatGPT. 2.Create new Assistant by filling instruction and selecting model. For details see below in Content aware feature section below. 3.Add shortcode [s2baia_chatbot bot_id=assistant] to any page, to display Assistant. We tested this feature with different models and found that the best result are when using gpt-4-turbo-preview, gpt-4 and gpt-4-turbo models. Please read this and this articles for detailed information. -Additionally you can create many Assistants inside OpenAI Assistant dashboard and link them with our plugin. Read this article on how to do it. Detailed setup and configuration: Initial configuration.
  1. Go to Settings page /wp-admin/admin.php?page=s2baia_settings. In the ChatGPT tab fill your API key in the 'Open AI Key:' . You can generate API key on this page: https://platform.openai.com/account/api-keys
  2. You can fill other fields on this tab or leave them by default.
Chat GPT Models configuration. 3.Switch to Models tab. Click on the 'Refresh from OpenAI' button. It updates models from OpenAI server. 4.Select Models which you want to use in different functions of our plugin. Finally click 'Save' button. Select the Edit checkbox for models that will be used with chatbots and text manipulation. Select the Expert checkbox for models to be used in the Expert playground. Remember that not all models are suitable for chatbots and word processing. That means you can get error response like this one 'This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?' when you try to use them. As of today's date (July 2024) we recommend to select gpt-3.5-turbo, gpt-3.5-turbo-16k-0613, gpt-4 versions, gpt-4-turbo-preview and gpt-4-turbo versions. You can play with selection and deselection models to find best that fit to your needs. For more information about selecting models read AI Chatbot setup. Open Chatbot menu page in wp-admin. You can see such tabs: General, Styles, Chatbots,Assitant API, Assistants, Logs and Support. On General, Styles You can customize default behavior, appearance and view of chatbots. In particular you can select ChatBot position, ChatBot size, model, colors of chatbot's elements etc. If you want to use different chatbots on different pages then create bot in Chatbots tab and then put shortcode in format [s2baia_chatbot bot_id=automatically_generated_hashcode] into any page or post. In addition, the plugin allows you to create AI Assistants using the Assistants API. You can create Assistants in Assistant API and or in Assitants tabs. Read below on how to do this. Notice! Chatbot view parameters like position, size, colors are affected by caching. When you found that you have changed chatbot parameters, but view has not changed then try to clear cache then reload page. Content aware feature for AI chatbot. OpenAI introduced new Assistant API which allows it automatically to parse and chunk uploaded documents, to create and to store the embeddings, and use both vector and keyword search to retrieve relevant content to answer user queries. We implemented File Search API feature in our pugin. Before using this on your website, you should remember some important tips: 1.It is Beta feature and not yet tested carefully. Thus it can cause unpredicted behavior. Therefore, we cannot guarantee the chatbot's responses. 2.OpenAI charges additionally besides used conversational tokens. At the moment of release version 1.5.8 of this plugin it costs $0.10 / GB of vector-storage per day (1 GB free) + used tokens during conversation. Please observe to be informed about pricing updates. 3.The effectiveness and accuracy of the bot's responses depends on the system instructions provided and the models used in the prompts. For detailed information please read article To setup content aware chatbot using Assistant API you need to open page Chatbot and select Tab "Assistant API". Then you need to perform 3 steps: 1.Upload file that will be used as knowledge base by ChatGPT. 2.Create new Assistant by filling instruction, selecting model and timeout. 3.Add the shortcode [s2baia_chatbot bot_id="assistant"] to any page you want. Additionally you can create many assistants manually in the Assistants OpenAI dashboard and link them to our plugin. For this you need to go to Assistants OpenAI dashboard and create assistants there. Then copy ID of created assistant. After that, you need to create a new assistant in the plugin Assistants tab.Finally, paste the ID in the Assistant ID field. Alternatively you can use Completion API to create content aware chatbot along with RAG by embedding website content. Starting from version 1.6.4 we added Retrieval-augmented generation (RAG) support to chatbot. So you can use external vector database API and use it in pair with Embedding API and with Chat Completion API endpoint to build content aware chatbot. With the right configuration you can have such powerful chatbot like Assistants but with cheaper price. How RAG feature works? Plugin allows to upload content of selected posts or pages from your website into external vector database using their API and generate search database. This vector database is able to do semantic search inside uploaded content. You can attach vector database to chatbot. When visitors ask questions, this chatbot sends a query to the vector database instead of sending it directly to ChatGPT. The vector database returns content that matches the user's query back to your site. The content found by the vector database is then sent to ChatGPT along with the user's query. If the vector database does not find any information that is related to the user's request, you have the option to stop sending the request to ChatGPT and return a message informing the client about the missing content. This way, you can achieve 2 goals:
  1. Limit sending any requests to ChatGPT that are not related to website content.
  2. Only send ChatGPT content from your website that is relevant to the user's request. This allows you to reduce the cost of using the Chat Completion API. For more details of how RAG works see this article. Also you can read this page to get idea on how plugin's RAG feature works.
RAG setup. 1.Open account at pinecone. Create empty Index there, set the dimension to 1536, and choose cosine for the metric. 2. Get your API KEY from https://www.pinecone.io/ 3.Open RAG wp-admin page of S2B AI Assistant 4.Fill field 'Pinecone API Key:' with API key 5.Click Sync indexes button. It should add your Pinecode Index in Pinecode Index field. Select it in dropdown box. 6.Select Embedding model with 1536 dimension. 7.Select other parameter on this page and click Save button. 8.Go to Pinecone tab and select content pages or posts from left list and add them into right list. 9.Open ChatBot wp-admin page of S2B AI Assistant plugin. 10.Go to 'Chatbots' tab and create new chatbot or select some among created before. 11.Make checked Use embedding (RAG) checkbox and select pinecone in Select index (RAG) field in chatbot configuration. 12.Click Save button 13.Put chatbot's shortcode to any page or post on your website 14.Try to use More detailed instruction on how to set up RAG feature you can fin on this page. Image generation setup. Image generation feature requires only API key. It is ready to use by default. You can configure generation options on the Image Generation tab. On the same tab you can generate and store new images using Dall-e-2 and Dall-e-3 models. Instruction setup. Select page types you want to display metabox of the S2B AI assistant plugin at the configuration page. Select models you want to use in the S2B AI assistant plugin. The S2B AI assistant plugin enables you to create and manage instructions for ChatGPT. You can store these instructions in a database and use them in your requests. To access the instructions, simply switch to the "Instructions" tab. From there, you can add, edit, delete, enable, or disable instructions. Additionally, you can search for specific instructions by entering text in the "Search Instructions" input box. For additional instructions and ideas, please visit our page or OpenAI best practice page Post types setup. The S2B AI Assistant plugin is accessible by default in the metabox displayed beneath the edit area for two post and page types. However, if desired, you have the option to enable it on other post types' edit pages. To do so, navigate to the General setup tab and select the desired post types.

