Enhance CLI with transport functionality and logging support and added multiple provider versioning

Author: ProgramComputer

Makefile

@@ -9,7 +9,8 @@ else
     CFLAGS += -O2
 endif
 
-LDFLAGS = -lm -lssl -lcrypto -lgit2 -lnpy_array
+# Add curl for HTTP transport
+LDFLAGS = -lm -lssl -lcrypto -lgit2 -lnpy_array -lcurl
 
 # Installation paths - default to user-local installation
 PREFIX ?= $(HOME)/.local
@@ -31,6 +32,9 @@ CORE_OBJS = $(CORE_SRCS:$(SRC_DIR)/%.c=$(OBJ_DIR)/%.o)
 CLI_OBJS = $(CLI_SRCS:src/cli/%.c=$(OBJ_DIR)/cli_%.o)
 OBJS = $(CORE_OBJS) $(CLI_OBJS)
 
+# Additional dependencies for transport
+TRANSPORT_DEPS = $(OBJ_DIR)/transport.o $(OBJ_DIR)/transport_ssh.o $(OBJ_DIR)/transport_http.o $(OBJ_DIR)/transport_local.o
+
 # Test files
 TEST_SRCS = $(wildcard $(TEST_DIR)/*.c)
 TEST_OBJS = $(TEST_SRCS:$(TEST_DIR)/%.c=$(OBJ_DIR)/%.o)
@@ -41,7 +45,7 @@ TARGET = $(BIN_DIR)/embedding_bridge
 LIB_TARGET = $(LIB_DIR)/libembedding_bridge.so
 
 # Main targets
-.PHONY: all clean test lib python-test valgrind memtest test-registry test-all test-c
+.PHONY: all clean test lib python-test valgrind memtest test-registry test-all test-c test-transport
 
 all: $(TARGET) lib
 
@@ -50,7 +54,7 @@ lib: $(LIB_TARGET)
 # Test targets organized by type
 test-all: test-c python-test
 
-test-c: memtest test-registry
+test-c: memtest test-registry test-transport
 	@echo "All C tests completed successfully"
 
 test: test-all
@@ -59,6 +63,10 @@ test-registry: $(TEST_BIN_DIR)/test_model_registry
 	@echo "Running model registry tests..."
 	$(TEST_BIN_DIR)/test_model_registry
 
+test-transport: $(TEST_BIN_DIR)/test_transport
+	@echo "Running transport tests..."
+	$(TEST_BIN_DIR)/test_transport
+
 python-test: install
 	@echo "Running Python CLI tests..."
 	DEBUG=1 PYTHONPATH=src/python:. LD_LIBRARY_PATH=lib pytest tests/python/test_cli.py -v -s
@@ -71,6 +79,10 @@ $(TEST_BIN_DIR)/test_lib: $(OBJ_DIR)/test_lib.o $(OBJ_DIR)/store.o $(OBJ_DIR)/er
 	@mkdir -p $(TEST_BIN_DIR)
 	$(CC) $^ -o $@ $(LDFLAGS)
 
+$(TEST_BIN_DIR)/test_transport: $(OBJ_DIR)/test_transport.o $(TRANSPORT_DEPS) $(OBJ_DIR)/error.o $(OBJ_DIR)/debug.o $(OBJ_DIR)/config.o $(OBJ_DIR)/fs.o
+	@mkdir -p $(TEST_BIN_DIR)
+	$(CC) $^ -o $@ $(LDFLAGS)
+
 valgrind: memtest
 	@echo "Running Valgrind memory leak check on library..."
 	valgrind --leak-check=full --show-leak-kinds=all --track-origins=yes --error-exitcode=1 $(TEST_BIN_DIR)/test_lib

README.md

@@ -9,6 +9,8 @@ A command-line tool for managing and versioning embedding vectors. Think of it a
 - Track embedding history and changes
 - Roll back to previous embedding versions
 - Support for multiple embedding models
+- Organize embeddings into sets for better management
+- Prepare for remote collaboration (coming soon)
 
 ## Installation
 
@@ -21,6 +23,9 @@ make DEBUG=0 install
 ## Quick Start
 
 ```bash
+# Initialize
+eb init
+
 # Register a model
 eb model register text-embedding-3-small --dimensions 1536 --normalize
 
@@ -35,6 +40,10 @@ eb diff <hash1> <hash2>
 
 # Roll back to previous version
 eb rollback <hash> document.txt
+
+# Create and manage sets
+eb set create experimental
+eb set switch experimental
 ```
 
