Add cohere embedding for ai-cache

[ayanami-desu]

Ⅰ. Describe what this PR did

Ⅱ. Does this pull request fix one issue?

fixes #1449

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

Ⅳ. Describe how to verify it

docker-compose.yml

services:
  envoy:
    image: higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/gateway:v2.0.2
    entrypoint: /usr/local/bin/envoy
    command: -c /etc/envoy/envoy.yaml --component-log-level wasm:debug
    networks:
    - wasmtest
    ports:
    - "10000:10000"
    volumes:
    - ./envoy.yaml:/etc/envoy/envoy.yaml
    - ./main.wasm:/etc/envoy/main.wasm
    - ./ai.wasm:/etc/envoy/ai.wasm

networks:
  wasmtest: {}

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/ai.wasm
                          configuration:
                            "@type": "type.googleapis.com/google.protobuf.StringValue"
                            value: |
                              {
                                "provider": {
                                  "type": "deepseek",
                                  "apiTokens": [
                                    "sk-"
                                  ]
                                }
                              }

                  - name: cache
                    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: cache
                          vm_config:
                            runtime: envoy.wasm.runtime.v8
                            code:
                              local:
                                filename: /etc/envoy/main.wasm
                          configuration:
                            "@type": "type.googleapis.com/google.protobuf.StringValue"
                            value: |
                              {
                                "embedding": {
                                  "type": "cohere",
                                  "serviceName": "cohere.dns",
                                  "apiKey": ""
                                },
                                "vector": {
                                  "type": "dashvector",
                                  "serviceName": "dashvector.dns",
                                  "collectionID": "first",
                                  "serviceHost": "vrs-cn-.dashvector.cn-hangzhou.aliyuncs.com",
                                  "apiKey": "sk-"
                                },
                                "cache": {
                                  "serviceName": "",
                                  "type": ""
                                }
                              }
                  - name: envoy.filters.http.router
                    typed_config:
                      "@type": type.googleapis.com/envoy.extensions.filters.http.router.v3.Router
  clusters:
   - 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"

   - name: outbound|443||cohere.dns
     connect_timeout: 30s
     type: LOGICAL_DNS
     dns_lookup_family: V4_ONLY
     lb_policy: ROUND_ROBIN
     load_assignment:
       cluster_name: outbound|443||cohere.dns
       endpoints:
         - lb_endpoints:
             - endpoint:
                 address:
                   socket_address:
                     address: api.cohere.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.cohere.com"

   - name: outbound|443||dashvector.dns
     connect_timeout: 30s
     type: LOGICAL_DNS
     dns_lookup_family: V4_ONLY
     lb_policy: ROUND_ROBIN
     load_assignment:
       cluster_name: outbound|443||dashvector.dns
       endpoints:
         - lb_endpoints:
             - endpoint:
                 address:
                   socket_address:
                     address: vrs-cn-.dashvector.cn-hangzhou.aliyuncs.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": "vrs-cn-.dashvector.cn-hangzhou.aliyuncs.com"

Ⅴ. Special notes for reviews

[CLAassistant]

All committers have signed the CLA.

[ayanami-desu]

上一个搞乱了一些东西，故重开

[johnlanni]

@ayanami-desu 麻烦签署一下 CLA，然后文件有一些冲突，麻烦fix一下

[ayanami-desu]

冲突解决了

[CH3CHO]

这个判定方法是不是需要改一下，直接判断 c.initializer 就行了吧？

[CH3CHO]

LGTM

[codecov-commenter]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 43.50%. Comparing base (ef31e09) to head (70ea2c3).
Report is 245 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1572      +/-   ##
==========================================
+ Coverage   35.91%   43.50%   +7.59%     
==========================================
  Files          69       76       +7     
  Lines       11576    12325     +749     
==========================================
+ Hits         4157     5362    +1205     
+ Misses       7104     6627     -477     
- Partials      315      336      +21     

see 69 files with indirect coverage changes