@promptbook/cli 0.66.0-0 → 0.66.0-1

package/esm/index.es.js

@@ -20,7 +20,7 @@ import glob from 'glob-promise';
 /**
  * The version of the Promptbook library
  */
-var PROMPTBOOK_VERSION = '0.65.0';
+var PROMPTBOOK_VERSION = '0.66.0-0';
 // TODO: !!!! List here all the versions and annotate + put into script
 
 /*! *****************************************************************************
@@ -303,6 +303,9 @@ var RESERVED_PARAMETER_MISSING_VALUE = 'MISSING-' + REPLACING_NONCE;
  * @private within the repository
  */
 var RESERVED_PARAMETER_RESTRICTED = 'RESTRICTED-' + REPLACING_NONCE;
+/**
+ * TODO: [🧠][🧜‍♂️] Maybe join remoteUrl and path into single value
+ */
 
 /**
  * Initializes `about` command for Promptbook CLI utilities
@@ -832,7 +835,7 @@ function forEachAsync(array, options, callbackfunction) {
     });
 }
 
-var PipelineCollection = [{title:"Prepare Knowledge from Markdown",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-from-markdown.ptbk.md",promptbookVersion:"0.65.0",parameters:[{name:"knowledgeContent",description:"Markdown document content",isInput:true,isOutput:false},{name:"knowledgePieces",description:"The knowledge JSON object",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced data researcher, extract the important knowledge from the document.\n\n# Rules\n\n-   Make pieces of information concise, clear, and easy to understand\n-   One piece of information should be approximately 1 paragraph\n-   Divide the paragraphs by markdown horizontal lines ---\n-   Omit irrelevant information\n-   Group redundant information\n-   Write just extracted information, nothing else\n\n# The document\n\nTake information from this document:\n\n> {knowledgeContent}",dependentParameterNames:["knowledgeContent"],resultingParameterName:"knowledgePieces"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-knowledge-from-markdown.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-keywords.ptbk.md",promptbookVersion:"0.65.0",parameters:[{name:"knowledgePieceContent",description:"The content",isInput:true,isOutput:false},{name:"keywords",description:"Keywords separated by comma",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced data researcher, detect the important keywords in the document.\n\n# Rules\n\n-   Write just keywords separated by comma\n\n# The document\n\nTake information from this document:\n\n> {knowledgePieceContent}",dependentParameterNames:["knowledgePieceContent"],resultingParameterName:"keywords"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-knowledge-keywords.ptbk.md"},{title:"Prepare Title",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-title.ptbk.md",promptbookVersion:"0.65.0",parameters:[{name:"knowledgePieceContent",description:"The content",isInput:true,isOutput:false},{name:"title",description:"The title of the document",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced content creator, write best title for the document.\n\n# Rules\n\n-   Write just title, nothing else\n-   Title should be concise and clear\n-   Write maximum 5 words for the title\n\n# The document\n\n> {knowledgePieceContent}",expectations:{words:{min:1,max:8}},dependentParameterNames:["knowledgePieceContent"],resultingParameterName:"title"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-knowledge-title.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-persona.ptbk.md",promptbookVersion:"0.65.0",parameters:[{name:"availableModelNames",description:"List of available model names separated by comma (,)",isInput:true,isOutput:false},{name:"personaDescription",description:"Description of the persona",isInput:true,isOutput:false},{name:"modelRequirements",description:"Specific requirements for the model",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"make-model-requirements",title:"Make modelRequirements",modelRequirements:{modelVariant:"CHAT",modelName:"gpt-4-turbo"},content:"You are experienced AI engineer, you need to create virtual assistant.\nWrite\n\n## Sample\n\n```json\n{\n\"modelName\": \"gpt-4o\",\n\"systemMessage\": \"You are experienced AI engineer and helpfull assistant.\",\n\"temperature\": 0.7\n}\n```\n\n## Instructions\n\n### Option `modelName`\n\nPick from the following models:\n\n-   {availableModelNames}\n\n### Option `systemMessage`\n\nThe system message is used to communicate instructions or provide context to the model at the beginning of a conversation. It is displayed in a different format compared to user messages, helping the model understand its role in the conversation. The system message typically guides the model's behavior, sets the tone, or specifies desired output from the model. By utilizing the system message effectively, users can steer the model towards generating more accurate and relevant responses.\n\nFor example:\n\n> You are an experienced AI engineer and helpful assistant.\n\n> You are a friendly and knowledgeable chatbot.\n\n### Option `temperature`\n\nThe sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.\n\nYou can pick a value between 0 and 2. For example:\n\n-   `0.1`: Low temperature, extremely conservative and deterministic\n-   `0.5`: Medium temperature, balanced between conservative and creative\n-   `1.0`: High temperature, creative and bit random\n-   `1.5`: Very high temperature, extremely creative and often chaotic and unpredictable\n-   `2.0`: Maximum temperature, completely random and unpredictable, for some extreme creative use cases\n\n# The assistant\n\nTake this description of the persona:\n\n> {personaDescription}",expectFormat:"JSON",dependentParameterNames:["availableModelNames","personaDescription"],resultingParameterName:"modelRequirements"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-persona.ptbk.md"}];
