summaryrefslogtreecommitdiffstats
path: root/g4f/Provider/Bing.py (unfollow)
Commit message (Collapse)AuthorFilesLines
2024-01-21Improve testsHeiner Lohaus1-8/+5
2024-01-14Refactor code with AIHeiner Lohaus1-104/+126
Add doctypes to many functions Add file upload for text files Add alternative url to FreeChatgpt Add webp to allowed image types
2024-01-13Fix process_image in BingHeiner Lohaus1-10/+14
Add ImageResponse to Bing Fix cursor styling in gui
2024-01-13Support upload image in guiHeiner Lohaus1-13/+5
Add image upload to OpenaiChat Add image response to OpenaiChat Improve ChatGPT Plus Support Remove unused requirements
2024-01-12Add publish-to-pypi workflowHeiner Lohaus1-1/+5
Improve gui frontend Fix web search in bing
2024-01-10Fix bing stream funcHeiner Lohaus1-1/+1
2024-01-10Added timeout to Bing (#1438)0.1.9.10Eikosa1-8/+9
Co-authored-by: H Lohaus <hlohaus@users.noreply.github.com>
2024-01-10Add create images to Bing (#1426)H Lohaus1-248/+67
Add create images from Bing Add FreeChatgpt Provider Fix Bard Provider
2023-12-25Support Python 3.8Heiner Lohaus1-2/+2
2023-12-21Update Bing.pynullstreak1-4/+12
2023-12-19Bing: add parameter to enable/disable web search (#1360)nullstreak1-4/+8
Web search is disabled by default and can be enabled by passing `web_search = True`
2023-12-18Fix Bing provider Cookie issue 2eminemkun1-2/+7
2023-12-16Fix Bing provider Cookie issueeminemkun1-2/+1
2023-12-06Add selenium to dockerfileHeiner Lohaus1-2/+5
Load model and provider list in gui Remove needs_auth in HuggingChat Add default model and login url in gui
2023-11-04Update Bing.py - Removed unnecessary "await" statements that could potentially lead to errorsLuneye1-2/+2
2023-10-27Update config supports_message_historyHeiner Lohaus1-3/+3
2023-10-24Indicated support of message history in Bing.pyLuneye1-0/+1
2023-10-23Bugfix Bing.py - Resolved Issues with system prompt, Bing personalities and enabled all supported user requestsLuneye1-47/+45
I used this repository (https://github.com/waylaidwanderer/node-chatgpt-api/) as a reference to fix all the bugs related to Bing "personality." I included all the required fields in the allowedMessageTypes and optionsSets (as well as sliceIds) to allow it to respond to any requests it actually supports. Will also finish the code to fully implement the image generation functionality.
2023-10-23'Refactored by Sourcery' (#1125)ⲘrṨhส∂ow1-42/+48
Co-authored-by: Sourcery AI <>
2023-10-22Major Update for Bing - Supports latest bundle version and image analysisLuneye1-42/+222
Here it is, a much-needed update to this service which offers numerous functionalities that the old code was unable to deliver to us. As you may know, ChatGPT Plus subscribers now have the opportunity to request image analysis directly from GPT within the chat bar. Bing has also integrated this feature into its chatbot. With this new code, you can now provide an image using a data URI, with all the following supported extensions: jpg, jpeg, png, and gif! **What is a data URI and how can I provide an image to Bing?** Just to clarify, a data URI is a method for encoding data directly into a URI (Uniform Resource Identifier). It is typically used for embedding small data objects like images, text, or other resources within web pages or documents. Data URIs are widely used in web applications. To provide an image from your desktop and retrieve it as a data URI, you can use this code: [GitHub link](https://gist.github.com/jsocol/1089733). Now, here is a code snippet you can use to provide images to Bing: ```python import g4f provider = g4f.Provider.Bing user_message = [{"role": "user", "content": "Hi, describe this image."}] response = g4f.ChatCompletion.create( model = g4f.models.gpt_4, provider = g4f.provider, # Corrected the provider value messages = user_message, stream = True, image = "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQEASABIAAD/4RiSRXhpZgAASUkqAAg..." # Insert your full data URI image here ) for message in response: print(message, flush=True, end='') ``` If you don't want to analyze the image, just do not specify the image parameter. Regarding the implementation, the image is preprocessed within the Bing.py code, which can be resource-intensive for a server-side implementation. When using the Bing chatbot in your web browser, the image is preprocessed on your computer before being sent to the server. This preprocessing includes tasks like image rotation and compression. Although this implementation works, it would be more efficient to delegate image preprocessing to the client as it happens in reality. I will try to provide a JavaScript code for that at a later time. As you saw, I did mention in the title that it is in Beta. The way the code is written, Bing can sometimes mess up its answers. Indeed, Bing does not really stream its responses as the other providers do. Bing sends its answers like this on each iteration: "Hi," "Hi, this," "Hi, this is," "Hi, this is Bing." Instead of sending each segment one at a time, it already adds them on each iteration. So, to simulate a normal streaming response, other contributors made the code wait for the next iteration to retrieve the newer segments and yield them. However, this method ignores something that Bing does. Bing processes its responses in a markdown detector, which searches for links while the AI answers. If it finds a link, it saves it and waits until the AI finishes its answer to put all the found links at the very end of the answer. So if the AI is writing a link, but then on the next iteration, it finishes writing this link, it will then be deleted from the answer and appear later at the very end. Example: "Here is your link reference [" "Here is your link reference [^" "Here is your link reference [^1" "Here is your link reference [^1^" And then the response would get stuck there because the markdown detector would have deleted this link reference in the next response and waited until the AI is finished to put it at the very end. For this reason, I am working on an update to anticipate the markdown detector. So please, if you guys notice any bugs with this new implementation, I would greatly appreciate it if you could report them on the issue tab of this repo. Thanks in advance, and I hope that all these explanations were clear to you!
