diff --git a/go.mod b/go.mod index 64ccbfc03..e996c4928 100644 --- a/go.mod +++ b/go.mod @@ -19,6 +19,7 @@ require ( github.com/lib/pq v1.11.2 github.com/lithammer/shortuuid/v4 v4.2.0 github.com/mark3labs/mcp-go v0.45.0 + github.com/openai/openai-go/v3 v3.31.0 github.com/pkg/errors v0.9.1 github.com/spf13/cobra v1.10.2 github.com/spf13/viper v1.21.0 @@ -32,6 +33,7 @@ require ( golang.org/x/net v0.52.0 golang.org/x/oauth2 v0.36.0 golang.org/x/sync v0.20.0 + google.golang.org/genai v1.54.0 google.golang.org/genproto v0.0.0-20260316180232-0b37fe3546d5 google.golang.org/genproto/googleapis/api v0.0.0-20260316172706-e463d84ca32d google.golang.org/grpc v1.79.2 @@ -40,6 +42,9 @@ require ( require ( cel.dev/expr v0.25.1 // indirect + cloud.google.com/go v0.116.0 // indirect + cloud.google.com/go/auth v0.9.3 // indirect + cloud.google.com/go/compute/metadata v0.9.0 // indirect dario.cat/mergo v1.0.2 // indirect filippo.io/edwards25519 v1.1.0 // indirect github.com/Azure/go-ansiterm v0.0.0-20250102033503-faa5f7b0171c // indirect @@ -66,6 +71,11 @@ require ( github.com/go-logr/stdr v1.2.2 // indirect github.com/go-ole/go-ole v1.2.6 // indirect github.com/go-viper/mapstructure/v2 v2.4.0 // indirect + github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect + github.com/google/go-cmp v0.7.0 // indirect + github.com/google/s2a-go v0.1.8 // indirect + github.com/googleapis/enterprise-certificate-proxy v0.3.4 // indirect + github.com/gorilla/websocket v1.5.3 // indirect github.com/inconshreveable/mousetrap v1.1.0 // indirect github.com/invopop/jsonschema v0.13.0 // indirect github.com/klauspost/compress v1.18.2 // indirect @@ -94,11 +104,16 @@ require ( github.com/spf13/cast v1.10.0 // indirect github.com/spf13/pflag v1.0.10 // indirect github.com/subosito/gotenv v1.6.0 // indirect + github.com/tidwall/gjson v1.18.0 // indirect + github.com/tidwall/match v1.1.1 // indirect + github.com/tidwall/pretty v1.2.1 // indirect + github.com/tidwall/sjson v1.2.5 // indirect github.com/tklauser/go-sysconf v0.3.16 // indirect github.com/tklauser/numcpus v0.11.0 // indirect github.com/wk8/go-ordered-map/v2 v2.1.8 // indirect github.com/yosida95/uritemplate/v3 v3.0.2 // indirect github.com/yusufpapurcu/wmi v1.2.4 // indirect + go.opencensus.io v0.24.0 // indirect go.opentelemetry.io/auto/sdk v1.2.1 // indirect go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.54.0 // indirect go.opentelemetry.io/otel v1.41.0 // indirect diff --git a/go.sum b/go.sum index 1ed2415ca..98fa99163 100644 --- a/go.sum +++ b/go.sum @@ -1,5 +1,12 @@ cel.dev/expr v0.25.1 h1:1KrZg61W6TWSxuNZ37Xy49ps13NUovb66QLprthtwi4= cel.dev/expr v0.25.1/go.mod h1:hrXvqGP6G6gyx8UAHSHJ5RGk//1Oj5nXQ2NI02Nrsg4= +cloud.google.com/go v0.26.0/go.mod h1:aQUYkXzVsufM+DwF1aE+0xfcU+56JwCaLick0ClmMTw= +cloud.google.com/go v0.116.0 h1:B3fRrSDkLRt5qSHWe40ERJvhvnQwdZiHu0bJOpldweE= +cloud.google.com/go v0.116.0/go.mod h1:cEPSRWPzZEswwdr9BxE6ChEn01dWlTaF05LiC2Xs70U= +cloud.google.com/go/auth v0.9.3 h1:VOEUIAADkkLtyfr3BLa3R8Ed/j6w1jTBmARx+wb5w5U= +cloud.google.com/go/auth v0.9.3/go.mod h1:7z6VY+7h3KUdRov5F1i8NDP5ZzWKYmEPO842BgCsmTk= +cloud.google.com/go/compute/metadata v0.9.0 h1:pDUj4QMoPejqq20dK0Pg2N4yG9zIkYGdBtwLoEkH9Zs= +cloud.google.com/go/compute/metadata v0.9.0/go.mod h1:E0bWwX5wTnLPedCKqk3pJmVgCBSM6qQI1yTBdEb3C10= connectrpc.com/connect v1.19.1 h1:R5M57z05+90EfEvCY1b7hBxDVOUl45PrtXtAV2fOC14= connectrpc.com/connect v1.19.1/go.mod h1:tN20fjdGlewnSFeZxLKb0xwIZ6ozc3OQs2hTXy4du9w= dario.cat/mergo v1.0.2 h1:85+piFYR1tMbRrLcDwR18y4UKJ3aH1Tbzi24VRW1TK8= @@ -10,6 +17,7 @@ github.com/AdaLogics/go-fuzz-headers v0.0.0-20240806141605-e8a1dd7889d6 h1:He8af github.com/AdaLogics/go-fuzz-headers v0.0.0-20240806141605-e8a1dd7889d6/go.mod h1:8o94RPi1/7XTJvwPpRSzSUedZrtlirdB3r9Z20bi2f8= github.com/Azure/go-ansiterm v0.0.0-20250102033503-faa5f7b0171c h1:udKWzYgxTojEKWjV8V+WSxDXJ4NFATAsZjh8iIbsQIg= github.com/Azure/go-ansiterm v0.0.0-20250102033503-faa5f7b0171c/go.mod h1:xomTg63KZ2rFqZQzSB4Vz2SUXa1BpHTVz9L5PTmPC4E= +github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU= github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERoyfY= github.com/Microsoft/go-winio v0.6.2/go.mod h1:yd8OoFMLzJbo9gZq8j5qaps8bJ9aShtEA8Ipt1oGCvU= github.com/antlr4-go/antlr/v4 v4.13.1 h1:SqQKkuVZ+zWkMMNkjy5FZe5mr5WURWnlpmOuzYWrPrQ= @@ -60,8 +68,11 @@ github.com/cenkalti/backoff/v4 v4.3.0 h1:MyRJ/UdXutAwSAT+s3wNd7MfTIcy71VQueUuFK3 github.com/cenkalti/backoff/v4 v4.3.0/go.mod h1:Y3VNntkOUPxTVeUxJ/G5vcM//AlwfmyYozVcomhLiZE= github.com/cenkalti/backoff/v5 v5.0.3 h1:ZN+IMa753KfX5hd8vVaMixjnqRZ3y8CuJKRKj1xcsSM= github.com/cenkalti/backoff/v5 v5.0.3/go.mod h1:rkhZdG3JZukswDf7f0cwqPNk4K0sa+F97BxZthm/crw= +github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU= github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs= github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs= +github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw= +github.com/cncf/udpa/go v0.0.0-20191209042840-269d4d468f6f/go.mod h1:M8M6+tZqaGXZJjfX53e64911xZQV5JYwmTeXPW+k8Sc= github.com/containerd/errdefs v1.0.0 h1:tg5yIfIlQIrxYtu9ajqY42W3lpS19XqdxRQeEwYG8PI= github.com/containerd/errdefs v1.0.0/go.mod h1:+YBYIdtsnF4Iw6nWZhJcqGSg/dwvV7tyJ/kCkyJ2k+M= github.com/containerd/errdefs/pkg v0.3.0 h1:9IKJ06FvyNlexW690DXuQNx2KA2cUJXx151Xdx3ZPPE= @@ -93,6 +104,10 @@ github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkp github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto= github.com/ebitengine/purego v0.10.0 h1:QIw4xfpWT6GWTzaW5XEKy3HXoqrJGx1ijYHzTF0/ISU= github.com/ebitengine/purego v0.10.0/go.mod h1:iIjxzd6CiRiOG0UyXP+V1+jWqUXVjPKLAI0mRfJZTmQ= +github.com/envoyproxy/go-control-plane v0.9.0/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4= +github.com/envoyproxy/go-control-plane v0.9.1-0.20191026205805-5f8ba28d4473/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4= +github.com/envoyproxy/go-control-plane v0.9.4/go.mod h1:6rpuAdCZL397s3pYoYcLgu1mIlRU8Am5FuJP05cCM98= +github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7+kN2VEUnK/pcBlmesArF7c= github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg= github.com/felixge/httpsnoop v1.0.4/go.mod h1:m8KPJKqk1gH5J9DgRY2ASl2lWCfGKXixSwevea8zH2U= github.com/frankban/quicktest v1.14.6 h1:7Xjx+VpznH+oBnejlPUj8oUpdxnVs4f8XU8WnHkI4W8= @@ -112,19 +127,46 @@ github.com/go-viper/mapstructure/v2 v2.4.0 h1:EBsztssimR/CONLSZZ04E8qAkxNYq4Qp9L github.com/go-viper/mapstructure/v2 v2.4.0/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM= github.com/golang-jwt/jwt/v5 