+var PipelineCollection = [{title:"Prepare Knowledge from Markdown",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-from-markdown.ptbk.md",promptbookVersion:"0.66.0-0",parameters:[{name:"knowledgeContent",description:"Markdown document content",isInput:true,isOutput:false},{name:"knowledgePieces",description:"The knowledge JSON object",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced data researcher, extract the important knowledge from the document.\n\n# Rules\n\n-   Make pieces of information concise, clear, and easy to understand\n-   One piece of information should be approximately 1 paragraph\n-   Divide the paragraphs by markdown horizontal lines ---\n-   Omit irrelevant information\n-   Group redundant information\n-   Write just extracted information, nothing else\n\n# The document\n\nTake information from this document:\n\n> {knowledgeContent}",dependentParameterNames:["knowledgeContent"],resultingParameterName:"knowledgePieces"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-knowledge-from-markdown.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-keywords.ptbk.md",promptbookVersion:"0.66.0-0",parameters:[{name:"knowledgePieceContent",description:"The content",isInput:true,isOutput:false},{name:"keywords",description:"Keywords separated by comma",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced data researcher, detect the important keywords in the document.\n\n# Rules\n\n-   Write just keywords separated by comma\n\n# The document\n\nTake information from this document:\n\n> {knowledgePieceContent}",dependentParameterNames:["knowledgePieceContent"],resultingParameterName:"keywords"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-knowledge-keywords.ptbk.md"},{title:"Prepare Title",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-title.ptbk.md",promptbookVersion:"0.66.0-0",parameters:[{name:"knowledgePieceContent",description:"The content",isInput:true,isOutput:false},{name:"title",description:"The title of the document",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced content creator, write best title for the document.\n\n# Rules\n\n-   Write just title, nothing else\n-   Title should be concise and clear\n-   Write maximum 5 words for the title\n\n# The document\n\n> {knowledgePieceContent}",expectations:{words:{min:1,max:8}},dependentParameterNames:["knowledgePieceContent"],resultingParameterName:"title"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-knowledge-title.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-persona.ptbk.md",promptbookVersion:"0.66.0-0",parameters:[{name:"availableModelNames",description:"List of available model names separated by comma (,)",isInput:true,isOutput:false},{name:"personaDescription",description:"Description of the persona",isInput:true,isOutput:false},{name:"modelRequirements",description:"Specific requirements for the model",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"make-model-requirements",title:"Make modelRequirements",modelRequirements:{modelVariant:"CHAT",modelName:"gpt-4-turbo"},content:"You are experienced AI engineer, you need to create virtual assistant.\nWrite\n\n## Sample\n\n```json\n{\n\"modelName\": \"gpt-4o\",\n\"systemMessage\": \"You are experienced AI engineer and helpfull assistant.\",\n\"temperature\": 0.7\n}\n```\n\n## Instructions\n\n### Option `modelName`\n\nPick from the following models:\n\n-   {availableModelNames}\n\n### Option `systemMessage`\n\nThe system message is used to communicate instructions or provide context to the model at the beginning of a conversation. It is displayed in a different format compared to user messages, helping the model understand its role in the conversation. The system message typically guides the model's behavior, sets the tone, or specifies desired output from the model. By utilizing the system message effectively, users can steer the model towards generating more accurate and relevant responses.\n\nFor example:\n\n> You are an experienced AI engineer and helpful assistant.\n\n> You are a friendly and knowledgeable chatbot.\n\n### Option `temperature`\n\nThe sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.\n\nYou can pick a value between 0 and 2. For example:\n\n-   `0.1`: Low temperature, extremely conservative and deterministic\n-   `0.5`: Medium temperature, balanced between conservative and creative\n-   `1.0`: High temperature, creative and bit random\n-   `1.5`: Very high temperature, extremely creative and often chaotic and unpredictable\n-   `2.0`: Maximum temperature, completely random and unpredictable, for some extreme creative use cases\n\n# The assistant\n\nTake this description of the persona:\n\n> {personaDescription}",expectFormat:"JSON",dependentParameterNames:["availableModelNames","personaDescription"],resultingParameterName:"modelRequirements"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-persona.ptbk.md"}];
 