屏幕截图:

  • Models settings
  • Instructions settings
  • Edit/Generate content in post/page metabox of edit screen
  • Expert tab allows to to customize request to Chat completion API
  • Chatbot minimized window
  • Chat bot maximized window
  • Chat bot styles configuration
  • Chat bot Assistant API Configuration
  • Chat bot discussion log
  • Create multiple chatbots with different styles and behavior
  • Chatbot configuration page
  • Image generation page
  • Store generated Image into Media Library
  • Modalless option of chat bot

常见问题:

How many different chat bots can I create?

As many as you want. Each chatbot can have different position, size, colors, behavior and other elements.

Can I customize the appearance of the chatbot?

Yes. You can change position, size, colors, behavior of each chatbot separately in Chatbots and Assistants tabs of configuration page.

Which difference between chatbots and assistants?

Actually they are two different types of chatbot. Assistants use OpenAI Assistant API, while Chatbots use OpenAI completion API to answer visitor's questions. Using Assistant API you can upload file to add additional information to chatbot's knowledge database. This allows you to create content aware chatbot.

How can I change icon of chatbot

First upload icon to Media Library. Then copy its url and paste it into "Url of chatbot picture:" field.

Which OpenAI models does the plugin use?

Any model that is accessible for your OpenAI account. You just need to open Settings page and switch to Models tab. After click 'Refresh from OpenAI'. All models will be attached to plugin. Then just select models you want to use.

How does S2B AI Assistant handle image generation?

S2B AI Assistant leverages the DALL-E model for image generation. You can specify prompts in the command line within the plugin, and S2B AI Assistant will generate unique images, logos, banners, and more, requiring no design skills from the user.

The S2B AI Assistant is NOT working in the front end.

The primary cause for this issue is often incorrect theme coding and jQuery being loaded from an external source. WordPress core already includes jQuery, and as per WordPress standards, it should be included using wp_enqueue_script. https://developer.wordpress.org/reference/functions/wp_enqueue_script/ . Verify if this is happening in your theme.

更新日志:

1.6.4 1.6.3 1.6.2 1.6.1 1.5.9 1.5.8 1.5.5 1.5.4 1.5.3 1.5.2 1.5.1 1.4.2 1.4.1 1.3.3 1.3.2 1.3.1 1.2.2 1.2.1 1.1.2 1.1.1 1.0.1 1.0.0