mfcli 0.2.5__tar.gz → 0.2.7__tar.gz

{mfcli-0.2.5 → mfcli-0.2.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mfcli
-Version: 0.2.5
+Version: 0.2.7
 Summary: AI-powered CLI for analyzing hardware engineering documents
 Author: Multifactor AI
 License: MIT
@@ -32,8 +32,6 @@ Requires-Dist: botocore
 Requires-Dist: pydantic==2.11.9
 Requires-Dist: protobuf
 Requires-Dist: sqlmodel
-Requires-Dist: llama-parse
-Requires-Dist: llama-index-core
 Requires-Dist: requests
 Requires-Dist: openai
 Requires-Dist: langchain
@@ -75,6 +73,7 @@ An AI-powered engineering document processing pipeline that intelligently analyz
 
 ## 📋 Table of Contents
 
+- [Quick Start](#quick-start)
 - [Architecture](#architecture)
 - [Prerequisites](#prerequisites)
 - [Installation](#installation)
@@ -89,6 +88,23 @@ An AI-powered engineering document processing pipeline that intelligently analyz
 - [Development](#development)
 - [Troubleshooting](#troubleshooting)
 
+## 🚀 Quick Start
+
+**New to mfcli?** Check out our **[Quick Start Guide](QUICKSTART.md)** for step-by-step instructions to get up and running in minutes!
+
+The Quick Start Guide covers:
+- ✅ Installing Cline for VS Code
+- ✅ Installing mfcli with pipx (recommended)
+- ✅ Setting up API keys
+- ✅ Creating your first project
+- ✅ Processing your hardware documents
+- ✅ Querying your knowledge base with AI
+- ✅ Currently unsupported features and workarounds
+
+**[👉 Go to Quick Start Guide →](QUICKSTART.md)**
+
+---
+
 ## 🏗️ Architecture
 
 The system uses a streamlined architecture with a single controller agent that orchestrates a sequential processing pipeline:
@@ -96,7 +112,7 @@ The system uses a streamlined architecture with a single controller agent that o
 ```
 Controller Agent
 ├── Tools:
-│   ├── run_pipeline (Sequential pipeline execution)
+│   ├── run (Sequential pipeline execution)
 │   └── query_knowledgebase (RAG-based document queries)
 │
 └── Pipeline Stages:
@@ -360,18 +376,18 @@ mfcli init
 ```
 
 You'll be prompted to enter a project name (3-45 characters, alphanumeric with underscores/hyphens allowed). If your directory is a git repository, the repository name will be suggested as the default - simply press Enter to accept it or type a different name. This creates a `multifactor/` folder at the git root (or current directory) containing:
-- `context/` - **Place your hardware design files here for processing**
+- `design/` - **Place your hardware design files here for processing**
 - `config.json` - Project configuration with your project name
 - `file_docket.json` - File tracking and metadata
 - `generated_files/`, `hw_cheat_sheets/`, `data_sheets/`, etc. - Output folders
 
-**3. Place your files in the context folder:**
+**3. Place your files in the design folder:**
 
 ```bash
-# Copy or move your hardware design files to the context folder
+# Copy or move your hardware design files to the design folder
 # Example for git repo at C:\git\my-project\:
-copy *.pdf C:\git\my-project\multifactor\context\
-copy *.csv C:\git\my-project\multifactor\context\
+copy *.pdf C:\git\my-project\multifactor\design\
+copy *.csv C:\git\my-project\multifactor\design\
 ```
 