v5.3.1 h1:kYf81DTWFe7t+1VvL7eS+jKFVWaUnK9cB1qbwn63YCY= github.com/golang-jwt/jwt/v5 v5.3.1/go.mod h1:fxCRLWMO43lRc8nhHWY6LGqRcf+1gQWArsqaEUEa5bE= +github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q= +github.com/golang/groupcache v0.0.0-20200121045136-8c9f03a8e57e/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc= +github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da h1:oI5xCqsCo564l8iNU+DwB5epxmsaqB+rhGL0m5jtYqE= +github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc= +github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A= +github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U= +github.com/golang/protobuf v1.3.2/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U= +github.com/golang/protobuf v1.4.0-rc.1/go.mod h1:ceaxUfeHdC40wWswd/P6IGgMaK3YpKi5j83Wpe3EHw8= +github.com/golang/protobuf v1.4.0-rc.1.0.20200221234624-67d41d38c208/go.mod h1:xKAWHe0F5eneWXFV3EuXVDTCmh+JuBKY0li0aMyXATA= +github.com/golang/protobuf v1.4.0-rc.2/go.mod h1:LlEzMj4AhA7rCAGe4KMBDvJI+AwstrUpVNzEA03Pprs= +github.com/golang/protobuf v1.4.0-rc.4.0.20200313231945-b860323f09d0/go.mod h1:WU3c8KckQ9AFe+yFwt9sWVRKCVIyN9cPHBJSNnbL67w= +github.com/golang/protobuf v1.4.0/go.mod h1:jodUvKwWbYaEsadDk5Fwe5c77LiNKVO9IDvqG2KuDX0= +github.com/golang/protobuf v1.4.1/go.mod h1:U8fpvMrcmy5pZrNK1lt4xCsGvpyWQ/VVv6QDs8UjoX8= +github.com/golang/protobuf v1.4.3/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI= github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek= github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps= github.com/google/cel-go v0.27.0 h1:e7ih85+4qVrBuqQWTW4FKSqZYokVuc3HnhH5keboFTo= github.com/google/cel-go v0.27.0/go.mod h1:tTJ11FWqnhw5KKpnWpvW9CJC3Y9GK4EIS0WXnBbebzw= +github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M= +github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU= +github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU= +github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= +github.com/google/go-cmp v0.5.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= +github.com/google/go-cmp v0.5.3/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= github.com/google/go-cmp v0.5.6/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8= github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU= github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e h1:ijClszYn+mADRFY17kjQEVQ1XRhq2/JR1M3sGqeJoxs= github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e/go.mod h1:boTsfXsheKC2y+lKOCMpSfarhxDeIzfZG1jqGcPl3cA= +github.com/google/s2a-go v0.1.8 h1:zZDs9gcbt9ZPLV0ndSyQk6Kacx2g/X+SKYovpnz3SMM= +github.com/google/s2a-go v0.1.8/go.mod h1:6iNWHTpQ+nfNRN5E00MSdfDwVesa8hhS32PhPO8deJA= +github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo= github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0= github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo= +github.com/googleapis/enterprise-certificate-proxy v0.3.4 h1:XYIDZApgAnrN1c855gTgghdIA6Stxb52D5RnLI1SLyw= +github.com/googleapis/enterprise-certificate-proxy v0.3.4/go.mod h1:YKe7cfqYXjKGpGvmSg28/fFvhNzinZQm8DGnaburhGA= github.com/gorilla/feeds v1.2.0 h1:O6pBiXJ5JHhPvqy53NsjKOThq+dNFm8+DFrxBEdzSCc= github.com/gorilla/feeds v1.2.0/go.mod h1:WMib8uJP3BbY+X8Szd1rA5Pzhdfh+HCCAYT2z7Fza6Y= +github.com/gorilla/websocket v1.5.3 h1:saDtZ6Pbx/0u+bgYQ3q96pZgCzfhKXGPqt7kZ72aNNg= +github.com/gorilla/websocket v1.5.3/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE= github.com/grpc-ecosystem/grpc-gateway/v2 v2.28.0 h1:HWRh5R2+9EifMyIHV7ZV+MIZqgz+PMpZ14Jynv3O2Zs= github.com/grpc-ecosystem/grpc-gateway/v2 v2.28.0/go.mod h1:JfhWUomR1baixubs02l85lZYYOm7LV6om4ceouMv45c= github.com/hashicorp/golang-lru/v2 v2.0.7 h1:a+bsQ5rvGLjzHuww6tVxozPZFVghXaHOwFs4luLUK2k= @@ -188,6 +230,8 @@ github.com/morikuni/aec v1.0.0 h1:nP9CBfwrvYnBRgY6qfDQkygYDmYwOilePFkwzv4dU8A= github.com/morikuni/aec v1.0.0/go.mod h1:BbKIizmSmc5MMPqRYbxO4ZU0S0+P200+tUnFx7PXmsc= github.com/ncruces/go-strftime v1.0.0 h1:HMFp8mLCTPp341M/ZnA4qaf7ZlsbTc+miZjCLOFAw7w= github.com/ncruces/go-strftime v1.0.0/go.mod h1:Fwc5htZGVVkseilnfgOVb9mKy6w1naJmn9CehxcKcls= +github.com/openai/openai-go/v3 v3.31.0 h1:3KxL3H+gw6vBkBW6dmcwhbFqP4kyMgmaWTsuRheyF8w= +github.com/openai/openai-go/v3 v3.31.0/go.mod h1:cdufnVK14cWcT9qA1rRtrXx4FTRsgbDPW7Ia7SS5cZo= github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8Oi/yOhh5U= github.com/opencontainers/go-digest v1.0.0/go.mod h1:0JzlMkj0TRzQZfJkVvzbP0HBR3IKzErnv2BNG4W4MAM= github.com/opencontainers/image-spec v1.1.1 h1:y0fUlFfIZhPF1W537XOLg0/fcx6zcHCJwooC2xJA040= @@ -201,6 +245,7 @@ github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRI github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55 h1:o4JXh1EVt9k/+g42oCprj/FisM4qX9L3sZB3upGN2ZU= github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55/go.mod h1:OmDBASR4679mdNQnz2pUhc2G8CO2JrUAVFDRBDP/hJE= +github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA= github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE= github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo= github.com/rogpeppe/go-internal v1.14.1 h1:UQB4HGPB6osV0SQTLymcB4TgvyWu6ZyliaW0tI/otEQ= @@ -226,9 +271,14 @@ github.com/spf13/pflag v1.0.10/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3A github.com/spf13/viper v1.21.0 h1:x5S+0EU27Lbphp4UKm1C+1oQO+rKx36vfCoaVebLFSU= github.com/spf13/viper v1.21.0/go.mod h1:P0lhsswPGWD/1lZJ9ny3fYnVqxiegrlNrEmgLjbTCAY= github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= +github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw= +github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo= github.com/stretchr/objx v0.5.2 h1:xuMeJ0Sdp5ZMRXx/aWO6RZxdr3beISkG5/G/aIRr3pY= github.com/stretchr/objx v0.5.2/go.mod h1:FRsXN1f5AsAjCGJKqEizvkpNtU+EGNCLh3NxZ/8L+MA= github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg= +github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg= +github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU= +github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4= github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U= github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U= github.com/subosito/gotenv v1.6.0 h1:9NlTDc1FTs4qu0DDq7AEtTPNw6SVm7uBMsUCUjABIf8= @@ -239,6 +289,16 @@ github.com/testcontainers/testcontainers-go/modules/mysql v0.41.0 h1:5rwejaJr5nI github.com/testcontainers/testcontainers-go/modules/mysql v0.41.0/go.mod h1:iMO/aFWnbjYkqHw8VPsJB3rVTOD9hKDsUtV0PvzD0DA= github.com/testcontainers/testcontainers-go/modules/postgres v0.41.0 