@promptbook/ollama 0.94.0-5 → 0.94.0

package/umd/index.umd.js

@@ -25,12 +25,52 @@
      * @generated
      * @see https://github.com/webgptorg/promptbook
      */
-    const PROMPTBOOK_ENGINE_VERSION = '0.94.0-5';
+    const PROMPTBOOK_ENGINE_VERSION = '0.94.0';
     /**
      * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
      * Note: [💞] Ignore a discrepancy between file name and entity name
      */
 
+    /**
+     * Detects if the code is running in a browser environment in main thread (Not in a web worker)
+     *
+     * Note: `$` is used to indicate that this function is not a pure function - it looks at the global object to determine the environment
+     *
+     * @public exported from `@promptbook/utils`
+     */
+    const $isRunningInBrowser = new Function(`
+    try {
+        return this === window;
+    } catch (e) {
+        return false;
+    }
+`);
+    /**
+     * TODO: [🎺]
+     */
+
+    /**
+     * Detects if the code is running in a web worker
+     *
+     * Note: `$` is used to indicate that this function is not a pure function - it looks at the global object to determine the environment
+     *
+     * @public exported from `@promptbook/utils`
+     */
+    const $isRunningInWebWorker = new Function(`
+    try {
+        if (typeof WorkerGlobalScope !== 'undefined' && self instanceof WorkerGlobalScope) {
+            return true;
+        } else {
+            return false;
+        }
+    } catch (e) {
+        return false;
+    }
+`);
+    /**
+     * TODO: [🎺]
+     */
+
     /**
      * Freezes the given object and all its nested objects recursively
      *
@@ -1062,7 +1102,7 @@
                 modelVariant: 'COMPLETION',
                 modelTitle: 'davinci-002',
                 modelName: 'davinci-002',
-                modelDescription: 'Legacy completion model with strong performance on text generation tasks. Optimized for complex instructions and longer outputs.',
+                modelDescription: 'Legacy completion model with 4K token context window. Excels at complex text generation, creative writing, and detailed content creation with strong contextual understanding. Optimized for instructions requiring nuanced outputs and extended reasoning. Suitable for applications needing high-quality text generation without conversation management.',
                 pricing: {
                     prompt: pricing(`$2.00 / 1M tokens`),
                     output: pricing(`$2.00 / 1M tokens`),
@@ -1080,7 +1120,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-3.5-turbo-16k',
                 modelName: 'gpt-3.5-turbo-16k',
-                modelDescription: 'GPT-3.5 Turbo with extended 16k token context length for handling longer conversations and documents.',
+                modelDescription: 'Extended context GPT-3.5 Turbo with 16K token window. Maintains core capabilities of standard 3.5 Turbo while supporting longer conversations and documents. Features good balance of performance and cost for applications requiring more context than standard 4K models. Effective for document analysis, extended conversations, and multi-step reasoning tasks.',
                 pricing: {
                     prompt: pricing(`$3.00 / 1M tokens`),
                     output: pricing(`$4.00 / 1M tokens`),
@@ -1104,7 +1144,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-4',
                 modelName: 'gpt-4',
-                modelDescription: 'GPT-4 is a powerful language model with enhanced reasoning, instruction-following capabilities, and 8K context window. Optimized for complex tasks requiring deep understanding.',
+                modelDescription: 'Powerful language model with 8K context window featuring sophisticated reasoning, instruction-following, and knowledge capabilities. Demonstrates strong performance on complex tasks requiring deep understanding and multi-step reasoning. Excels at code generation, logical analysis, and nuanced content creation. Suitable for advanced applications requiring high-quality outputs.',
                 pricing: {
                     prompt: pricing(`$30.00 / 1M tokens`),
                     output: pricing(`$60.00 / 1M tokens`),
@@ -1116,7 +1156,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-4-32k',
                 modelName: 'gpt-4-32k',
-                modelDescription: 'Extended context version of GPT-4 with a 32K token window for processing very long inputs and generating comprehensive responses for complex tasks.',
+                modelDescription: 'Extended context version of GPT-4 with 32K token window. Maintains all capabilities of standard GPT-4 while supporting analysis of very lengthy documents, code bases, and conversations. Features enhanced ability to maintain context over long interactions and process detailed information from large inputs. Ideal for document analysis, legal review, and complex problem-solving.',
                 pricing: {
                     prompt: pricing(`$60.00 / 1M tokens`),
                     output: pricing(`$120.00 / 1M tokens`),
@@ -1139,7 +1179,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-4-turbo-2024-04-09',
                 modelName: 'gpt-4-turbo-2024-04-09',
-                modelDescription: 'Latest stable GPT-4 Turbo model from April 2024 with enhanced reasoning and context handling capabilities. Offers 128K context window and improved performance.',
+                modelDescription: 'Latest stable GPT-4 Turbo from April 2024 with 128K context window. Features enhanced reasoning chains, improved factual accuracy with 40% reduction in hallucinations, and better instruction following compared to earlier versions. Includes advanced function calling capabilities and knowledge up to April 2024. Provides optimal performance for enterprise applications requiring reliability.',