 **4. Run the pipeline:**
@@ -381,7 +397,7 @@ mfcli run
 ```
 
 This will:
-- Process all supported files in the `multifactor/context/` directory
+- Process all supported files in the `multifactor/design/` directory
 - Skip files that have already been processed (matching MD5 checksum)
 - Prompt for confirmation if a file has been modified (different MD5)
 - Generate BOM CSV files (if schematics are found)
@@ -416,9 +432,56 @@ This ensures efficient processing by only analyzing new or changed files, while
 The `mfcli` tool provides the following commands:
 
 - **`mfcli init`** - Initialize a new project in the current directory
-- **`mfcli run_pipeline`** - Run the analysis pipeline on the current directory
+- **`mfcli run`** - Run the analysis pipeline on the current directory
 - **`mfcli web [--port PORT]`** - Start the web UI (default port: 9999)
-- **`mfcli addfile FILE [--purpose PURPOSE]`** - Add a file to ChromaDB knowledge base
+- **`mfcli add FILE [--purpose PURPOSE]`** - Add a file to ChromaDB knowledge base
+- **`mfcli ls`** - List all files that have been vectorized into the knowledge base
+- **`mfcli rm FILENAME [--yes]`** - Remove files from the knowledge base by filename
+- **`mfcli configure [--check]`** - Interactive setup wizard to configure API keys and settings
+- **`mfcli log-level LEVEL`** - Set the logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL)
+- **`mfcli setup-mcp`** - Auto-configure MCP server for Cline and Claude Code
+- **`mfcli doctor`** - Run system health checks and diagnose issues
+- **`mfcli clean [--accept] [--all]`** - Clean all mfcli app data
+- **`mfcli pre-uninstall`** - Check for running processes before uninstallation
+
+#### Configure Logging Level
+
+Set the logging verbosity level for mfcli operations:
+
+```bash
+# Set to DEBUG for detailed troubleshooting
+mfcli log-level DEBUG
+
+# Set to INFO for normal operation (default)
+mfcli log-level INFO
+
+# Set to WARNING to only see warnings and errors
+mfcli log-level WARNING
+
+# Set to ERROR to only see errors
+mfcli log-level ERROR
+
+# Set to CRITICAL for only critical errors
+mfcli log-level CRITICAL
+```
+
+The log level setting is stored in your configuration file (`~/Multifactor/.env`) and will take effect on the next mfcli command. This is particularly useful when:
+- **DEBUG**: Troubleshooting issues or understanding detailed pipeline operations
+- **INFO**: Normal day-to-day operation with informative messages
+- **WARNING**: Production use where you only want to see potential issues
+- **ERROR**: When you only care about actual errors
+
+**Example:**
+```bash
+# Enable detailed logging for troubleshooting
+mfcli log-level DEBUG
+
+# Run the pipeline with verbose output
+mfcli run
+
+# Return to normal logging
+mfcli log-level INFO
+```
 
 #### Start Web UI
 
@@ -519,7 +582,7 @@ To use the MCP server with Cline (or other MCP-compatible clients), add the foll
    ```bash
    cd /path/to/hardware/files
    mfcli init
-   mfcli run_pipeline
+   mfcli run
    ```
 
 3. **Add the MCP configuration** to your Cline/Claude settings file (see Configuration above)
@@ -543,7 +606,7 @@ To use the MCP server with Cline (or other MCP-compatible clients), add the foll
 - **Solution**: Run the pipeline at least once to create the vector database:
   ```bash
   mfcli init
-  mfcli run_pipeline
+  mfcli run
   ```
 
 **Error**: `MCP server timeout`
@@ -666,12 +729,11 @@ Created within a **"multifactor"** folder at the **git repository root** if you'
 └── multifactor/                 # Parent folder for all project files and outputs
     ├── config.json              # Project configuration (project name, etc.)
     ├── file_docket.json         # File tracking and processing metadata
-    ├── context/                 # Place your hardware design files here for processing
+    ├── design/                  # Place your hardware design files here for processing
     ├── generated_files/         # BOM CSV files generated from schematics
     ├── hw_cheat_sheets/         # JSON cheat sheets (MCU, errata, debug, functional blocks)
     ├── data_sheets/             # Downloaded component datasheets (from BOM processing)
     ├── pdf_parts/               # Extracted PDF parts for analysis
-    ├── agent_instructions/      # (Reserved for future use)
     ├── fw_tasks/                # (Reserved for future use)
     └── requirements/            # (Reserved for future use)
 ```
@@ -682,7 +744,7 @@ If you're in a git repository at `C:\git\my-hardware-project\` and run `mfcli in
 