h1:AOtFXssrDlLm84A2sTTR/AhvJiYbrIuCO59d+Ro9Tb0= github.com/testcontainers/testcontainers-go/modules/postgres v0.41.0/go.mod h1:k2a09UKhgSp6vNpliIY0QSgm4Hi7GXVTzWvWgUemu/8= +github.com/tidwall/gjson v1.14.2/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk= +github.com/tidwall/gjson v1.18.0 h1:FIDeeyB800efLX89e5a8Y0BNH+LOngJyGrIWxG2FKQY= +github.com/tidwall/gjson v1.18.0/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk= +github.com/tidwall/match v1.1.1 h1:+Ho715JplO36QYgwN9PGYNhgZvoUSc9X2c80KVTi+GA= +github.com/tidwall/match v1.1.1/go.mod h1:eRSPERbgtNPcGhD8UCthc6PmLEQXEWd3PRB5JTxsfmM= +github.com/tidwall/pretty v1.2.0/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU= +github.com/tidwall/pretty v1.2.1 h1:qjsOFOWWQl+N3RsoF5/ssm1pHmJJwhjlSbZ51I6wMl4= +github.com/tidwall/pretty v1.2.1/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU= +github.com/tidwall/sjson v1.2.5 h1:kLy8mja+1c9jlljvWTlSazM7cKDRfJuR/bOJhcY5NcY= +github.com/tidwall/sjson v1.2.5/go.mod h1:Fvgq9kS/6ociJEDnK0Fk1cpYF4FIW6ZF7LAe+6jwd28= github.com/tklauser/go-sysconf v0.3.16 h1:frioLaCQSsF5Cy1jgRBrzr6t502KIIwQ0MArYICU0nA= github.com/tklauser/go-sysconf v0.3.16/go.mod h1:/qNL9xxDhc7tx3HSRsLWNnuzbVfh3e7gh/BmM179nYI= github.com/tklauser/numcpus v0.11.0 h1:nSTwhKH5e1dMNsCdVBukSZrURJRoHbSEQjdEbY+9RXw= @@ -251,6 +311,8 @@ github.com/yuin/goldmark v1.7.16 h1:n+CJdUxaFMiDUNnWC3dMWCIQJSkxH4uz3ZwQBkAlVNE= github.com/yuin/goldmark v1.7.16/go.mod h1:ip/1k0VRfGynBgxOz0yCqHrbZXhcjxyuS66Brc7iBKg= github.com/yusufpapurcu/wmi v1.2.4 h1:zFUKzehAFReQwLys1b/iSMl+JQGSCSjtVqQn9bBrPo0= github.com/yusufpapurcu/wmi v1.2.4/go.mod h1:SBZ9tNy3G9/m5Oi98Zks0QjeHVDvuK0qfxQmPyzfmi0= +go.opencensus.io v0.24.0 h1:y73uSU6J157QMP2kn2r30vwW1A2W2WFwSCGnAVxeaD0= +go.opencensus.io v0.24.0/go.mod h1:vNK8G9p7aAivkbmorf4v+7Hgx+Zs0yY+0fOtgBfjQKo= go.opentelemetry.io/auto/sdk v1.2.1 h1:jXsnJ4Lmnqd11kwkBV2LgLoFMZKizbCi5fNZ/ipaZ64= go.opentelemetry.io/auto/sdk v1.2.1/go.mod h1:KRTj+aOaElaLi+wW1kO/DZRXwkF4C5xPbEe3ZiIhN7Y= go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.54.0 h1:TT4fX+nBOA/+LUkobKGW1ydGcn+G3vRw9+g5HwCphpk= @@ -273,22 +335,42 @@ go.opentelemetry.io/proto/otlp v1.0.0 h1:T0TX0tmXU8a3CbNXzEKGeU5mIVOdf0oykP+u2lI go.opentelemetry.io/proto/otlp v1.0.0/go.mod h1:Sy6pihPLfYHkr3NkUbEhGHFhINUSI/v80hjKIs5JXpM= go.yaml.in/yaml/v3 v3.0.4 h1:tfq32ie2Jv2UxXFdLJdh3jXuOzWiL1fo0bu/FbuKpbc= go.yaml.in/yaml/v3 v3.0.4/go.mod h1:DhzuOOF2ATzADvBadXxruRBLzYTpT36CKvDb3+aBEFg= +golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w= +golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto= golang.org/x/crypto v0.49.0 h1:+Ng2ULVvLHnJ/ZFEq4KdcDd/cfjrrjjNSXNzxg0Y4U4= golang.org/x/crypto v0.49.0/go.mod h1:ErX4dUh2UM+CFYiXZRTcMpEcN8b/1gxEuv3nODoYtCA= +golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA= golang.org/x/exp v0.0.0-20251023183803-a4bb9ffd2546 h1:mgKeJMpvi0yx/sU5GsxQ7p6s2wtOnGAHZWCHUM4KGzY= golang.org/x/exp v0.0.0-20251023183803-a4bb9ffd2546/go.mod h1:j/pmGrbnkbPtQfxEe5D0VQhZC6qKbfKifgD0oM7sR70= golang.org/x/image v0.0.0-20191009234506-e7c1f5e7dbb8/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0= golang.org/x/image v0.30.0 h1:jD5RhkmVAnjqaCUXfbGBrn3lpxbknfN9w2UhHHU+5B4= golang.org/x/image v0.30.0/go.mod h1:SAEUTxCCMWSrJcCy/4HwavEsfZZJlYxeHLc6tTiAe/c= +golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE= +golang.org/x/lint v0.0.0-20190227174305-5b3e6a55c961/go.mod h1:wehouNa3lNwaWXcvxsM5YxQ5yQlVC4a0KAMCusXpPoU= +golang.org/x/lint v0.0.0-20190313153728-d0100b6bd8b3/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc= golang.org/x/mod v0.34.0 h1:xIHgNUUnW6sYkcM5Jleh05DvLOtwc6RitGHbDk4akRI= golang.org/x/mod v0.34.0/go.mod h1:ykgH52iCZe79kzLLMhyCUzhMci+nQj+0XkbXpNYtVjY= +golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4= +golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4= +golang.org/x/net v0.0.0-20190213061140-3a22650c66bd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4= +golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg= +golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg= +golang.org/x/net v0.0.0-20201110031124-69a78807bb2b/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU= golang.org/x/net v0.52.0 h1:He/TN1l0e4mmR3QqHMT2Xab3Aj3L9qjbhRm78/6jrW0= golang.org/x/net v0.52.0/go.mod h1:R1MAz7uMZxVMualyPXb+VaqGSa3LIaUqk0eEt3w36Sw= +golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U= golang.org/x/oauth2 v0.36.0 h1:peZ/1z27fi9hUOFCAZaHyrpWG5lwe0RJEEEeH0ThlIs= golang.org/x/oauth2 v0.36.0/go.mod h1:YDBUJMTkDnJS+A4BP4eZBjCqtokkg1hODuPjwiGPO7Q= +golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= golang.org/x/sync v0.20.0 h1:e0PTpb7pjO8GAtTs2dQ6jYa5BWYlMuX047Dco/pItO4= golang.org/x/sync v0.20.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0= +golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= +golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= +golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20201204225414-ed752295db88/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20210616094352-59db8d763f22/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= @@ -298,23 +380,50 @@ golang.org/x/sys v0.42.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw= golang.org/x/term v0.41.0 h1:QCgPso/Q3RTJx2Th4bDLqML4W6iJiaXFq2/ftQF13YU= golang.org/x/term v0.41.0/go.mod h1:3pfBgksrReYfZ5lvYM0kSO0LIkAl4Yl2bXOkKP7Ec2A= golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ= +golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ= golang.org/x/text v0.35.0 h1:JOVx6vVDFokkpaq1AEptVzLTpDe9KGpj5tR4/X+ybL8= golang.org/x/text v0.35.0/go.mod h1:khi/HExzZJ2pGnjenulevKNX1W67CUy0AsXcNubPGCA= golang.org/x/time v0.14.0 h1:MRx4UaLrDotUKUdCIqzPC48t1Y9hANFKIRpNx+Te8PI= golang.org/x/time v0.14.0/go.mod h1:eL/Oa2bBBK0TkX57Fyni+NgnyQQN4LitPmob2Hjnqw4= +golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ= +golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ= +golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY= +golang.org/x/tools v0.0.0-20190311212946-11955173bddd/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs= +golang.org/x/tools v0.0.0-20190524140312-2c0ae7006135/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q= golang.org/x/tools v0.42.0 h1:uNgphsn75Tdz5Ji2q36v/nsFSfR/9BRFvqhGBaJGd5k= golang.org/x/tools v0.42.0/go.mod h1:Ma6lCIwGZvHK6XtgbswSoWroEkhugApmsXyrUmBhfr0= golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= gonum.org/v1/gonum v0.16.0 h1:5+ul4Swaf3ESvrOnidPp4GZbzf0mxVQpDCYUQE7OJfk= gonum.org/v1/gonum v0.16.0/go.mod h1:fef3am4MQ93R2HHpKnLk4/Tbh/s0+wqD5nfa6Pnwy4E= +google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9YwlJXL52JkM= +google.golang.org/appengine v1.4.