 /**
  * This error indicates that the promptbook in a markdown format cannot be parsed into a valid promptbook object
@@ -6806,6 +6809,15 @@ var ANTHROPIC_CLAUDE_MODELS = [
  * TODO: [🎰] Some mechanism to auto-update available models
  */
 
+/**
+ * Get current date in ISO 8601 format
+ *
+ * @private internal utility
+ */
+function getCurrentIsoDate() {
+    return new Date().toISOString();
+}
+
 /**
  * Helper of usage compute
  *
@@ -6840,13 +6852,42 @@ function uncertainNumber(value) {
 }
 
 /**
- * Get current date in ISO 8601 format
+ * Computes the usage of the Anthropic Claude API based on the response from Anthropic Claude
  *
- * @private internal utility
+ * @param promptContent The content of the prompt
+ * @param resultContent The content of the result (for embedding prompts or failed prompts pass empty string)
+ * @param rawResponse The raw response from Anthropic Claude API
+ * @throws {PipelineExecutionError} If the usage is not defined in the response from Anthropic Claude
+ * @private internal utility of `AnthropicClaudeExecutionTools`
  */
-function getCurrentIsoDate() {
-    return new Date().toISOString();
+function computeAnthropicClaudeUsage(promptContent, // <- Note: Intentionally using [] to access type properties to bring jsdoc from Prompt/PromptResult to consumer
+resultContent, rawResponse) {
+    var _a, _b;
+    if (rawResponse.usage === undefined) {
+        throw new PipelineExecutionError('The usage is not defined in the response from Anthropic Claude');
+    }
+    if (((_a = rawResponse.usage) === null || _a === void 0 ? void 0 : _a.input_tokens) === undefined) {
+        throw new PipelineExecutionError('In Anthropic Claude response `usage.prompt_tokens` not defined');
+    }
+    var inputTokens = rawResponse.usage.input_tokens;
+    var outputTokens = ((_b = rawResponse.usage) === null || _b === void 0 ? void 0 : _b.output_tokens) || 0;
+    var modelInfo = ANTHROPIC_CLAUDE_MODELS.find(function (model) { return model.modelName === rawResponse.model; });
+    var price;
+    if (modelInfo === undefined || modelInfo.pricing === undefined) {
+        price = uncertainNumber();
+    }
+    else {
+        price = uncertainNumber(inputTokens * modelInfo.pricing.prompt + outputTokens * modelInfo.pricing.output);
+    }
+    return {
+        price: price,
+        input: __assign({ tokensCount: uncertainNumber(rawResponse.usage.input_tokens) }, computeUsageCounts(promptContent)),
+        output: __assign({ tokensCount: uncertainNumber(outputTokens) }, computeUsageCounts(resultContent)),
+    };
 }
+/**
+ * TODO: [🤝] DRY Maybe some common abstraction between `computeOpenaiUsage` and `computeAnthropicClaudeUsage`
+ */
 