                 pricing: {
                     prompt: pricing(`$10.00 / 1M tokens`),
                     output: pricing(`$30.00 / 1M tokens`),
@@ -1151,7 +1191,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-3.5-turbo-1106',
                 modelName: 'gpt-3.5-turbo-1106',
-                modelDescription: 'November 2023 version of GPT-3.5 Turbo with improved instruction following and a 16K token context window.',
+                modelDescription: 'November 2023 version of GPT-3.5 Turbo with 16K token context window. Features improved instruction following, more consistent output formatting, and enhanced function calling capabilities. Includes knowledge cutoff from April 2023. Suitable for applications requiring good performance at lower cost than GPT-4 models.',
                 pricing: {
                     prompt: pricing(`$1.00 / 1M tokens`),
                     output: pricing(`$2.00 / 1M tokens`),
@@ -1163,7 +1203,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-4-turbo',
                 modelName: 'gpt-4-turbo',
-                modelDescription: 'More capable model than GPT-4 with improved instruction following, function calling and a 128K token context window for handling very large documents.',
+                modelDescription: 'More capable and cost-efficient version of GPT-4 with 128K token context window. Features improved instruction following, advanced function calling capabilities, and better performance on coding tasks. Maintains superior reasoning and knowledge while offering substantial cost reduction compared to base GPT-4. Ideal for complex applications requiring extensive context processing.',
                 pricing: {
                     prompt: pricing(`$10.00 / 1M tokens`),
                     output: pricing(`$30.00 / 1M tokens`),
@@ -1175,10 +1215,10 @@
                 modelVariant: 'COMPLETION',
                 modelTitle: 'gpt-3.5-turbo-instruct-0914',
                 modelName: 'gpt-3.5-turbo-instruct-0914',
-                modelDescription: 'September 2023 version of GPT-3.5 Turbo optimized for completion-style instruction following with a 4K context window.',
+                modelDescription: 'September 2023 version of GPT-3.5 Turbo Instruct with 4K context window. Optimized for completion-style instruction following with deterministic responses. Better suited than chat models for applications requiring specific formatted outputs without conversation management. Knowledge cutoff from September 2021.',
                 pricing: {
                     prompt: pricing(`$1.50  / 1M tokens`),
-                    output: pricing(`$2.00 / 1M tokens`), // <- For gpt-3.5-turbo-instruct
+                    output: pricing(`$2.00 / 1M tokens`),
                 },
             },
             /**/
@@ -1187,7 +1227,7 @@
                 modelVariant: 'COMPLETION',
                 modelTitle: 'gpt-3.5-turbo-instruct',
                 modelName: 'gpt-3.5-turbo-instruct',
-                modelDescription: 'Optimized version of GPT-3.5 for completion-style API with good instruction following and a 4K token context window.',
+                modelDescription: 'Optimized version of GPT-3.5 for completion-style API with 4K token context window. Features strong instruction following with single-turn design rather than multi-turn conversation. Provides more consistent, deterministic outputs compared to chat models. Well-suited for templated content generation and structured text transformation tasks.',
                 pricing: {
                     prompt: pricing(`$1.50  / 1M tokens`),
                     output: pricing(`$2.00 / 1M tokens`),
@@ -1205,7 +1245,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-3.5-turbo',
                 modelName: 'gpt-3.5-turbo',
-                modelDescription: 'Latest version of GPT-3.5 Turbo with improved performance and instruction following capabilities. Default 4K context window with options for 16K.',
+                modelDescription: 'Latest version of GPT-3.5 Turbo with 4K token default context window (16K available). Features continually improved performance with enhanced instruction following and reduced hallucinations. Offers excellent balance between capability and cost efficiency. Suitable for most general-purpose applications requiring good AI capabilities at reasonable cost.',
                 pricing: {
                     prompt: pricing(`$0.50 / 1M tokens`),
                     output: pricing(`$1.50 / 1M tokens`),
@@ -1217,7 +1257,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-3.5-turbo-0301',
                 modelName: 'gpt-3.5-turbo-0301',
-                modelDescription: 'March 2023 version of GPT-3.5 Turbo with a 4K token context window. Legacy model maintained for backward compatibility.',
+                modelDescription: 'March 2023 version of GPT-3.5 Turbo with 4K token context window. Legacy model maintained for backward compatibility with specific application behaviors. Features solid conversational abilities and basic instruction following. Knowledge cutoff from September 2021. Suitable for applications explicitly designed for this version.',
                 pricing: {
                     prompt: pricing(`$1.50 / 1M tokens`),
                     output: pricing(`$2.00 / 1M tokens`),
@@ -1229,7 +1269,7 @@
                 modelVariant: 'COMPLETION',
                 modelTitle: 'babbage-002',
                 modelName: 'babbage-002',
-                modelDescription: 'Efficient legacy completion model with a good balance of performance and speed. Suitable for straightforward text generation tasks.',