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4= +google.golang.org/genai v1.54.0 h1:ZQCa70WMTJDI11FdqWCzGvZ5PanpcpfoO6jl/lrSnGU= +google.golang.org/genai v1.54.0/go.mod h1:A3kkl0nyBjyFlNjgxIwKq70julKbIxpSxqKO5gw/gmk= +google.golang.org/genproto v0.0.0-20180817151627-c66870c02cf8/go.mod h1:JiN7NxoALGmiZfu7CAH4rXhgtRTLTxftemlI0sWmxmc= +google.golang.org/genproto v0.0.0-20190819201941-24fa4b261c55/go.mod h1:DMBHOl98Agz4BDEuKkezgsaosCRResVns1a3J2ZsMNc= +google.golang.org/genproto v0.0.0-20200526211855-cb27e3aa2013/go.mod h1:NbSheEEYHJ7i3ixzK3sjbqSGDJWnxyFXZblF3eUsNvo= google.golang.org/genproto v0.0.0-20260316180232-0b37fe3546d5 h1:JNfk58HZ8lfmXbYK2vx/UvsqIL59TzByCxPIX4TDmsE= google.golang.org/genproto v0.0.0-20260316180232-0b37fe3546d5/go.mod h1:x5julN69+ED4PcFk/XWayw35O0lf/nGa4aNgODCmNmw= google.golang.org/genproto/googleapis/api v0.0.0-20260316172706-e463d84ca32d h1:RdWlPmVySdTF0IBIZzvZJvSD0ZocPBNUsnE+uGBxj+4= google.golang.org/genproto/googleapis/api v0.0.0-20260316172706-e463d84ca32d/go.mod h1:X2gu9Qwng7Nn009s/r3RUxqkzQNqOrAy79bluY7ojIg= google.golang.org/genproto/googleapis/rpc v0.0.0-20260311181403-84a4fc48630c h1:xgCzyF2LFIO/0X2UAoVRiXKU5Xg6VjToG4i2/ecSswk= google.golang.org/genproto/googleapis/rpc v0.0.0-20260311181403-84a4fc48630c/go.mod h1:4Hqkh8ycfw05ld/3BWL7rJOSfebL2Q+DVDeRgYgxUU8= +google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c= +google.golang.org/grpc v1.23.0/go.mod h1:Y5yQAOtifL1yxbo5wqy6BxZv8vAUGQwXBOALyacEbxg= +google.golang.org/grpc v1.25.1/go.mod h1:c3i+UQWmh7LiEpx4sFZnkU36qjEYZ0imhYfXVyQciAY= +google.golang.org/grpc v1.27.0/go.mod h1:qbnxyOmOxrQa7FizSgH+ReBfzJrCY1pSN7KXBS8abTk= +google.golang.org/grpc v1.33.2/go.mod h1:JMHMWHQWaTccqQQlmk3MJZS+GWXOdAesneDmEnv2fbc= google.golang.org/grpc v1.79.2 h1:fRMD94s2tITpyJGtBBn7MkMseNpOZU8ZxgC3MMBaXRU= google.golang.org/grpc v1.79.2/go.mod h1:KmT0Kjez+0dde/v2j9vzwoAScgEPx/Bw1CYChhHLrHQ= +google.golang.org/protobuf v0.0.0-20200109180630-ec00e32a8dfd/go.mod h1:DFci5gLYBciE7Vtevhsrf46CRTquxDuWsQurQQe4oz8= +google.golang.org/protobuf v0.0.0-20200221191635-4d8936d0db64/go.mod h1:kwYJMbMJ01Woi6D6+Kah6886xMZcty6N08ah7+eCXa0= +google.golang.org/protobuf v0.0.0-20200228230310-ab0ca4ff8a60/go.mod h1:cfTl7dwQJ+fmap5saPgwCLgHXTUD7jkjRqWcaiX5VyM= +google.golang.org/protobuf v1.20.1-0.20200309200217-e05f789c0967/go.mod h1:A+miEFZTKqfCUM6K7xSMQL9OKL/b6hQv+e19PK+JZNE= +google.golang.org/protobuf v1.21.0/go.mod h1:47Nbq4nVaFHyn7ilMalzfO3qCViNmqZ2kzikPIcrTAo= +google.golang.org/protobuf v1.22.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU= +google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU= +google.golang.org/protobuf v1.23.1-0.20200526195155-81db48ad09cc/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU= +google.golang.org/protobuf v1.25.0/go.mod h1:9JNX74DMeImyA3h4bdi1ymwjUzf21/xIlbajtzgsN7c= google.golang.org/protobuf v1.36.11 h1:fV6ZwhNocDyBLK0dj+fg8ektcVegBBuEolpbTQyBNVE= google.golang.org/protobuf v1.36.11/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= @@ -325,6 +434,8 @@ gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= gotest.tools/v3 v3.5.2 h1:7koQfIKdy+I8UTetycgUqXWSDwpgv193Ka+qRsmBY8Q= gotest.tools/v3 v3.5.2/go.mod h1:LtdLGcnqToBH83WByAAi/wiwSFCArdFIUV/xxN4pcjA= +honnef.co/go/tools v0.0.0-20190102054323-c2f93a96b099/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4= +honnef.co/go/tools v0.0.0-20190523083050-ea95bdfd59fc/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4= modernc.org/cc/v4 v4.27.1 h1:9W30zRlYrefrDV2JE2O8VDtJ1yPGownxciz5rrbQZis= modernc.org/cc/v4 v4.27.1/go.mod h1:uVtb5OGqUKpoLWhqwNQo/8LwvoiEBLvZXIQ/SmO6mL0= modernc.org/ccgo/v4 v4.30.1 h1:4r4U1J6Fhj98NKfSjnPUN7Ze2c6MnAdL0hWw6+LrJpc= diff --git a/internal/ai/client.go b/internal/ai/client.go new file mode 100644 index 000000000..bfd6f79ae --- /dev/null +++ b/internal/ai/client.go @@ -0,0 +1,65 @@ +package ai + +import ( + "net/http" + "net/url" + "strings" + "time" + + "github.com/pkg/errors" +) + +const defaultHTTPTimeout = 2 * time.Minute + +type transcriberOptions struct { + httpClient *http.Client +} + +// TranscriberOption configures a transcriber. +type TranscriberOption func(*transcriberOptions) + +// WithHTTPClient sets the HTTP client used by a transcriber. +func WithHTTPClient(client *http.Client) TranscriberOption { + return func(options *transcriberOptions) { + if client != nil { + options.httpClient = client + } + } +} + +// NewTranscriber creates a transcriber for a provider. +func NewTranscriber(config ProviderConfig, options ...TranscriberOption) (Transcriber, error) { + transcriberOptions := transcriberOptions{ + httpClient: &http.Client{Timeout: defaultHTTPTimeout}, + } + for _, applyOption := range options { + applyOption(&transcriberOptions) + } + + switch config.Type { + case ProviderOpenAI: + return newOpenAITranscriber(config, transcriberOptions) + case ProviderGemini: + return newGeminiTranscriber(config, transcriberOptions) + default: + return nil, errors.Wrapf(ErrCapabilityUnsupported, "provider type %q", config.Type) + } +} + +func normalizeEndpoint(endpoint string, defaultEndpoint string, providerName string) (string, error) { + endpoint = strings.TrimSpace(endpoint) + if endpoint == "" { + endpoint = defaultEndpoint + } + if _, err := url.ParseRequestURI(endpoint); err != nil { + return "", errors.Wrapf(err, "invalid %s endpoint", providerName) + } + return strings.TrimRight(endpoint, "/"), nil +} + +func requireAPIKey(apiKey string, providerName string) error { + if apiKey == "" { + return errors.Errorf("%s API key is required", providerName) + } + return nil +} diff --git a/internal/ai/gemini.go b/internal/ai/gemini.go new file mode 100644 index 000000000..5caf3be8d --- /dev/null +++ b/internal/ai/gemini.go @@ -0,0 +1,162 @@ +package ai + +import ( + "context" + "io" + "mime" + "net/url" + "strings" + + "github.com/pkg/errors" + "google.golang.org/genai" +) + +const ( + defaultGeminiEndpoint = "https://generativelanguage.googleapis.com/v1beta" + geminiTranscriptionPrompt = `Transcribe the audio accurately. Return only the transcript text. Do not summarize, explain, or add content that is not spoken.