 /**
  * Execution Tools for calling Anthropic Claude API.
@@ -6867,9 +6908,8 @@ var AnthropicClaudeExecutionTools = /** @class */ (function () {
         var anthropicOptions = __assign({}, options);
         delete anthropicOptions.isVerbose;
         delete anthropicOptions.isProxied;
-        this.client = new Anthropic(
-        //            <- TODO: [🧱] Implement in a functional (not new Class) way
-        anthropicOptions);
+        this.client = new Anthropic(anthropicOptions);
+        // <- TODO: !!!!!! Lazy-load client
     }
     Object.defineProperty(AnthropicClaudeExecutionTools.prototype, "title", {
         get: function () {
@@ -6940,15 +6980,10 @@ var AnthropicClaudeExecutionTools = /** @class */ (function () {
                         if (contentBlock.type !== 'text') {
                             throw new PipelineExecutionError("Returned content is not \"text\" type but \"".concat(contentBlock.type, "\""));
                         }
-                        console.log('!!!!!! rawResponse.usage', rawResponse.usage);
                         resultContent = contentBlock.text;
                         // eslint-disable-next-line prefer-const
                         complete = getCurrentIsoDate();
-                        usage = {
-                            price: { value: 0, isUncertain: true } /* <- TODO: [🐞] !!!!!! Compute usage */,
-                            input: __assign({ tokensCount: uncertainNumber(rawResponse.usage.input_tokens) }, computeUsageCounts(prompt.content)),
-                            output: __assign({ tokensCount: uncertainNumber(rawResponse.usage.output_tokens) }, computeUsageCounts(prompt.content)),
-                        };
+                        usage = computeAnthropicClaudeUsage(content, '', rawResponse);
                         return [2 /*return*/, {
                                 content: resultContent,
                                 modelName: rawResponse.model,
@@ -7473,9 +7508,8 @@ var AzureOpenAiExecutionTools = /** @class */ (function () {
         this.options = options;
         this.client = new OpenAIClient(
         //            <- TODO: [🧱] Implement in a functional (not new Class) way
-        "https://".concat(options.resourceName, ".openai.azure.com/"), new AzureKeyCredential(
-        //            <- TODO: [🧱] Implement in a functional (not new Class) way
-        options.apiKey));
+        "https://".concat(options.resourceName, ".openai.azure.com/"), new AzureKeyCredential(options.apiKey));
+        // <- TODO: !!!!!! Lazy-load client
     }
     Object.defineProperty(AzureOpenAiExecutionTools.prototype, "title", {
         get: function () {
@@ -7745,6 +7779,9 @@ resultContent, rawResponse) {
         output: __assign({ tokensCount: uncertainNumber(outputTokens) }, computeUsageCounts(resultContent)),
     };
 }
+/**
+ * TODO: [🤝] DRY Maybe some common abstraction between `computeOpenaiUsage` and `computeAnthropicClaudeUsage`
+ */
 
 /**
  * Execution Tools for calling OpenAI API.
@@ -7765,6 +7802,7 @@ var OpenAiExecutionTools = /** @class */ (function () {
         delete openAiOptions.isVerbose;
         delete openAiOptions.user;
         this.client = new OpenAI(__assign({}, openAiOptions));
+        // <- TODO: !!!!!! Lazy-load client
     }
     Object.defineProperty(OpenAiExecutionTools.prototype, "title", {
         get: function () {
@@ -8066,7 +8104,7 @@ var EXECUTION_TOOLS_CLASSES = {
     // <- Note: [🦑] Add here new LLM provider
 };
 /**
- * TODO: [🧠] Better file name than `config.ts` + maybe move to two separate files
+ * TODO: !!!!!!! Make global register for this
  * TODO: [🧠][🎌] Adding this should be responsibility of each provider package NOT this one central place
  */