+                modelDescription: 'Efficient legacy completion model with 4K context window balancing performance and speed. Features moderate reasoning capabilities with focus on straightforward text generation tasks. Significantly more efficient than davinci models while maintaining adequate quality for many applications. Suitable for high-volume, cost-sensitive text generation needs.',
                 pricing: {
                     prompt: pricing(`$0.40 / 1M tokens`),
                     output: pricing(`$0.40 / 1M tokens`),
@@ -1241,7 +1281,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-4-1106-preview',
                 modelName: 'gpt-4-1106-preview',
-                modelDescription: 'November 2023 preview version of GPT-4 Turbo with improved instruction following and a 128K token context window.',
+                modelDescription: 'November 2023 preview version of GPT-4 Turbo with 128K token context window. Features improved instruction following, better function calling capabilities, and enhanced reasoning. Includes knowledge cutoff from April 2023. Suitable for complex applications requiring extensive document understanding and sophisticated interactions.',
                 pricing: {
                     prompt: pricing(`$10.00 / 1M tokens`),
                     output: pricing(`$30.00 / 1M tokens`),
@@ -1253,7 +1293,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-4-0125-preview',
                 modelName: 'gpt-4-0125-preview',
-                modelDescription: 'January 2024 preview version of GPT-4 Turbo with improved reasoning capabilities and a 128K token context window.',
+                modelDescription: 'January 2024 preview version of GPT-4 Turbo with 128K token context window. Features improved reasoning capabilities, enhanced tool use, and more reliable function calling. Includes knowledge cutoff from October 2023. Offers better performance on complex logical tasks and more consistent outputs than previous preview versions.',
                 pricing: {
                     prompt: pricing(`$10.00 / 1M tokens`),
                     output: pricing(`$30.00 / 1M tokens`),
@@ -1271,7 +1311,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-3.5-turbo-0125',
                 modelName: 'gpt-3.5-turbo-0125',
-                modelDescription: 'January 2024 version of GPT-3.5 Turbo with improved reasoning capabilities and a 16K token context window.',
+                modelDescription: 'January 2024 version of GPT-3.5 Turbo with 16K token context window. Features improved reasoning capabilities, better instruction adherence, and reduced hallucinations compared to previous versions. Includes knowledge cutoff from September 2021. Provides good performance for most general applications at reasonable cost.',
                 pricing: {
                     prompt: pricing(`$0.50 / 1M tokens`),
                     output: pricing(`$1.50  / 1M tokens`),
@@ -1283,7 +1323,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-4-turbo-preview',
                 modelName: 'gpt-4-turbo-preview',
-                modelDescription: 'Preview version of GPT-4 Turbo that points to the latest model version. Features improved instruction following, 128K token context window and lower latency.',
+                modelDescription: 'Preview version of GPT-4 Turbo with 128K token context window that points to the latest development model. Features cutting-edge improvements to instruction following, knowledge representation, and tool use capabilities. Provides access to newest features but may have occasional behavior changes. Best for non-critical applications wanting latest capabilities.',
                 pricing: {
                     prompt: pricing(`$10.00 / 1M tokens`),
                     output: pricing(`$30.00 / 1M tokens`),
@@ -1295,11 +1335,10 @@
                 modelVariant: 'EMBEDDING',
                 modelTitle: 'text-embedding-3-large',
                 modelName: 'text-embedding-3-large',
-                modelDescription: "OpenAI's most capable text embedding model designed for high-quality embeddings for complex similarity tasks and information retrieval.",
+                modelDescription: "OpenAI's most capable text embedding model generating 3072-dimensional vectors. Designed for high-quality embeddings for complex similarity tasks, clustering, and information retrieval. Features enhanced cross-lingual capabilities and significantly improved performance on retrieval and classification benchmarks. Ideal for sophisticated RAG systems and semantic search applications.",
                 pricing: {
                     prompt: pricing(`$0.13 / 1M tokens`),
-                    // TODO: [🏏] Leverage the batch API @see https://platform.openai.com/docs/guides/batch
-                    output: 0, // <- Note: [🆖] In Embedding models you dont pay for output
+                    output: 0,
                 },
             },
             /**/
@@ -1308,11 +1347,10 @@
                 modelVariant: 'EMBEDDING',
                 modelTitle: 'text-embedding-3-small',
                 modelName: 'text-embedding-3-small',
-                modelDescription: 'Cost-effective embedding model with good performance for simpler tasks like text similarity and retrieval. Good balance of quality and efficiency.',
+                modelDescription: 'Cost-effective embedding model generating 1536-dimensional vectors. Balances quality and efficiency for simpler tasks while maintaining good performance on text similarity and retrieval applications. Offers 20% better quality than ada-002 at significantly lower cost. Ideal for production embedding applications with cost constraints.',
