feat: support deepseek ai model

[goooogoooo]

Ⅰ. Describe what this PR did

Support DeepSeek ai model, api documentation: https://platform.deepseek.com/api-docs/zh-cn/

Ⅱ. Does this pull request fix one issue?

fixes #961

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: deepseek
                            timeout: 300s
                http_filters:
                  - name: wasmtest
                    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: wasmtest
                          vm_config:
                            runtime: envoy.wasm.runtime.v8
                            code:
                              local:
                                filename: /etc/envoy/plugin.wasm
                          configuration:
                            "@type": "type.googleapis.com/google.protobuf.StringValue"
                            value: |
                              {
                                "provider": {
                                  "type": "deepseek",
                                  "apiTokens": [
                                    "******"
                                  ]
                                }
                              }
                  - name: envoy.filters.http.router
  clusters:
    - name: httpbin
      connect_timeout: 30s
      type: LOGICAL_DNS
      # Comment out the following line to test on v6 networks
      dns_lookup_family: V4_ONLY
      lb_policy: ROUND_ROBIN
      load_assignment:
        cluster_name: httpbin
        endpoints:
          - lb_endpoints:
              - endpoint:
                  address:
                    socket_address:
                      address: httpbin
                      port_value: 80
    - name: deepseek
      connect_timeout: 30s
      type: LOGICAL_DNS
      dns_lookup_family: V4_ONLY
      lb_policy: ROUND_ROBIN
      load_assignment:
        cluster_name: deepseek
        endpoints:
          - lb_endpoints:
              - endpoint:
                  address:
                    socket_address:
                      address: api.deepseek.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.deepseek.com"

• Use deepseek-chat model

Request:

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

Response:

{
	"id": "b8720950-569d-4413-b2cf-436e2729db00",
	"choices": [{
		"index": 0,
		"message": {
			"content": "你好！我是一个人工智能助手，专门设计来回答问题、提供信息和帮助解决问题。如果你有任何疑问或需要帮助，请随时告诉我。",
			"role": "assistant"
		},
		"finish_reason": "stop",
		"logprobs": null
	}],
	"created": 1716370331,
	"model": "deepseek-chat",
	"system_fingerprint": "fp_1d4b677f33",
	"object": "chat.completion",
	"usage": {
		"prompt_tokens": 13,
		"completion_tokens": 31,
		"total_tokens": 44
	}
}

• Use deepseek-coder deepseek-coder

Request:

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

Response:

{
	"id": "f3b071c1-e1ad-4590-b0d7-afb1eb1bf529",
	"choices": [{
		"index": 0,
		"message": {
			"content": "你好！我是DeepSeek Coder，由中国的深度求索（DeepSeek）公司开发的编程智能助手。我专门用来回答计算机科学相关的问题。如果你有任何编程或计算机科学相关的问题，欢迎随时向我提问。",
			"role": "assistant"
		},
		"finish_reason": "stop",
		"logprobs": null
	}],
	"created": 1716370341,
	"model": "deepseek-coder",
	"system_fingerprint": "fp_ded2115e5a",
	"object": "chat.completion",
	"usage": {
		"prompt_tokens": 18,
		"completion_tokens": 62,
		"total_tokens": 80
	}
}

Ⅴ. Special notes for reviews

[CLAassistant]

All committers have signed the CLA.

[CH3CHO]

LGTM. Thanks.