2023-10-10remove unused import in Bing.pyCommenter1233211-1/+0
2023-10-09Add proxy support to all providersHeiner Lohaus1-14/+17
2023-10-06Fix timeout in create_asyncHeiner Lohaus1-1/+1
2023-10-06~abc1-2/+4
2023-10-05Add AiAsk, Chatgpt4Online, ChatgptDemoHeiner Lohaus1-58/+31
and ChatgptX Provider Fix Bing, Liaobots and ChatgptAi Provider Add "gpt_35_long" model and custom timeout
2023-10-04~ | g4f v-0.1.4.8 - Fixed `g4f.Provider.Bing`abc1-8/+34
implemented new "X-Sydney-EncryptedConversationSignature" found in headers from "turing/conversation/create"
2023-10-02Bing Updates:Heiner Lohaus1-33/+45
Add retry create conversation Removed get_cookies fallback Add creative tone parameter
2023-10-02Add Phind ProviderHeiner Lohaus1-9/+13
Add release_curl in url_cffi requets Support create image response in Bing
2023-09-05Fix imports in BingHeiner Lohaus1-16/+7
2023-09-05Add to many provider async and stream support, Fix Ails, AItianhu, ChatgptAi, ChatgptLogin Provider, Add fallback cookies to Bing, Improve OpenaiChat ProviderHeiner Lohaus1-17/+6
2023-09-04Join the messageshs_junxiang1-4/+1
A better approach is to use the `.join()` method of strings, which reduces string concatenation operations and improves performance. Additionally, using formatted strings (f-strings) makes the code cleaner and more readable.
2023-09-03type hintsmsi-JunXiang1-3/+11
Use `from __future__ import annotations avoid `dict` and `list` cause "TypeErro: 'type' object is not subscriptable". Refer to the following Stack Overflow discussions for more information: 1. https://stackoverflow.com/questions/75202610/typeerror-type-object-is-not-subscriptable-python 2. https://stackoverflow.com/questions/59101121/type-hint-for-a-dict-gives-typeerror-type-object-is-not-subscriptable
2023-09-01Set working=True in Liaobots, Fix bing provider, Update readmeHeiner Lohaus1-19/+2
2023-08-28~ | v-0.0.2.6abc1-25/+25
2023-08-28Update Bing.pyLuneye1-7/+7
Fixed some errors in my previously precipitated commit.
2023-08-28Update Bing.pyLuneye1-53/+45
Added support the async function Will implement proper cookie retrieval later but Bing is working for now
2023-08-28Add async support for H2oHeiner Lohaus1-14/+6
Add format_prompt helper Fix create_completion in AsyncGeneratorProvider Move get_cookies from constructor to function Add ow HuggingChat implement Remove need auth form Liabots Add staic cache for access_token in OpenaiChat Add OpenAssistant provider Support stream and async in You Support async and add userId in Yqcloud Add log_time module
2023-08-27Update Bing.py Luneye1-46/+76
Removed unnecessary check that could prematurely stop the AI's response while answering
2023-08-27~ | code stylingabc1-17/+10
2023-08-25Add OpenaiChat and Hugchat ProviderHeiner Lohaus1-58/+28
Add tests for providers with auth Improve async support / 2x faster Shared get_cookies by domain function
2023-08-23Add create_async methodHeiner Lohaus1-19/+39
2023-08-21Fix bing providerHeiner Lohaus1-261/+203
2023-08-17~ | major refractoring | v0.0.2.0abc1-3/+3
2023-08-14refactor: refactor providerMIDORIBIN1-0/+362
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-10 12:26:30 +0100