` + maxGeminiInlineAudioSize = 14 * 1024 * 1024 + defaultGeminiAPIVersion = "v1beta" + geminiProviderDisplayName = "Gemini" + geminiDefaultTemperature = float32(0) +) + +var geminiSupportedContentTypes = map[string]string{ + "audio/wav": "audio/wav", + "audio/x-wav": "audio/wav", + "audio/mp3": "audio/mp3", + "audio/mpeg": "audio/mp3", + "audio/aiff": "audio/aiff", + "audio/aac": "audio/aac", + "audio/ogg": "audio/ogg", + "audio/flac": "audio/flac", + "audio/x-flac": "audio/flac", +} + +type geminiTranscriber struct { + client *genai.Client +} + +func newGeminiTranscriber(config ProviderConfig, options transcriberOptions) (*geminiTranscriber, error) { + endpoint, err := normalizeEndpoint(config.Endpoint, defaultGeminiEndpoint, geminiProviderDisplayName) + if err != nil { + return nil, err + } + if err := requireAPIKey(config.APIKey, geminiProviderDisplayName); err != nil { + return nil, err + } + baseURL, apiVersion, err := normalizeGeminiEndpoint(endpoint) + if err != nil { + return nil, err + } + httpOptions := genai.HTTPOptions{ + BaseURL: baseURL, + APIVersion: apiVersion, + } + if options.httpClient.Timeout > 0 { + timeout := options.httpClient.Timeout + httpOptions.Timeout = &timeout + } + + client, err := genai.NewClient(context.Background(), &genai.ClientConfig{ + APIKey: config.APIKey, + Backend: genai.BackendGeminiAPI, + HTTPClient: options.httpClient, + HTTPOptions: httpOptions, + }) + if err != nil { + return nil, errors.Wrap(err, "failed to create Gemini client") + } + return &geminiTranscriber{client: client}, nil +} + +// Transcribe transcribes audio with Gemini generateContent. +func (t *geminiTranscriber) Transcribe(ctx context.Context, request TranscribeRequest) (*TranscribeResponse, error) { + if strings.TrimSpace(request.Model) == "" { + return nil, errors.New("model is required") + } + if request.Audio == nil { + return nil, errors.New("audio is required") + } + audio, err := io.ReadAll(request.Audio) + if err != nil { + return nil, errors.Wrap(err, "failed to read audio") + } + if len(audio) == 0 { + return nil, errors.New("audio is required") + } + if len(audio) > maxGeminiInlineAudioSize { + return nil, errors.Errorf("audio is too large for Gemini inline transcription; maximum size is %d bytes", maxGeminiInlineAudioSize) + } + + contentType, err := normalizeGeminiContentType(request.ContentType) + if err != nil { + return nil, err + } + prompt := buildGeminiTranscriptionPrompt(request.Prompt, request.Language) + temperature := geminiDefaultTemperature + response, err := t.client.Models.GenerateContent(ctx, normalizeGeminiModelName(request.Model), []*genai.Content{ + genai.NewContentFromParts([]*genai.Part{ + genai.NewPartFromBytes(audio, contentType), + genai.NewPartFromText(prompt), + }, genai.RoleUser), + }, &genai.GenerateContentConfig{ + Temperature: &temperature, + }) + if err != nil { + return nil, errors.Wrap(err, "failed to send Gemini transcription request") + } + text := strings.TrimSpace(response.Text()) + if text == "" { + return nil, errors.New("Gemini transcription response did not include text") + } + return &TranscribeResponse{ + Text: text, + }, nil +} + +func normalizeGeminiEndpoint(endpoint string) (string, string, error) { + parsed, err := url.Parse(endpoint) + if err != nil { + return "", "", errors.Wrap(err, "invalid Gemini endpoint") + } + path := strings.TrimRight(parsed.Path, "/") + apiVersion := defaultGeminiAPIVersion + for _, supportedVersion := range []string{"v1alpha", "v1beta", "v1"} { + if path == "/"+supportedVersion || strings.HasSuffix(path, "/"+supportedVersion) { + apiVersion = supportedVersion + parsed.Path = strings.TrimSuffix(path, "/"+supportedVersion) + break + } + } + return strings.TrimRight(parsed.String(), "/"), apiVersion, nil +} + +func normalizeGeminiContentType(contentType string) (string, error) { + mediaType, _, err := mime.ParseMediaType(strings.TrimSpace(contentType)) + if err != nil { + return "", errors.Wrap(err, "invalid audio content type") + } + mediaType = strings.ToLower(mediaType) + normalized, ok := geminiSupportedContentTypes[mediaType] + if !ok { + return "", errors.Errorf("audio content type %q is not supported by Gemini", mediaType) + } + return normalized, nil +} + +func buildGeminiTranscriptionPrompt(prompt string, language string) string { + parts := []string{geminiTranscriptionPrompt} + language = strings.TrimSpace(language) + if language != "" { + parts = append(parts, "The input language is "+language+".") + } + prompt = strings.TrimSpace(prompt) + if prompt != "" { + parts = append(parts, "Context and spelling hints:\n"+prompt) + } + return strings.Join(parts, "\n\n") +} + +func normalizeGeminiModelName(model string) string { + return strings.TrimPrefix(strings.TrimSpace(model), "models/") +} diff --git a/internal/ai/gemini/client.go b/internal/ai/gemini/client.go deleted file mode 100644 index 6a0448670..000000000 --- a/internal/ai/gemini/client.go +++ /dev/null @@ -1,59 +0,0 @@ -package gemini - -import ( - "net/http" - "net/url" - "strings" - "time" - - "github.com/pkg/errors" - - "github.com/usememos/memos/internal/ai" -) - -const defaultEndpoint = "https://generativelanguage.googleapis.com/v1beta" - -// Transcriber transcribes audio with Gemini audio understanding. -type Transcriber struct { - endpoint string - apiKey string - httpClient *http.Client -} - -// NewTranscriber creates a new Gemini transcriber. -func NewTranscriber(config ai.ProviderConfig, options ...Option) (*Transcriber, error) { - endpoint := strings.TrimSpace(config.Endpoint) - if endpoint == "" { - endpoint = defaultEndpoint - } - if _, err := url.ParseRequestURI(endpoint); err != nil { - return nil, errors.Wrap(err, "invalid Gemini endpoint") - } - if config.APIKey == "" { - return nil, errors.New("Gemini API key is required") - } - - transcriber := &Transcriber{ - endpoint: strings.TrimRight(endpoint, "/"), - apiKey: config.APIKey, - httpClient: &http.Client{ - Timeout: 2 * time.Minute, - }, - } - for _, option := range options { - option(transcriber) - } - return transcriber, nil -} - -// Option configures a Transcriber. -type Option func(*Transcriber) - -// WithHTTPClient sets the HTTP client used by the transcriber. -func WithHTTPClient(client *http.Client) Option { - return func(t *Transcriber) { - if client != nil { - t.httpClient = client - } - } -} diff --git a/internal/ai/gemini/transcription.go b/internal/ai/gemini/transcription.go deleted file mode 100644 index 8b6dd969b..000000000 --- a/internal/ai/gemini/transcription.go +++ /dev/null @@ -1,201 +0,0 @@ -package gemini - -import ( - "bytes" - "context" - "encoding/base64" - "encoding/json" - "io" - "mime" - "net/http" - "net/url" - "strings" - - "github.com/pkg/errors" - - "github.com/usememos/memos/internal/ai" -) - -const ( - transcriptionInstruction = `Transcribe the audio accurately. Return only the transcript text. Do not summarize, explain, or add content that is not spoken.