Add singleheader and tests for generation with context.

jmont-dev · Aug 18, 2024 · de85c5b · de85c5b
1 parent 7de8114
commit de85c5b
Show file tree

Hide file tree

Showing 2 changed files with 43 additions and 1 deletion.
diff --git a/singleheader/ollama.hpp b/singleheader/ollama.hpp
@@ -35171,6 +35171,13 @@ class Ollama
         Ollama(): Ollama("http://localhost:11434") {}
         ~Ollama() { delete this->cli; }
 
+    ollama::response generate(const std::string& model,const std::string& prompt, const ollama::response& context, const json& options=nullptr, const std::vector<std::string>& images=std::vector<std::string>())
+    {
+        ollama::request request(model, prompt, options, false, images);
+        if ( context.as_json().contains("context") ) request["context"] = context.as_json()["context"];
+        return generate(request);
+    }
+
     ollama::response generate(const std::string& model,const std::string& prompt, const json& options=nullptr, const std::vector<std::string>& images=std::vector<std::string>())
     {
         ollama::request request(model, prompt, options, false, images);
@@ -35201,6 +35208,13 @@ class Ollama
         return response;        
     }
 
+    bool generate(const std::string& model,const std::string& prompt, ollama::response& context, std::function<void(const ollama::response&)> on_receive_token, const json& options=nullptr, const std::vector<std::string>& images=std::vector<std::string>())
+    {
+        ollama::request request(model, prompt, options, true, images);
+        if ( context.as_json().contains("context") ) request["context"] = context.as_json()["context"];
+        return generate(request, on_receive_token);
+    }
+
     bool generate(const std::string& model,const std::string& prompt, std::function<void(const ollama::response&)> on_receive_token, const json& options=nullptr, const std::vector<std::string>& images=std::vector<std::string>())
     {
         ollama::request request(model, prompt, options, true, images);
@@ -35640,11 +35654,16 @@ namespace ollama
         ollama.setServerURL(server_url);
     }
 
-    inline ollama::response generate(const std::string& model,const std::string& prompt,const json& options=nullptr, const std::vector<std::string>& images=std::vector<std::string>())
+    inline ollama::response generate(const std::string& model, const std::string& prompt, const json& options=nullptr, const std::vector<std::string>& images=std::vector<std::string>())
     {
         return ollama.generate(model, prompt, options, images);
     }
 
+    ollama::response generate(const std::string& model,const std::string& prompt, const ollama::response& context, const json& options=nullptr, const std::vector<std::string>& images=std::vector<std::string>())
+    {
+        return ollama.generate(model, prompt, context, options, images);
+    }
+
     inline ollama::response generate(const ollama::request& request)
     {
         return ollama.generate(request);
@@ -35655,6 +35674,11 @@ namespace ollama
         return ollama.generate(model, prompt, on_receive_response, options, images);
     }
 
+    inline bool generate(const std::string& model,const std::string& prompt, ollama::response& context, std::function<void(const ollama::response&)> on_receive_response, const json& options=nullptr, const std::vector<std::string>& images=std::vector<std::string>())
+    {
+        return ollama.generate(model, prompt, context, on_receive_response, options, images);
+    }
+
     inline bool generate(ollama::request& request, std::function<void(const ollama::response&)> on_receive_response)
     {
         return ollama.generate(request, on_receive_response);

diff --git a/test/test.cpp b/test/test.cpp
@@ -108,6 +108,14 @@ TEST_SUITE("Ollama Tests") {
         CHECK( response.as_json().contains("response") == true );
     }
 
+    TEST_CASE("Generation with Context") {
+
+        ollama::response context = ollama::generate(test_model, "Why is the sky blue?", options);
+
+        ollama::response response = ollama::generate(test_model, "Tell me more about this.", context, options);
+
+        CHECK( response.as_json().contains("response") == true );
+    }
 
     std::atomic<bool> done{false};
     std::string streamed_response;
@@ -130,6 +138,16 @@ TEST_SUITE("Ollama Tests") {
         CHECK( streamed_response != "" );
     }
 
+    TEST_CASE("Streaming Generation with Context") {
+
+        ollama::response context = ollama::generate(test_model, "Why is the sky blue?", options);
+
+        std::function<void(const ollama::response&)> response_callback = on_receive_response;  
+        ollama::generate(test_model, "Tell me more about this.", context, response_callback, options);
+
+        CHECK( streamed_response!="" );
+    }
+
     TEST_CASE("Non-Singleton Generation") {
 
         Ollama my_ollama_server("http://localhost:11434");