All committers have signed the CLA.

cc @CH3CHO

Ⅰ. Describe what this PR did

Support baichuan ai llm, api documentation (https://platform.baichuan-ai.com/docs/api)

Ⅱ. Does this pull request fix one issue?

fix #952

Ⅲ. Why don't you add test cases (unit test/integration test)?

Ⅳ. Describe how to verify it

envoy.yaml:

admin:
  address:
    socket_address:
      protocol: TCP
      address: 0.0.0.0
      port_value: 9901
static_resources:
  listeners:
    - name: listener_0
      address:
        socket_address:
          protocol: TCP
          address: 0.0.0.0
          port_value: 10000
      filter_chains:
        - filters:
            - name: envoy.filters.network.http_connection_manager
              typed_config:
                "@type": type.googleapis.com/envoy.extensions.filters.network.http_connection_manager.v3.HttpConnectionManager
                scheme_header_transformation:
                  scheme_to_overwrite: https
                stat_prefix: ingress_http
                # Output envoy logs to stdout
                access_log:
                  - name: envoy.access_loggers.stdout
                    typed_config:
                      "@type": type.googleapis.com/envoy.extensions.access_loggers.stream.v3.StdoutAccessLog
                # Modify as required
                route_config:
                  name: local_route
                  virtual_hosts:
                    - name: local_service
                      domains: ["*"]
                      routes:
                        - match:
                            prefix: "/"
                          route:
                            cluster: baichuan
                            timeout: 300s
                http_filters:
                  - name: baichuan
                    typed_config:
                      "@type": type.googleapis.com/udpa.type.v1.TypedStruct
                      type_url: type.googleapis.com/envoy.extensions.filters.http.wasm.v3.Wasm
                      value:
                        config:
                          name: baichuan
                          vm_config:
                            runtime: envoy.wasm.runtime.v8
                            code:
                              local:
                                filename: /etc/envoy/main.wasm
                          configuration:
                            "@type": "type.googleapis.com/google.protobuf.StringValue"
                            value: |
                              {
                                "provider": {
                                  "type": "baichuan",
                                  "apiTokens": [
                                    "sk-xxxxxx"
                                  ],
                                  "withSearchEnhance":false
                                }
                              }

                  - name: envoy.filters.http.router
  clusters:
    - name: baichuan
      connect_timeout: 30s
      type: LOGICAL_DNS
      dns_lookup_family: V4_ONLY
      lb_policy: ROUND_ROBIN
      load_assignment:
        cluster_name: baichuan
        endpoints:
          - lb_endpoints:
              - endpoint:
                  address:
                    socket_address:
                      address: api.baichuan-ai.com
                      port_value: 443
      transport_socket:
        name: envoy.transport_sockets.tls
        typed_config:
          "@type": type.googleapis.com/envoy.extensions.transport_sockets.tls.v3.UpstreamTlsContext
          "sni": "api.baichuan-ai.com"

Request:

curl "http://localhost:10000/v1/chat/completions"  -H "Content-Type: application/json" -d '{
  "model": "Baichuan2-Turbo",            
  "messages": [                                                     
    {                        
      "role": "user",                
      "content": "你好，你是谁？"
    }                                                                                 
  ]                                                 
}'  

Response:

{
   "id":"chatcmpl-Mcdc9015KFRHoSV",
   "object":"chat.completion",
   "created":1716190037,
   "model":"Baichuan2-Turbo",
   "choices":[
      {
         "index":0,
         "message":{
            "role":"assistant",
            "content":"你好！我是百川大模型，是由百川智能的工程师们创造的大语言模型，我可以和人类进行自然交流、解答问题、协助创作，帮助大众轻松、普惠的获得世界知识和专业服务。如果你有任何问题，可以随时向我提问。"
         },
         "finish_reason":"stop"
      }
   ],
   "usage":{
      "prompt_tokens":6,
      "completion_tokens":52,
      "total_tokens":58
   }
}

Ⅴ. Special notes for reviews

在baichuan ai的api文档中，我发现有一个api parameter是with_search_enhance， 这是一个bool类型的参数，每次打开需要消耗额外的token，我认为该参数只需要从context json中获取即可，故没有添加到文档和代码中。

疑似api token泄露