` - maxInlineAudioSizeBytes = 14 * 1024 * 1024 -) - -var supportedContentTypes = map[string]string{ - "audio/wav": "audio/wav", - "audio/x-wav": "audio/wav", - "audio/mp3": "audio/mp3", - "audio/mpeg": "audio/mp3", - "audio/aiff": "audio/aiff", - "audio/aac": "audio/aac", - "audio/ogg": "audio/ogg", - "audio/flac": "audio/flac", - "audio/x-flac": "audio/flac", -} - -type generateContentRequest struct { - Contents []content `json:"contents"` - GenerationConfig map[string]json.Number `json:"generationConfig,omitempty"` -} - -type content struct { - Role string `json:"role,omitempty"` - Parts []part `json:"parts"` -} - -type part struct { - Text string `json:"text,omitempty"` - InlineData *inlineData `json:"inlineData,omitempty"` -} - -type inlineData struct { - MIMEType string `json:"mimeType"` - Data string `json:"data"` -} - -type generateContentResponse struct { - Candidates []struct { - Content struct { - Parts []struct { - Text string `json:"text"` - } `json:"parts"` - } `json:"content"` - } `json:"candidates"` -} - -type errorResponse struct { - Error struct { - Message string `json:"message"` - Status string `json:"status"` - } `json:"error"` -} - -// Transcribe transcribes audio with Gemini generateContent. -func (t *Transcriber) Transcribe(ctx context.Context, request ai.TranscribeRequest) (*ai.TranscribeResponse, error) { - if strings.TrimSpace(request.Model) == "" { - return nil, errors.New("model is required") - } - if request.Audio == nil { - return nil, errors.New("audio is required") - } - audio, err := io.ReadAll(request.Audio) - if err != nil { - return nil, errors.Wrap(err, "failed to read audio") - } - if len(audio) == 0 { - return nil, errors.New("audio is required") - } - if len(audio) > maxInlineAudioSizeBytes { - return nil, errors.Errorf("audio is too large for Gemini inline transcription; maximum size is %d bytes", maxInlineAudioSizeBytes) - } - - contentType, err := normalizeContentType(request.ContentType) - if err != nil { - return nil, err - } - prompt := buildTranscriptionPrompt(request.Prompt, request.Language) - body, err := json.Marshal(generateContentRequest{ - Contents: []content{ - { - Role: "user", - Parts: []part{ - {InlineData: &inlineData{ - MIMEType: contentType, - Data: base64.StdEncoding.EncodeToString(audio), - }}, - {Text: prompt}, - }, - }, - }, - GenerationConfig: map[string]json.Number{ - "temperature": json.Number("0"), - }, - }) - if err != nil { - return nil, errors.Wrap(err, "failed to marshal Gemini transcription request") - } - - httpRequest, err := http.NewRequestWithContext(ctx, http.MethodPost, t.endpoint+"/models/"+url.PathEscape(normalizeModelName(request.Model))+":generateContent", bytes.NewReader(body)) - if err != nil { - return nil, errors.Wrap(err, "failed to create Gemini transcription request") - } - httpRequest.Header.Set("Content-Type", "application/json") - httpRequest.Header.Set("x-goog-api-key", t.apiKey) - - httpResponse, err := t.httpClient.Do(httpRequest) - if err != nil { - return nil, errors.Wrap(err, "failed to send Gemini transcription request") - } - defer httpResponse.Body.Close() - - responseBody, err := io.ReadAll(httpResponse.Body) - if err != nil { - return nil, errors.Wrap(err, "failed to read Gemini transcription response") - } - if httpResponse.StatusCode < http.StatusOK || httpResponse.StatusCode >= http.StatusMultipleChoices { - return nil, errors.Errorf("Gemini transcription request failed with status %d: %s", httpResponse.StatusCode, extractErrorMessage(responseBody)) - } - - var response generateContentResponse - if err := json.Unmarshal(responseBody, &response); err != nil { - return nil, errors.Wrap(err, "failed to unmarshal Gemini transcription response") - } - text := extractText(response) - if text == "" { - return nil, errors.New("Gemini transcription response did not include text") - } - return &ai.TranscribeResponse{ - Text: text, - }, nil -} - -func normalizeContentType(contentType string) (string, error) { - mediaType, _, err := mime.ParseMediaType(strings.TrimSpace(contentType)) - if err != nil { - return "", errors.Wrap(err, "invalid audio content type") - } - mediaType = strings.ToLower(mediaType) - normalized, ok := supportedContentTypes[mediaType] - if !ok { - return "", errors.Errorf("audio content type %q is not supported by Gemini", mediaType) - } - return normalized, nil -} - -func buildTranscriptionPrompt(prompt string, language string) string { - parts := []string{transcriptionInstruction} - language = strings.TrimSpace(language) - if language != "" { - parts = append(parts, "The input language is "+language+".") - } - prompt = strings.TrimSpace(prompt) - if prompt != "" { - parts = append(parts, "Context and spelling hints:\n"+prompt) - } - return strings.Join(parts, "\n\n") -} - -func normalizeModelName(model string) string { - return strings.TrimPrefix(strings.TrimSpace(model), "models/") -} - -func extractText(response generateContentResponse) string { - var texts []string - for _, candidate := range response.Candidates { - for _, part := range candidate.Content.Parts { - text := strings.TrimSpace(part.Text) - if text != "" { - texts = append(texts, text) - } - } - } - return strings.Join(texts, "\n") -} - -func extractErrorMessage(responseBody []byte) string { - var response errorResponse - if err := json.Unmarshal(responseBody, &response); err == nil && response.Error.Message != "" { - return response.Error.Message - } - return string(responseBody) -} diff --git a/internal/ai/gemini/transcription_test.go b/internal/ai/gemini_test.go similarity index 86% rename from internal/ai/gemini/transcription_test.go rename to internal/ai/gemini_test.go index 0c0fb8aa8..83f3e6289 100644 --- a/internal/ai/gemini/transcription_test.go +++ b/internal/ai/gemini_test.go @@ -1,4 +1,4 @@ -package gemini +package ai import ( "context" @@ -11,11 +11,9 @@ import ( "time" "github.com/stretchr/testify/require" - - "github.com/usememos/memos/internal/ai" ) -func TestTranscribe(t *testing.T) { +func TestGeminiTranscribe(t *testing.T) { t.Parallel() server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { @@ -61,7 +59,8 @@ func TestTranscribe(t *testing.T) { })) defer server.Close() - transcriber, err := NewTranscriber(ai.ProviderConfig{ + transcriber, err := NewTranscriber(ProviderConfig{ + Type: ProviderGemini, Endpoint: server.URL + "/v1beta", APIKey: "test-key", }) @@ -69,7 +68,7 @@ func