 ## Core Commands
@@ -67,6 +76,46 @@ eb diff <hash1> <hash2>
 eb rollback <hash> file.txt
 ```
 
+### Set Management
+```bash
+# Create a new set of embeddings
+eb set create <name> [--desc="Description"] [--base=<base-set>]
+
+# List available sets
+eb set list
+eb set list --verbose
+
+# Switch between sets
+eb set switch <name>
+
+# Show current set status
+eb set status
+
+# Compare differences between sets
+eb set diff <set1> <set2>
+
+# Merge sets (future functionality)
+eb set merge <source-set> [--target=<target-set>] [--strategy=<strategy>]
+
+# Delete a set
+eb set delete <name> [--force]
+```
+
+### Remote Operations (Future Functionality)
+```bash
+# Add a remote
+eb remote add <name> <url>
+
+# List remote sets
+eb remote sets <remote>
+
+# Push a set to remote
+eb remote push <set-name> [remote]
+
+# Pull a set from remote
+eb remote pull <set-name> [remote]
+```
+
 ## Contributing
 
 We welcome contributions! Please see our [Contributing Guidelines](CONTRIBUTING.md) for details.

src/cli/cli.c

@@ -8,6 +8,7 @@
 #include "colors.h"
 #include "../core/error.h"
 #include "rollback.h"
+#include "log.h"
 
 bool has_option(int argc, char** argv, const char* option) {
     for (int i = 1; i < argc; i++) {
@@ -58,6 +59,15 @@ void cli_warning(const char* fmt, ...) {
     va_end(args);
 }
 
+void cli_info(const char* fmt, ...) {
+    va_list args;
+    va_start(args, fmt);
+    fprintf(stderr, "%sinfo:%s ", COLOR_BLUE, COLOR_RESET);
+    vfprintf(stderr, fmt, args);
+    fprintf(stderr, "\n");
+    va_end(args);
+}
+
 bool is_option_with_value(const char* arg) {
     return (strcmp(arg, "-m") == 0 || strcmp(arg, "--model") == 0 ||
             strcmp(arg, "-t") == 0 || strcmp(arg, "--threshold") == 0 ||
@@ -141,5 +151,6 @@ static const eb_command_t commands[] = {
     {"model", "Manage embedding models", cmd_model},
     {"rollback", "Revert to a previous embedding version", cmd_rollback},
     {"status", "Show embedding status for a source file", cmd_status},
+    {"log", "Display embedding log for files", cmd_log},
     {NULL, NULL, NULL}
 }; 

src/cli/cli.h

@@ -31,6 +31,8 @@ typedef struct {
 
 typedef struct {
     const char* model;          // Model to use for embedding
+    const char* models;         // Models to use for diff (comma-separated)
+    const char* second_model;   // Second model parsed from models
     bool use_git;              // Whether to use Git integration
     bool use_file;             // Use file as input (for query)
     bool use_color;            // Use colored output
@@ -56,6 +58,11 @@ int cmd_remote(int argc, char** argv);
 int cmd_model(int argc, char** argv);
 int cmd_rollback(int argc, char** argv);
 int cmd_status(int argc, char **argv);
+int cmd_log(int argc, char **argv);
+int cmd_set(int argc, char **argv);
+int cmd_switch(int argc, char **argv);
+int cmd_merge(int argc, char **argv);
+int cmd_gc(int argc, char **argv);
 
 // Option parsing
 bool parse_cli_options(int argc, char** argv, eb_cli_options_t* opts);
@@ -71,15 +78,17 @@ const char* get_model(int argc, char** argv);
 void handle_error(eb_status_t status, const char* context);
 void cli_error(const char* fmt, ...);
 void cli_warning(const char* fmt, ...);
+void cli_info(const char* fmt, ...);
 
 // Store operation functions
 /* Store precomputed embedding file
  * @param embedding_file: Path to the precomputed embedding (.bin or .npy)
  * @param dims: Number of dimensions (0 for .npy auto-detect)
  * @param source_file: Original source file
+ * @param model: Model/provider name (can be NULL)
  * @return: 0 on success, 1 on error
  */
-int store_precomputed(const char *embedding_file, size_t dims, const char *source_file);
+int store_precomputed(const char *embedding_file, size_t dims, const char *source_file, const char *model);
 
 /* Store embedding from source file
  * @param source_file: Source file to generate embedding from