                 pricing: {
                     prompt: pricing(`$0.02 / 1M tokens`),
-                    // TODO: [🏏] Leverage the batch API @see https://platform.openai.com/docs/guides/batch
-                    output: 0, // <- Note: [🆖] In Embedding models you dont pay for output
+                    output: 0,
                 },
             },
             /**/
@@ -1321,7 +1359,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-3.5-turbo-0613',
                 modelName: 'gpt-3.5-turbo-0613',
-                modelDescription: 'June 2023 version of GPT-3.5 Turbo with function calling capabilities and a 4K token context window.',
+                modelDescription: "June 2023 version of GPT-3.5 Turbo with 4K token context window. Features function calling capabilities for structured data extraction and API interaction. Includes knowledge cutoff from September 2021. Maintained for applications specifically designed for this version's behaviors and capabilities.",
                 pricing: {
                     prompt: pricing(`$1.50 / 1M tokens`),
                     output: pricing(`$2.00 / 1M tokens`),
@@ -1333,11 +1371,10 @@
                 modelVariant: 'EMBEDDING',
                 modelTitle: 'text-embedding-ada-002',
                 modelName: 'text-embedding-ada-002',
-                modelDescription: 'Legacy text embedding model suitable for text similarity and retrieval augmented generation use cases. Replaced by newer embedding-3 models.',
+                modelDescription: 'Legacy text embedding model generating 1536-dimensional vectors suitable for text similarity and retrieval applications. Processes up to 8K tokens per request with consistent embedding quality. While superseded by newer embedding-3 models, still maintains adequate performance for many semantic search and classification tasks.',
                 pricing: {
                     prompt: pricing(`$0.1 / 1M tokens`),
-                    // TODO: [🏏] Leverage the batch API @see https://platform.openai.com/docs/guides/batch
-                    output: 0, // <- Note: [🆖] In Embedding models you dont pay for output
+                    output: 0,
                 },
             },
             /**/
@@ -1364,7 +1401,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-4o-2024-05-13',
                 modelName: 'gpt-4o-2024-05-13',
-                modelDescription: 'May 2024 version of GPT-4o with enhanced multimodal capabilities, improved reasoning, and optimized for vision, audio and chat at lower latencies.',
+                modelDescription: 'May 2024 version of GPT-4o with 128K context window. Features enhanced multimodal capabilities including superior image understanding (up to 20MP), audio processing, and improved reasoning. Optimized for 2x lower latency than GPT-4 Turbo while maintaining high performance. Includes knowledge up to October 2023. Ideal for production applications requiring reliable multimodal capabilities.',
                 pricing: {
                     prompt: pricing(`$5.00 / 1M tokens`),
                     output: pricing(`$15.00 / 1M tokens`),
@@ -1376,7 +1413,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-4o',
                 modelName: 'gpt-4o',
-                modelDescription: "OpenAI's most advanced multimodal model optimized for performance, speed, and cost. Capable of vision, reasoning, and high quality text generation.",
+                modelDescription: "OpenAI's most advanced general-purpose multimodal model with 128K context window. Optimized for balanced performance, speed, and cost with 2x faster responses than GPT-4 Turbo. Features excellent vision processing, audio understanding, reasoning, and text generation quality. Represents optimal balance of capability and efficiency for most advanced applications.",
                 pricing: {
                     prompt: pricing(`$5.00 / 1M tokens`),
                     output: pricing(`$15.00 / 1M tokens`),
@@ -1388,7 +1425,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-4o-mini',
                 modelName: 'gpt-4o-mini',
-                modelDescription: 'Smaller, more cost-effective version of GPT-4o with good performance across text, vision, and audio tasks at reduced complexity.',
+                modelDescription: 'Smaller, more cost-effective version of GPT-4o with 128K context window. Maintains impressive capabilities across text, vision, and audio tasks while operating at significantly lower cost. Features 3x faster inference than GPT-4o with good performance on general tasks. Excellent for applications requiring good quality multimodal capabilities at scale.',
                 pricing: {
                     prompt: pricing(`$0.15 / 1M tokens`),
                     output: pricing(`$0.60 / 1M tokens`),
@@ -1400,7 +1437,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'o1-preview',
                 modelName: 'o1-preview',
-                modelDescription: 'Advanced reasoning model with exceptional performance on complex logical, mathematical, and analytical tasks. Built for deep reasoning and specialized professional tasks.',
+                modelDescription: 'Advanced reasoning model with 128K context window specializing in complex logical, mathematical, and analytical tasks. Features exceptional step-by-step problem-solving capabilities, advanced mathematical and scientific reasoning, and superior performance on STEM-focused problems. Significantly outperforms GPT-4 on quantitative reasoning benchmarks. Ideal for professional and specialized applications.',
                 pricing: {
                     prompt: pricing(`$15.00 / 1M tokens`),