TestTranscribe(t *testing.T) { ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second) defer cancel() - response, err := transcriber.Transcribe(ctx, ai.TranscribeRequest{ + response, err := transcriber.Transcribe(ctx, TranscribeRequest{ Model: "models/gemini-2.5-flash", ContentType: "audio/mpeg", Audio: strings.NewReader("audio bytes"), @@ -80,16 +79,17 @@ func TestTranscribe(t *testing.T) { require.Equal(t, "hello from gemini", response.Text) } -func TestTranscribeRejectsUnsupportedContentType(t *testing.T) { +func TestGeminiTranscribeRejectsUnsupportedContentType(t *testing.T) { t.Parallel() - transcriber, err := NewTranscriber(ai.ProviderConfig{ + transcriber, err := NewTranscriber(ProviderConfig{ + Type: ProviderGemini, Endpoint: "https://example.com/v1beta", APIKey: "test-key", }) require.NoError(t, err) - _, err = transcriber.Transcribe(context.Background(), ai.TranscribeRequest{ + _, err = transcriber.Transcribe(context.Background(), TranscribeRequest{ Model: "gemini-2.5-flash", ContentType: "video/mp4", Audio: strings.NewReader("video bytes"), diff --git a/internal/ai/openai.go b/internal/ai/openai.go new file mode 100644 index 000000000..6a1d8a0b3 --- /dev/null +++ b/internal/ai/openai.go @@ -0,0 +1,98 @@ +package ai + +import ( + "context" + "mime" + "strings" + + openaisdk "github.com/openai/openai-go/v3" + openaioption "github.com/openai/openai-go/v3/option" + "github.com/pkg/errors" +) + +const defaultOpenAIEndpoint = "https://api.openai.com/v1" + +type openAITranscriber struct { + client openaisdk.Client +} + +func newOpenAITranscriber(config ProviderConfig, options transcriberOptions) (*openAITranscriber, error) { + endpoint, err := normalizeEndpoint(config.Endpoint, defaultOpenAIEndpoint, "OpenAI") + if err != nil { + return nil, err + } + if err := requireAPIKey(config.APIKey, "OpenAI"); err != nil { + return nil, err + } + + return &openAITranscriber{ + client: openaisdk.NewClient( + openaioption.WithAPIKey(config.APIKey), + openaioption.WithBaseURL(endpoint), + openaioption.WithHTTPClient(options.httpClient), + ), + }, nil +} + +// Transcribe transcribes audio with the OpenAI /audio/transcriptions endpoint. +func (t *openAITranscriber) Transcribe(ctx context.Context, request TranscribeRequest) (*TranscribeResponse, error) { + if strings.TrimSpace(request.Model) == "" { + return nil, errors.New("model is required") + } + if request.Audio == nil { + return nil, errors.New("audio is required") + } + + filename, contentType, err := normalizeOpenAIAudioFileMetadata(request) + if err != nil { + return nil, err + } + + params := openaisdk.AudioTranscriptionNewParams{ + File: openaisdk.File(request.Audio, filename, contentType), + Model: openaisdk.AudioModel(request.Model), + ResponseFormat: openaisdk.AudioResponseFormatJSON, + } + if request.Prompt != "" { + params.Prompt = openaisdk.String(request.Prompt) + } + if request.Language != "" { + params.Language = openaisdk.String(request.Language) + } + + response, err := t.client.Audio.Transcriptions.New(ctx, params) + if err != nil { + return nil, errors.Wrap(err, "failed to send OpenAI transcription request") + } + return &TranscribeResponse{ + Text: response.Text, + Language: response.Language, + Duration: response.Duration, + }, nil +} + +func normalizeOpenAIAudioFileMetadata(request TranscribeRequest) (string, string, error) { + filename := strings.TrimSpace(request.Filename) + if filename == "" { + filename = "audio" + } + contentType := strings.TrimSpace(request.ContentType) + if contentType == "" { + contentType = "application/octet-stream" + } else { + mediaType, _, err := mime.ParseMediaType(contentType) + if err != nil { + return "", "", errors.Wrap(err, "invalid audio content type") + } + contentType = mediaType + } + return sanitizeFilename(filename), contentType, nil +} + +func sanitizeFilename(filename string) string { + filename = strings.NewReplacer("\r", "_", "\n", "_").Replace(filename) + if strings.TrimSpace(filename) == "" { + return "audio" + } + return filename +} diff --git a/internal/ai/openai/client.go b/internal/ai/openai/client.go deleted file mode 100644 index b1ad49dea..000000000 --- a/internal/ai/openai/client.go +++ /dev/null @@ -1,59 +0,0 @@ -package openai - -import ( - "net/http" - "net/url" - "strings" - "time" - - "github.com/pkg/errors" - - "github.com/usememos/memos/internal/ai" -) - -const defaultEndpoint = "https://api.openai.com/v1" - -// Transcriber transcribes audio with OpenAI-compatible transcription APIs. -type Transcriber struct { - endpoint string - apiKey string - httpClient *http.Client -} - -// NewTranscriber creates a new OpenAI-compatible transcriber. -func NewTranscriber(config ai.ProviderConfig, options ...Option) (*Transcriber, error) { - endpoint := strings.TrimSpace(config.Endpoint) - if endpoint == "" { - endpoint = defaultEndpoint - } - if _, err := url.ParseRequestURI(endpoint); err != nil { - return nil, errors.Wrap(err, "invalid OpenAI endpoint") - } - if config.APIKey == "" { - return nil, errors.New("OpenAI API key is required") - } - - transcriber := &Transcriber{ - endpoint: endpoint, - apiKey: config.APIKey, - httpClient: &http.Client{ - Timeout: 2 * time.Minute, - }, - } - for _, option := range options { - option(transcriber) - } - return transcriber, nil -} - -// Option configures a Transcriber. -type Option func(*Transcriber) - -// WithHTTPClient sets the HTTP client used by the transcriber. -func WithHTTPClient(client *http.Client) Option { - return func(t *Transcriber) { - if client != nil { - t.httpClient = client - } - } -} diff --git a/internal/ai/openai/transcription.go b/internal/ai/openai/transcription.go deleted file mode 100644 index 79a9adad5..000000000 --- a/internal/ai/openai/transcription.go +++ /dev/null @@ -1,145 +0,0 @@ -package openai - -import ( - "bytes" - "context" - "encoding/json" - "io" - "mime" - "mime/multipart" - "net/http" - "net/textproto" - "strings" - - "github.com/pkg/errors" - - "github.com/usememos/memos/internal/ai" -) - -type transcriptionResponse struct { - Text string `json:"text"` - Language string `json:"language"` - Duration float64 `json:"duration"` -} - -type errorResponse struct { - Error struct { - Message string `json:"message"` - Type string `json:"type"` - Code string `json:"code"` - } `json:"error"` -} - -// Transcribe transcribes audio with the /audio/transcriptions endpoint. -func (t *Transcriber) Transcribe(ctx context.Context, request ai.TranscribeRequest) (*ai.TranscribeResponse, error) { - if