LLM変換ハンドラ

transformRequestPayload: async (event, context) => {
      // Cohere doesn't support chat completions, so we first print the system prompt, and if there
      // are additional chat entries, we add these to the system prompt under the heading CONVERSATION HISTORY
      let prompt = event.payload.messages[0].content;
      if (event.payload.messages.length > 1) {
         let history = event.payload.messages.slice(1).reduce((acc, cur) => `${acc}\n${cur.role}: ${cur.content}` , '');
         prompt += `\n\nCONVERSATION HISTORY:${history}\nassistant:`
      }
      // using Cohere
      let modelId = "cohere.command"
      let runtimeType = "COHERE";
       return {
        "compartmentId": event.compartmentId,
        "servingMode": {
          "servingType": "ON_DEMAND",
            "modelId": modelId
        },
        "inferenceRequest": {
          "runtimeType": runtimeType,
          "prompt": prompt,
          "isStream": event.payload.streamResponse,
          "maxTokens": event.payload.maxTokens,
          "temperature": event.payload.temperature,
          // parameters set to default values
          "frequencyPenalty": 0,
          "isEcho": false,
          "numGenerations": 1,
          "presencePenalty": 0,
          "returnLikelihoods": "NONE",
          "topK": 0,
          "topP": 0.75,
          "truncate": "NONE"
        }
      };
}

transformResponsePayload: async (event, context) => {      
    let llmPayload = {};
    if (event.payload.responseItems) {
        // streaming case
        llmPayload.responseItems = [];
        event.payload.responseItems.forEach(item => {
          llmPayload.responseItems.push({"candidates": [{"content": item.text || "" }]});
        });
      } else {
        // non-streaming
        llmPayload.candidates = event.payload.inferenceResponse.generatedTexts.map( item => {return {"content": item.text || "" };});
      }
      return llmPayload;
 }

transformErrorResponsePayload: async (event, context) => {      
      const error = event.payload.message || 'unknown error';
      if (error.startsWith('invalid request: total number of tokens')) {
        // returning modelLengthExceeded error code will cause a retry with reduced chat history
        return {"errorCode" : "modelLengthExceeded", "errorMessage": error};
      } else {
        return {"errorCode" : "unknown", "errorMessage": error};
      }
}

transformRequestPayload: async (event, context) => {
      // Cohere doesn't support chat completions, so we first print the system prompt, and if there
      // are additional chat entries, we add these to the system prompt under the heading CONVERSATION HISTORY
      let prompt = event.payload.messages[0].content;
      if (event.payload.messages.length > 1) {
         let history = event.payload.messages.slice(1).reduce((acc, cur) => `${acc}\n${cur.role}: ${cur.content}` , '');
         prompt += `\n\nCONVERSATION HISTORY:${history}\nassistant:`
      }
      // using Llama
      let modelId = "meta.llama-2-70b-chat"
      let runtimeType = "LLAMA";
       return {
        "compartmentId": event.compartmentId,
        "servingMode": {
          "servingType": "ON_DEMAND",
            "modelId": modelId
        },
        "inferenceRequest": {
          "runtimeType": runtimeType,
          "prompt": prompt,
          "isStream": event.payload.streamResponse,
          "maxTokens": event.payload.maxTokens,
          "temperature": event.payload.temperature,
          // parameters set to default values
          "frequencyPenalty": 0,
          "isEcho": false,
          "numGenerations": 1,
          "presencePenalty": 0,
          "returnLikelihoods": "NONE",
          "topK": 0,
          "topP": 0.75,
          "truncate": "NONE"
        }
      };
}

transformResponsePayload: async (event, context) => {      
    let llmPayload = {};
    if (event.payload.responseItems) {
        // streaming case
        llmPayload.responseItems = [];
        event.payload.responseItems.forEach(item => {
          llmPayload.responseItems.push({"candidates": [{"content": item.text || "" }]});
        });
      } else {
        // non-streaming
        llmPayload.candidates = event.payload.inferenceResponse.choices.map( item => {return {"content": item.text || "" };});
      }
      return llmPayload;
 }

transformErrorResponsePayload: async (event, context) => {      
      const error = event.payload.message || 'unknown error';
      if (error.startsWith('invalid request: total number of tokens')) {
        // returning modelLengthExceeded error code will cause a retry with reduced chat history
        return {"errorCode" : "modelLengthExceeded", "errorMessage": error};
      } else {
        return {"errorCode" : "unknown", "errorMessage": error};
      }
}