                     output: pricing(`$60.00 / 1M tokens`),
@@ -1412,8 +1449,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'o1-preview-2024-09-12',
                 modelName: 'o1-preview-2024-09-12',
-                modelDescription: 'September 2024 version of O1 preview with specialized reasoning capabilities for complex tasks requiring precise analytical thinking.',
-                //             <- TODO: [💩] Some better system to organize these date suffixes and versions
+                modelDescription: 'September 2024 version of O1 preview with 128K context window. Features specialized reasoning capabilities with 30% improvement on mathematical and scientific accuracy over previous versions. Includes enhanced support for formal logic, statistical analysis, and technical domains. Optimized for professional applications requiring precise analytical thinking and rigorous methodologies.',
                 pricing: {
                     prompt: pricing(`$15.00 / 1M tokens`),
                     output: pricing(`$60.00 / 1M tokens`),
@@ -1425,7 +1461,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'o1-mini',
                 modelName: 'o1-mini',
-                modelDescription: 'Smaller, cost-effective version of the O1 model with good performance on reasoning tasks while maintaining efficiency for everyday analytical use.',
+                modelDescription: 'Smaller, cost-effective version of the O1 model with 128K context window. Maintains strong analytical reasoning abilities while reducing computational requirements by 70%. Features good performance on mathematical, logical, and scientific tasks at significantly lower cost than full O1. Excellent for everyday analytical applications that benefit from reasoning focus.',
                 pricing: {
                     prompt: pricing(`$3.00 / 1M tokens`),
                     output: pricing(`$12.00 / 1M tokens`),
@@ -1437,7 +1473,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'o1',
                 modelName: 'o1',
-                modelDescription: "OpenAI's advanced reasoning model focused on logic and problem-solving. Designed for complex analytical tasks with rigorous step-by-step reasoning. 128K context window.",
+                modelDescription: "OpenAI's advanced reasoning model with 128K context window focusing on logical problem-solving and analytical thinking. Features exceptional performance on quantitative tasks, step-by-step deduction, and complex technical problems. Maintains 95%+ of o1-preview capabilities with production-ready stability. Ideal for scientific computing, financial analysis, and professional applications.",
                 pricing: {
                     prompt: pricing(`$15.00 / 1M tokens`),
                     output: pricing(`$60.00 / 1M tokens`),
@@ -1449,11 +1485,10 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'o3-mini',
                 modelName: 'o3-mini',
-                modelDescription: 'Cost-effective reasoning model optimized for academic and scientific problem-solving. Efficient performance on STEM tasks with deep mathematical and scientific knowledge. 128K context window.',
+                modelDescription: 'Cost-effective reasoning model with 128K context window optimized for academic and scientific problem-solving. Features efficient performance on STEM tasks with specialized capabilities in mathematics, physics, chemistry, and computer science. Offers 80% of O1 performance on technical domains at significantly lower cost. Ideal for educational applications and research support.',
                 pricing: {
                     prompt: pricing(`$3.00 / 1M tokens`),
                     output: pricing(`$12.00 / 1M tokens`),
-                    // <- TODO: !! Unsure, check the pricing
                 },
             },
             /**/
@@ -1462,7 +1497,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'o1-mini-2024-09-12',
                 modelName: 'o1-mini-2024-09-12',
-                modelDescription: "September 2024 version of O1-mini with balanced reasoning capabilities and cost-efficiency. Good for analytical tasks that don't require the full O1 model.",
+                modelDescription: "September 2024 version of O1-mini with 128K context window featuring balanced reasoning capabilities and cost-efficiency. Includes 25% improvement in mathematical accuracy and enhanced performance on coding tasks compared to previous versions. Maintains efficient resource utilization while delivering improved results for analytical applications that don't require the full O1 model.",
                 pricing: {
                     prompt: pricing(`$3.00 / 1M tokens`),
                     output: pricing(`$12.00 / 1M tokens`),
@@ -1474,7 +1509,7 @@
                 modelVariant: 'CHAT',
                 modelTitle: 'gpt-3.5-turbo-16k-0613',
                 modelName: 'gpt-3.5-turbo-16k-0613',
-                modelDescription: 'June 2023 version of GPT-3.5 Turbo with extended 16k token context window for processing longer conversations and documents.',
+                modelDescription: "June 2023 version of GPT-3.5 Turbo with extended 16K token context window. Features good handling of longer conversations and documents with improved memory management across extended contexts. Includes knowledge cutoff from September 2021. Maintained for applications specifically designed for this version's behaviors and capabilities.",
                 pricing: {
                     prompt: pricing(`$3.00 / 1M tokens`),
                     output: pricing(`$4.00 / 1M tokens`),
@@ -2063,131 +2098,221 @@
     const OLLAMA_MODELS = exportJson({
         name: 'OLLAMA_MODELS',
         value: [