strings.TrimSpace(request.Model) == "" { - return nil, errors.New("model is required") - } - if request.Audio == nil { - return nil, errors.New("audio is required") - } - - body := &bytes.Buffer{} - writer := multipart.NewWriter(body) - if err := writeAudioFilePart(writer, request); err != nil { - return nil, err - } - if err := writer.WriteField("model", request.Model); err != nil { - return nil, errors.Wrap(err, "failed to write model field") - } - if err := writer.WriteField("response_format", "json"); err != nil { - return nil, errors.Wrap(err, "failed to write response format field") - } - if request.Prompt != "" { - if err := writer.WriteField("prompt", request.Prompt); err != nil { - return nil, errors.Wrap(err, "failed to write prompt field") - } - } - if request.Language != "" { - if err := writer.WriteField("language", request.Language); err != nil { - return nil, errors.Wrap(err, "failed to write language field") - } - } - if err := writer.Close(); err != nil { - return nil, errors.Wrap(err, "failed to close multipart writer") - } - - httpRequest, err := http.NewRequestWithContext(ctx, http.MethodPost, strings.TrimRight(t.endpoint, "/")+"/audio/transcriptions", body) - if err != nil { - return nil, errors.Wrap(err, "failed to create transcription request") - } - httpRequest.Header.Set("Authorization", "Bearer "+t.apiKey) - httpRequest.Header.Set("Content-Type", writer.FormDataContentType()) - - httpResponse, err := t.httpClient.Do(httpRequest) - if err != nil { - return nil, errors.Wrap(err, "failed to send transcription request") - } - defer httpResponse.Body.Close() - - responseBody, err := io.ReadAll(httpResponse.Body) - if err != nil { - return nil, errors.Wrap(err, "failed to read transcription response") - } - if httpResponse.StatusCode < http.StatusOK || httpResponse.StatusCode >= http.StatusMultipleChoices { - return nil, errors.Errorf("transcription request failed with status %d: %s", httpResponse.StatusCode, extractErrorMessage(responseBody)) - } - - var response transcriptionResponse - if err := json.Unmarshal(responseBody, &response); err != nil { - return nil, errors.Wrap(err, "failed to unmarshal transcription response") - } - return &ai.TranscribeResponse{ - Text: response.Text, - Language: response.Language, - Duration: response.Duration, - }, nil -} - -func writeAudioFilePart(writer *multipart.Writer, request ai.TranscribeRequest) error { - filename := strings.TrimSpace(request.Filename) - if filename == "" { - filename = "audio" - } - contentType := strings.TrimSpace(request.ContentType) - if contentType == "" { - contentType = "application/octet-stream" - } else { - mediaType, _, err := mime.ParseMediaType(contentType) - if err != nil { - return errors.Wrap(err, "invalid audio content type") - } - contentType = mediaType - } - - header := make(textproto.MIMEHeader) - header.Set("Content-Disposition", mime.FormatMediaType("form-data", map[string]string{ - "name": "file", - "filename": sanitizeFilename(filename), - })) - header.Set("Content-Type", contentType) - part, err := writer.CreatePart(header) - if err != nil { - return errors.Wrap(err, "failed to create audio file part") - } - if _, err := io.Copy(part, request.Audio); err != nil { - return errors.Wrap(err, "failed to write audio file part") - } - return nil -} - -func extractErrorMessage(responseBody []byte) string { - var response errorResponse - if err := json.Unmarshal(responseBody, &response); err == nil && response.Error.Message != "" { - return response.Error.Message - } - return string(responseBody) -} - -func sanitizeFilename(filename string) string { - filename = strings.NewReplacer("\r", "_", "\n", "_").Replace(filename) - if strings.TrimSpace(filename) == "" { - return "audio" - } - return filename -} diff --git a/internal/ai/openai/transcription_test.go b/internal/ai/openai_test.go similarity index 88% rename from internal/ai/openai/transcription_test.go rename to internal/ai/openai_test.go index c436b7cd1..6f6a2b677 100644 --- a/internal/ai/openai/transcription_test.go +++ b/internal/ai/openai_test.go @@ -1,4 +1,4 @@ -package openai +package ai import ( "context" @@ -10,11 +10,9 @@ import ( "time" "github.com/stretchr/testify/require" - - "github.com/usememos/memos/internal/ai" ) -func TestTranscribe(t *testing.T) { +func TestOpenAITranscribe(t *testing.T) { t.Parallel() server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { @@ -42,7 +40,8 @@ func TestTranscribe(t *testing.T) { })) defer server.Close() - transcriber, err := NewTranscriber(ai.ProviderConfig{ + transcriber, err := NewTranscriber(ProviderConfig{ + Type: ProviderOpenAI, Endpoint: server.URL, APIKey: "test-key", }) @@ -50,7 +49,7 @@ func TestTranscribe(t *testing.T) { ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second) defer cancel() - response, err := transcriber.Transcribe(ctx, ai.TranscribeRequest{ + response, err := transcriber.Transcribe(ctx, TranscribeRequest{ Model: "gpt-4o-transcribe", Filename: "voice.wav", ContentType: "audio/wav", diff --git a/server/router/api/v1/ai_service.go b/server/router/api/v1/ai_service.go index 14d80b88d..ad70b6e3f 100644 --- a/server/router/api/v1/ai_service.go +++ b/server/router/api/v1/ai_service.go @@ -7,13 +7,10 @@ import ( "net/http" "strings" - "github.com/pkg/errors" "google.golang.org/grpc/codes" "google.golang.org/grpc/status" "github.com/usememos/memos/internal/ai" - "github.com/usememos/memos/internal/ai/gemini" - "github.com/usememos/memos/internal/ai/openai" v1pb "github.com/usememos/memos/proto/gen/api/v1" storepb "github.com/usememos/memos/proto/gen/store" ) @@ -97,7 +94,7 @@ func (s *APIV1Service) Transcribe(ctx context.Context, request *v1pb.TranscribeR if err != nil { return nil, err } - transcriber, err := newAITranscriber(provider) + transcriber, err := ai.NewTranscriber(provider) if err != nil { return nil, status.Errorf(codes.InvalidArgument, "failed to create AI transcriber: %v", err) } @@ -165,17 +162,6 @@ func convertAIProviderTypeFromStore(providerType storepb.AIProviderType) ai.Prov } } -func newAITranscriber(provider ai.ProviderConfig) (ai.Transcriber, error) { - switch provider.Type { - case ai.ProviderOpenAI: - return openai.NewTranscriber(provider) - case ai.ProviderGemini: - return gemini.NewTranscriber(provider) - default: - return nil, errors.Wrapf(ai.ErrCapabilityUnsupported, "provider type %q", provider.Type) - } -} - func isSupportedTranscriptionContentType(contentType string) bool { mediaType, _, err := mime.ParseMediaType(strings.TrimSpace(contentType)) if err != nil {