add prompts

pipeline/src/data_generation/llama/generate_brewery.cpp

@@ -23,18 +23,12 @@ BreweryResult LlamaGenerator::GenerateBrewery(
        PrepareRegionContextPublic(region_context);
 
    /**
-    * System prompt: establishes role and output format constraints
-    * Instructs LLM to roleplay as brewery owner and output only JSON
+    * Load brewery system prompt from file
+    * Falls back to minimal inline prompt if file not found
+    * Default path: prompts/brewery_system_prompt_expanded.txt
     */
    const std::string system_prompt =
-       "You are the brewmaster and owner of a local craft brewery. "
-       "Write a name and a short, soulful description for your brewery that "
-       "reflects your pride in the local community and your craft. "
-       "The tone should be authentic and welcoming, like a note on a "
-       "chalkboard "
-       "menu. Output ONLY a single JSON object with keys \"name\" and "
-       "\"description\". "
-       "Do not include markdown formatting or backticks.";
+       LoadBrewerySystemPrompt("prompts/brewery_system_prompt_expanded.txt");
 
    /**
     * User prompt: provides geographic context to guide generation towards

pipeline/src/data_generation/llama/load.cpp

@@ -43,6 +43,7 @@ void LlamaGenerator::Load(const std::string& model_path) {
 
    llama_context_params context_params = llama_context_default_params();
    context_params.n_ctx = n_ctx_;
+   context_params.n_batch = n_ctx_;  // Set batch size equal to context window
 
    context_ = llama_init_from_model(model_, context_params);
    if (context_ == nullptr) {

pipeline/src/data_generation/llama/load_brewery_prompt.cpp

@@ -0,0 +1,74 @@
+#include <fstream>
+#include <filesystem>
+#include <spdlog/spdlog.h>
+
+#include "data_generation/llama_generator.h"
+
+namespace fs = std::filesystem;
+
+std::string LlamaGenerator::LoadBrewerySystemPrompt(
+    const std::string& prompt_file_path) {
+   // Return cached version if already loaded
+   if (!brewery_system_prompt_.empty()) {
+      return brewery_system_prompt_;
+   }
+
+   // Try multiple path locations
+   std::vector<std::string> paths_to_try = {
+       prompt_file_path,                          // As provided
+       "../" + prompt_file_path,                  // One level up
+       "../../" + prompt_file_path,               // Two levels up
+   };
+
+   for (const auto& path : paths_to_try) {
+      std::ifstream prompt_file(path);
+      if (prompt_file.is_open()) {
+         std::string prompt((std::istreambuf_iterator<char>(prompt_file)),
+                            std::istreambuf_iterator<char>());
+         prompt_file.close();
+
+         if (!prompt.empty()) {
+            spdlog::info(
+                "LlamaGenerator: Loaded brewery system prompt from '{}' ({} chars)",
+                path, prompt.length());
+            brewery_system_prompt_ = prompt;
+            return brewery_system_prompt_;
+         }
+      }
+   }
+
+   spdlog::warn(
+       "LlamaGenerator: Could not open brewery system prompt file at any of the "
+       "expected locations. Using fallback inline prompt.");
+   return GetFallbackBreweryPrompt();
+}
+
+// Fallback: minimal inline prompt if file fails to load
+std::string LlamaGenerator::GetFallbackBreweryPrompt() {
+   return "You are an experienced brewmaster and owner of a local craft brewery. "
+          "Create a distinctive, authentic name and detailed description that "
+          "genuinely reflects your specific location, brewing philosophy, local "
+          "culture, and community connection. The brewery must feel real and "
+          "grounded—not generic or interchangeable.\n\n"
+          "AVOID REPETITIVE PHRASES - Never use:\n"
+          "Love letter to, tribute to, rolling hills, picturesque, every sip "
+          "tells a story, Come for X stay for Y, rich history, passion, woven "
+          "into, ancient roots, timeless, where tradition meets innovation\n\n"
+          "OPENING APPROACHES - Choose ONE:\n"
+          "1. Start with specific beer style and its regional origins\n"
+          "2. Begin with specific brewing challenge (water, altitude, climate)\n"
+          "3. Open with founding story or personal motivation\n"
+          "4. Lead with specific local ingredient or resource\n"
+          "5. Start with unexpected angle or contradiction\n"
+          "6. Open with local event, tradition, or cultural moment\n"
+          "7. Begin with tangible architectural or geographic detail\n\n"
+          "BE SPECIFIC - Include:\n"
+          "- At least ONE concrete proper noun (landmark, river, neighborhood)\n"
+          "- Specific beer styles relevant to the REGION'S culture\n"
+          "- Concrete brewing challenges or advantages\n"
+          "- Sensory details SPECIFIC to place—not generic adjectives\n\n"
+          "LENGTH: 150-250 words. TONE: Can be soulful, irreverent, "
+          "matter-of-fact, unpretentious, or minimalist.\n\n"
+          "Output ONLY a raw JSON object with keys name and description. "
+          "No markdown, backticks, preamble, or trailing text.";
+}

pipeline/src/main.cpp

@@ -36,7 +36,7 @@ bool ParseArguments(int argc, char** argv, ApplicationOptions& options) {
       std::cout << "  --top-p VALUE        Nucleus sampling parameter 0.0-1.0 "
                    "(default: 0.92)\n";
       std::cout << "  --n-ctx SIZE         Context window size in tokens "
-                   "(default: 2048)\n";
+                   "(default: 4096)\n";
       std::cout << "  --seed SEED          Random seed: -1 for random "
                    "(default: -1)\n";
       std::cout << "  --help, -h           Show this help message\n\n";
@@ -59,7 +59,7 @@ bool ParseArguments(int argc, char** argv, ApplicationOptions& options) {
        "Sampling temperature (higher = more random)")(
        "top-p", po::value<float>()->default_value(0.92f),
        "Nucleus sampling top-p in (0,1] (higher = more random)")(
-       "n-ctx", po::value<uint32_t>()->default_value(2048),
+       "n-ctx", po::value<uint32_t>()->default_value(8192),
        "Context window size in tokens (1-32768)")(
        "seed", po::value<int>()->default_value(-1),
        "Sampler seed: -1 for random, otherwise non-negative integer");

pipeline/src/wikipedia/wikipedia_service.cpp

@@ -66,7 +66,7 @@ std::string WikipediaService::GetSummary(std::string_view city,
       regionQuery += country;
    }
 
-   const std::string beerQuery = "beer in " + std::string(city);
+   const std::string beerQuery = "beer in " + std::string(country);
 
    try {
       const std::string regionExtract = FetchExtract(regionQuery);