rming/dify-openai-apis

OpenAI-compatible APIs for Dify platform services.

English | 中文

dify-openai-apis

Description

OpenAI-compatible APIs for Dify platform services.
This crate provides a set of APIs that are compatible with OpenAI's GPT-3 API, and can be used to interact with Dify's platform services and tools.

Note: The app currently does not support OpenAI's Legacy Completions API. Please use the Chat Completion API instead.

Config

Configurations can be set via .env file or environment variables:

• HOST: The host to bind the server to. Default: 127.0.0.1
• PORT: The port to bind the server to. Default: 3000
• DIFY_BASE_URL: The base URL of Dify's API. Default: https://api.dify.ai
• DIFY_API_KEY: Your API key for Dify's API. Default: your_api_key
• DIFY_TIMEOUT: The timeout for requests to Dify's API. Default: 10
• WORKERS_NUM: The number of worker threads to use. Default: 4
• RUST_LOG: The log level for the server. Default: error

Note:

• DIFY_API_KEY is the default API key. If a user provides an API key via Bearer Token when requesting the API /v1/chat/completions, it will override this default value.
• RUST_LOG is the log level, with a default value of error, meaning only error logs will be output. If you want to debug, it is recommended to set it to debug or trace.

Install

Please download the precompiled binary from : Release page

You can also install it using the cargo command.

# require cargo installed
cargo install dify-openai-apis

Usage

To start the server, run:

# require cargo bin directory in PATH
# export PATH=$HOME/.cargo/bin:$PATH
dify-openai-apis

dify-openai-apis's Issues

A dockerfile and a Compose to launch it

Hi,

please find a way to launch it on docker :

FROM rust:latest
WORKDIR /usr/bin
RUN apk add musl-dev
RUN cargo install dify-openai-apis
CMD ["dify-openai-apis"]

to build the image:
docker build --pull --rm -f "dockerfile.dockerfile" -t difyopenaiapis:0.1.8 "."

and a compose.yaml to launch it:

  difyopenaiapis:
    image: "difyopenaiapis:0.1.8"
    container_name: difyopenaiapis
    environment:
      HOST: 0.0.0.0
      PORT: 3000
      DIFY_BASE_URL: "http://dify.api.to"
      DIFY_API_KEY: "app-******"
      DIFY_TIMEOUT: 20
      WORKERS_NUM: 4
      RUST_LOG: "debug"
    ports:
      - '8080:3000'
    restart: "always"

Regards

OpenAI compatible servers / APIs | Continue.dev

Hello.
Thanks you for your work.

I have try to use the extension : https://docs.continue.dev/reference/Model%20Providers/openai

Normally, is OpenAI compatible servers / APIs.

I try everything (connection refused and 404 not found) to connect to this extension.

Do you know why ? Can you help me please ?

When i start "dify-openai-apis" i didn't have any message or logs into my terminal.

## Issue: Dependency Conflict with `env_logger` ### Description When trying to install the `dify-openai-apis` package, I encountered a dependency conflict with the `env_logger` crate. The error message is as follows:

Issue: Dependency Conflict with env_logger

Description

When trying to install the dify-openai-apis package, I encountered a dependency conflict with the env_logger crate. The error message is as follows:

Error occurred when using this API in some applications.

I found that when I call this API interface on front-end pages like chatgpt-next-web, it works fine. But when I call the same interface in some applications, such as Qchatgpt and chatgpt on WeChat, it gives an error instead of returning the expected output. I'd like to know if the program hasn't fully implemented OpenAI's request format or if there's an issue with my configuration.

return object is always in text format instead of application/json

Hi,

seems like the return object is always in text format instead of application/json.

Any way to customise this?

Thanks for your help

Regards

Mat