+            {
+                modelVariant: 'CHAT',
+                modelTitle: 'llama3',
+                modelName: 'llama3',
+                modelDescription: 'Meta Llama 3 (8B-70B parameters) with 8K context window. Latest generation foundation model with enhanced reasoning, instruction following, and factual accuracy. Superior performance to Llama 2 across all benchmarks with improved multilingual capabilities.',
+            },
+            {
+                modelVariant: 'CHAT',
+                modelTitle: 'llama3-chat',
+                modelName: 'llama3-chat',
+                modelDescription: 'Meta Llama 3 Chat with 8K context window, fine-tuned specifically for dialogue with significantly improved instruction following. Features enhanced safety guardrails and reduced hallucinations. Recommended over Llama 2 Chat for all conversational applications.',
+            },
+            {
+                modelVariant: 'CHAT',
+                modelTitle: 'llama3-instruct',
+                modelName: 'llama3-instruct',
+                modelDescription: 'Meta Llama 3 Instruct with 8K context window, fine-tuned for following specific instructions with precise outputs. Features improved structured response formatting and accurate completion of complex directives.',
+            },
+            {
+                modelVariant: 'CHAT',
+                modelTitle: 'codellama:13b',
+                modelName: 'codellama:13b',
+                modelDescription: 'Meta CodeLlama 13B with 16K context window, specialized foundation model for code generation and understanding. Supports multiple programming languages with strong contextual code completion capabilities.',
+            },
+            {
+                modelVariant: 'CHAT',
+                modelTitle: 'codellama:34b',
+                modelName: 'codellama:34b',
+                modelDescription: 'Meta CodeLlama 34B with 16K context window, larger code-specialized model with improved reasoning about complex programming tasks. Enhanced documentation generation and bug detection compared to smaller variants.',
+            },
+            {
+                modelVariant: 'CHAT',
+                modelTitle: 'phi3:mini',
+                modelName: 'phi3:mini',
+                modelDescription: 'Microsoft Phi-3 Mini (3.8B parameters) with 4K context window, highly efficient small language model with remarkable reasoning given its size. Performs competitively with much larger models on common benchmarks. Excellent for resource-constrained environments.',
+            },
+            {
+                modelVariant: 'CHAT',
+                modelTitle: 'phi3:medium',
+                modelName: 'phi3:medium',
+                modelDescription: 'Microsoft Phi-3 Medium (14B parameters) with 8K context window, balanced model offering strong performance with reasonable compute requirements. Features improved reasoning and factuality compared to Mini variant while maintaining efficiency.',
+            },
+            {
+                modelVariant: 'CHAT',
+                modelTitle: 'mistral-nemo',
+                modelName: 'mistral-nemo',
+                modelDescription: 'Mistral NeMo with 32K context window, open-source model optimized for enterprise use cases with improved reasoning and knowledge capabilities. Features strong performance on professional and domain-specific tasks.',
+            },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'llama2',
                 modelName: 'llama2',
-                modelDescription: 'Meta Llama 2, a general-purpose large language model.',
+                modelDescription: 'Meta Llama 2 (7B-70B parameters) with 4K context window. General-purpose foundation model balancing performance and efficiency for text generation and reasoning tasks. Suitable for most non-specialized applications. Note: Superseded by Llama 3 models which offer better performance.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'llama2-chat',
                 modelName: 'llama2-chat',
-                modelDescription: 'Meta Llama 2 Chat, optimized for conversational tasks.',
+                modelDescription: 'Meta Llama 2 Chat with 4K context window, fine-tuned specifically for conversational AI. Enhanced instruction following and safer responses compared to base model. Ideal for chatbots and interactive applications. Note: Consider using newer Llama 3 Chat for improved performance.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'alpaca-7b',
                 modelName: 'alpaca-7b',
-                modelDescription: 'Stanford Alpaca 7B, instruction-tuned LLaMA model.',
+                modelDescription: 'Stanford Alpaca 7B with 2K context window, instruction-tuned LLaMA model focused on following specific directions. Optimized for resource efficiency while maintaining good response quality. Suitable for lightweight applications.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'alpaca-30b',
                 modelName: 'alpaca-30b',
-                modelDescription: 'Stanford Alpaca 30B, larger instruction-tuned LLaMA model.',
+                modelDescription: 'Stanford Alpaca 30B with 2K context window. Larger instruction-tuned LLaMA model with improved reasoning and content generation capabilities. Better performance than 7B variant but requires more computational resources.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'vicuna-13b',
                 modelName: 'vicuna-13b',
-                modelDescription: 'Vicuna 13B, fine-tuned LLaMA for chat and instruction.',