transformRequestPayload: async (event, context) => {
      // Cohere doesn't support chat completions, so we first print the system prompt, and if there
      // are additional chat entries, we add these to the system prompt under the heading CONVERSATION HISTORY
      let prompt = event.payload.messages[0].content;
      if (event.payload.messages.length > 1) {
         let history = event.payload.messages.slice(1).reduce((acc, cur) => `${acc}\n${cur.role}: ${cur.content}` , '');
         prompt += `\n\nCONVERSATION HISTORY:${history}\nassistant:`
      }
      let modelId = "cohere.command"
      return {
        "compartmentId": event.compartmentId,
        "servingMode": {
          "servingType": "ON_DEMAND",
          "modelId": modelId
        },
        "input" : prompt,
        "temperature": event.payload.temperature,
        // parameters set to default values
        "length": "AUTO",
        "extractiveness": "AUTO",
        "format": "PARAGRAPH",
        // natural language instructions
        "additionalCommand": "write in a conversational style"
      };
}

transformResponsePayload: async (event, context) => {
      let llmPayload = {};
      // non-streaming only: streaming is not supported
      llmPayload.candidates = [{"content": event.payload.summary}];
      return llmPayload;
}

transformErrorResponsePayload: async (event, context) => {             const error = event.payload.message ||
          'unknown error';      if(error.startsWith('invalid request:
          total number of tokens')) {        // returning modelLengthExceeded error
          code will cause a retry with reduced chat history        return{"errorCode": "modelLengthExceeded", "errorMessage": error};      }
          else{        return{"errorCode": "unknown", "errorMessage": error};      }}

transformRequestPayload: async (event, context) => {            
      // Cohere doesn't support chat completions, so we first print the system prompt, and if there
      // are additional chat entries, we add these to the system prompt under the heading CONVERSATION HISTORY
      let prompt = event.payload.messages[0].content;
      if (event.payload.messages.length > 1) {
         let history = event.payload.messages.slice(1).reduce((acc, cur) => `${acc}\n${cur.role}: ${cur.content}` , '');
         prompt += `\n\nCONVERSATION HISTORY:${history}\nassistant:`
      }
      return {
        "max_tokens": event.payload.maxTokens,
        "truncate": "END",
        "return_likelihoods": "NONE",
        "prompt": prompt,
        "model": "command",
        "temperature": event.payload.temperature,
        "stream": event.payload.streamResponse
      };
 }

transformResponsePayload: async (event, context) => {
  let llmPayload = {};      
  if (event.payload.responseItems) {
        // streaming case
        llmPayload.responseItems = [];
        event.payload.responseItems.forEach(item => {
          llmPayload.responseItems.push({"candidates": [{"content": item.text || "" }]});
        });
      } else {
        // non-streaming
        llmPayload.candidates = event.payload.generations.map( item => {return {"content": item.text || "" };});
      }
   return llmPayload;
}

transformErrorResponsePayload: async (event, context) => {      
    // NOTE: Depending on the Cohere version, this code might need to be updated
      const error = event.payload.message || 'unknown error';
      if (error.startsWith('invalid request: total number of tokens')) {
        // returning modelLengthExceeded error code will cause a retry with reduced chat history
        return {"errorCode" : "modelLengthExceeded", "errorMessage": error};
      } else {
        return {"errorCode" : "unknown", "errorMessage": error};
      }
 
}

レスポンス検証を使用する場合は、streamResponseをfalseに設定します。検証を実行する前にメッセージ全体が必要であるため、メッセージは何度もユーザーに対してレンダリングされ、最初にストリームされてから検証され、次に再度ストリームされます。

• notAuthorized: LLMリクエストに適切な認可キーがないことを示します。
• modelLengthExceeded: リクエスト・メッセージ(ユーザーおよびアシスタントの絞込みメッセージとともにシステム・プロンプト)とトークンの最大数がモデルのトークン制限を超えていることを示します。
• requestFlagged: LLMプロバイダの管理ポリシーに違反するため、LLMがリクエストを処理できないことを示します。たとえば、人種差別的なコンテンツや性的虐待的なコンテンツを含むリクエストにはフラグが付けられます。
• responseFlagged: LLMレスポンスがLLMプロバイダのモデレーション・ポリシーに違反することを示します。たとえば、人種差別的な言語や性的虐待的な言語などの有毒な内容を含む応答にはフラグが付けられます。
• requestInvalid: LLMへのリクエストが無効であることを示します。たとえば、イベント・ハンドラで設定された検証ルールの一部に失敗したか、LLMで認識されない形式であるため、リクエストは有効ではありません。
• responseInvalid: LLMで生成されたレスポンスが無効であることを示します。たとえば、検証イベント・ハンドラで定義された検証ルールの一部に失敗したため、レスポンスは有効ではありません。
• unknown: その他のエラーが発生した場合。