+                modelDescription: 'Vicuna 13B with 2K context window, fine-tuned from LLaMA for chat and instruction following. Known for balanced performance, good conversational abilities, and improved helpfulness over base models. Popular for diverse conversational applications.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'falcon-7b',
                 modelName: 'falcon-7b',
-                modelDescription: 'Falcon 7B, a performant open large language model.',
+                modelDescription: 'Falcon 7B with 2K context window, performant open large language model trained on 1.5 trillion tokens. Strong on general knowledge tasks with smaller computational requirements. Good balance of performance and efficiency.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'falcon-40b',
                 modelName: 'falcon-40b',
-                modelDescription: 'Falcon 40B, a larger open large language model.',
+                modelDescription: 'Falcon 40B with 2K context window, larger open large language model with enhanced reasoning and knowledge capabilities. Significantly better performance than 7B version but requires substantially more resources. Suitable for complex generation tasks.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'bloom-7b',
                 modelName: 'bloom-7b',
-                modelDescription: 'BLOOM 7B, multilingual large language model.',
+                modelDescription: 'BLOOM 7B with 2K context window, multilingual large language model supporting 46+ languages. Trained for diverse linguistic capabilities across languages. Especially useful for non-English or multilingual applications.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'mistral-7b',
                 modelName: 'mistral-7b',
-                modelDescription: 'Mistral 7B, efficient and fast open LLM.',
+                modelDescription: 'Mistral 7B with 8K context window, efficient and fast open LLM with performance rivaling much larger models. Features Grouped-Query Attention for faster inference. Excellent balance of quality and speed for various applications.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'gorilla',
                 modelName: 'gorilla',
-                modelDescription: 'Gorilla, open-source LLM for tool use and APIs.',
+                modelDescription: 'Gorilla with 4K context window, specialized open-source LLM for tool use and API interaction. Fine-tuned to understand and generate API calls accurately. Optimal for agent applications that interact with external tools and services.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'cerebras-13b',
                 modelName: 'cerebras-13b',
-                modelDescription: 'Cerebras-GPT 13B, open large language model.',
+                modelDescription: 'Cerebras-GPT 13B with 2K context window, trained on diverse high-quality datasets. Good general-purpose capabilities with particular strengths in factual response accuracy. Well-suited for applications requiring reliable information.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'openchat-7b',
                 modelName: 'openchat-7b',
-                modelDescription: 'OpenChat 7B, fine-tuned for conversational tasks.',
+                modelDescription: 'OpenChat 7B with 4K context window, optimized for conversational abilities and instruction following. Outperforms many larger models on benchmark tasks while maintaining efficiency. Ideal for interactive applications with limited resources.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'openchat-13b',
                 modelName: 'openchat-13b',
-                modelDescription: 'OpenChat 13B, larger conversational LLM.',
+                modelDescription: 'OpenChat 13B with 4K context window, larger conversational LLM with enhanced reasoning, helpfulness, and knowledge. Significant improvement over 7B variant in complex tasks and nuanced conversations. Well-balanced for most conversational applications.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'mpt-7b-chat',
                 modelName: 'mpt-7b-chat',
-                modelDescription: 'MPT-7B Chat, optimized for dialogue and chat.',
+                modelDescription: 'MPT-7B Chat with 4K context window (extendable to 65K+), optimized for dialogue using high-quality conversation data. Features enhanced conversational abilities with strong safety alignments. Good for deployment in public-facing chat applications.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'mpt-7b-instruct',
                 modelName: 'mpt-7b-instruct',
-                modelDescription: 'MPT-7B Instruct, instruction-tuned variant.',
+                modelDescription: 'MPT-7B Instruct with 4K context window (extendable to 65K+), instruction-tuned variant optimized for following specific directives. Better than chat variant for single-turn instruction tasks. Well-suited for content generation and task completion.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'command-7b',
                 modelName: 'command-7b',
-                modelDescription: 'Command 7B, instruction-following LLM.',
+                modelDescription: 'Command 7B with 4K context window, instruction-following LLM tuned specifically for direct command execution and helpful responses. Optimized for clarity of outputs and following explicit directions. Good for practical task-oriented applications.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'starcoder',
                 modelName: 'starcoder',
-                modelDescription: 'StarCoder, code generation large language model.',
+                modelDescription: 'StarCoder with 8K context window, specialized code generation large language model trained on permissively licensed code. Supports 80+ programming languages. Optimized for code completion, generation, and understanding tasks.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'starcoder2',
                 modelName: 'starcoder2',
-                modelDescription: 'StarCoder2, improved code generation model.',
+                modelDescription: 'StarCoder2 with 16K context window, improved code generation model with better reasoning about code, debugging capabilities, and documentation generation. Supports 600+ programming languages. Ideal for complex software development assistance.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'mixtral-7b-chat',
                 modelName: 'mixtral-7b-chat',
-                modelDescription: 'Mixtral 7B Chat, Mixture-of-Experts conversational model.',
+                modelDescription: 'Mixtral 7B Chat with 32K context window, Mixture-of-Experts conversational model with strong performance across diverse tasks. Efficiently routes inputs to specialized sub-networks for optimal processing. Well-balanced for most chat applications.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'mixtral-8x7b',
                 modelName: 'mixtral-8x7b',
-                modelDescription: 'Mixtral 8x7B, Mixture-of-Experts large language model.',
+                modelDescription: 'Mixtral 8x7B with 32K context window, advanced Mixture-of-Experts architecture using 8 expert networks of 7B parameters each. Competitive with much larger dense models while using less computation. Excellent general-purpose capabilities.',
             },
             {
                 modelVariant: 'CHAT',
                 modelTitle: 'mixtral-8x7b-instruct',
                 modelName: 'mixtral-8x7b-instruct',
-                modelDescription: 'Mixtral 8x7B Instruct, instruction-tuned Mixture-of-Experts model.',
+                modelDescription: 'Mixtral 8x7B Instruct with 32K context window, instruction-tuned Mixture-of-Experts model for direct task execution. Enhanced directive following and more structured outputs compared to base model. Optimal for specific instruction-based workloads.',
+            },
+            {
+                modelVariant: 'CHAT',
+                modelTitle: 'neural-chat',
+                modelName: 'neural-chat',
+                modelDescription: 'Intel Neural Chat (latest) with 8K context window, optimized for Intel hardware with efficient inference. Balanced model for general-purpose conversational applications with good instruction following capabilities.',
+            },
+            {
+                modelVariant: 'CHAT',
+                modelTitle: 'qwen:7b',
+                modelName: 'qwen:7b',
+                modelDescription: 'Alibaba Qwen 7B with 8K context window. Versatile model with strong multilingual capabilities, particularly for Chinese and English. Features good reasoning and knowledge across diverse domains.',
+            },
+            {
+                modelVariant: 'CHAT',
+                modelTitle: 'qwen:14b',
+                modelName: 'qwen:14b',
+                modelDescription: 'Alibaba Qwen 14B with 8K context window. Enhanced version with improved reasoning and knowledge capabilities. Particularly strong in multilingual applications and domain-specific tasks requiring deeper understanding.',
+            },
+            {
+                modelVariant: 'CHAT',
+                modelTitle: 'gemma:2b',
+                modelName: 'gemma:2b',
+                modelDescription: 'Google Gemma 2B with 8K context window. Lightweight but capable model designed for efficiency. Good performance for its size on common tasks, ideal for resource-constrained environments and quick responses.',
+            },
+            {
+                modelVariant: 'CHAT',
+                modelTitle: 'gemma:7b',
+                modelName: 'gemma:7b',
+                modelDescription: 'Google Gemma 7B with 8K context window. Well-balanced model offering strong performance across general tasks while maintaining reasonable resource requirements. Good alternative to similar-sized models with competitive capabilities.',
+            },
+            {
+                modelVariant: 'CHAT',
+                modelTitle: 'dolphin-mixtral',
+                modelName: 'dolphin-mixtral',
+                modelDescription: 'Dolphin Mixtral with 32K context window. Community-tuned version of Mixtral with enhanced instruction following and creative capabilities. Maintains the MoE architecture while improving conversational abilities and reducing hallucinations.',
+            },
+            {
+                modelVariant: 'CHAT',
+                modelTitle: 'yi:34b-chat',
+                modelName: 'yi:34b-chat',
+                modelDescription: 'Yi 34B Chat with 4K context window. Large bilingual model with exceptional English and Chinese capabilities. Strong performance on reasoning, knowledge, and instruction following tasks that competes with much larger commercial models.',
             },
             // <- [🕕]
         ],
@@ -2215,7 +2340,7 @@
             const openAiCompatibleOptions = {
                 baseURL: DEFAULT_OLLAMA_BASE_URL,
                 ...ollamaOptions,
-                userId: 'ollama',
+                apiKey: 'ollama',
             };
             super(openAiCompatibleOptions);
         }
@@ -2274,6 +2399,9 @@
      * @public exported from `@promptbook/ollama`
      */
     const createOllamaExecutionTools = Object.assign((options) => {
+        if (($isRunningInBrowser() || $isRunningInWebWorker()) && !options.dangerouslyAllowBrowser) {
+            options = { ...options, dangerouslyAllowBrowser: true };
+        }
         return new OllamaExecutionTools(options);
     }, {
         packageName: '@promptbook/ollama',