 - `C:\git\my-hardware-project\multifactor\config.json` - Project configuration
 - `C:\git\my-hardware-project\multifactor\file_docket.json` - File tracking
-- `C:\git\my-hardware-project\multifactor\context\` - Place source files here
+- `C:\git\my-hardware-project\multifactor\design\` - Place source files here
 - `C:\git\my-hardware-project\multifactor\generated_files\` - Generated BOM files
 - `C:\git\my-hardware-project\multifactor\hw_cheat_sheets\` - Cheat sheets
 - `C:\git\my-hardware-project\multifactor\data_sheets\` - Downloaded datasheets
@@ -694,7 +756,7 @@ If you're NOT in a git repository and run `mfcli init` from `C:\Projects\hardwar
 
 - `C:\Projects\hardware\board_v1\multifactor\config.json` - Project configuration
 - `C:\Projects\hardware\board_v1\multifactor\file_docket.json` - File tracking
-- `C:\Projects\hardware\board_v1\multifactor\context\` - Place source files here
+- `C:\Projects\hardware\board_v1\multifactor\design\` - Place source files here
 - `C:\Projects\hardware\board_v1\multifactor\generated_files\` - Generated BOM files
 - `C:\Projects\hardware\board_v1\multifactor\hw_cheat_sheets\` - Cheat sheets
 - `C:\Projects\hardware\board_v1\multifactor\data_sheets\` - Downloaded datasheets
@@ -805,7 +867,7 @@ First, navigate to your hardware files directory and initialize:
 ```bash
 cd /path/to/hardware/files
 mfcli init
-mfcli run_pipeline
+mfcli run
 ```
 
 ### Starting the Web UI
@@ -902,10 +964,10 @@ pytest app/tests/
 #### 4. Pipeline Processing Failures
 
 **Error**: `Could not find metadata file. Please initialize this repo with "mfcli init"`
-- **Solution**: You need to run `mfcli init` in your hardware files directory before running `mfcli run_pipeline`
+- **Solution**: You need to run `mfcli init` in your hardware files directory before running `mfcli run`
 
 **Error**: `File not found`
-- **Solution**: Make sure you're running `mfcli run_pipeline` from within your hardware files directory (where you ran `mfcli init`)
+- **Solution**: Make sure you're running `mfcli run` from within your hardware files directory (where you ran `mfcli init`)
 
 **Error**: `File extension is not supported`
 - **Solution**: Check that your files are in supported formats (PDF, EDIF, CSV, .net, .cir, .asc)

{mfcli-0.2.5 → mfcli-0.2.7}/README.md

@@ -17,6 +17,7 @@ An AI-powered engineering document processing pipeline that intelligently analyz
 
 ## 📋 Table of Contents
 
+- [Quick Start](#quick-start)
 - [Architecture](#architecture)
 - [Prerequisites](#prerequisites)
 - [Installation](#installation)
@@ -31,6 +32,23 @@ An AI-powered engineering document processing pipeline that intelligently analyz
 - [Development](#development)
 - [Troubleshooting](#troubleshooting)
 
+## 🚀 Quick Start
+
+**New to mfcli?** Check out our **[Quick Start Guide](QUICKSTART.md)** for step-by-step instructions to get up and running in minutes!
+
+The Quick Start Guide covers:
+- ✅ Installing Cline for VS Code
+- ✅ Installing mfcli with pipx (recommended)
+- ✅ Setting up API keys
+- ✅ Creating your first project
+- ✅ Processing your hardware documents
+- ✅ Querying your knowledge base with AI
+- ✅ Currently unsupported features and workarounds
+
+**[👉 Go to Quick Start Guide →](QUICKSTART.md)**
+
+---
+
 ## 🏗️ Architecture
 
 The system uses a streamlined architecture with a single controller agent that orchestrates a sequential processing pipeline:
@@ -38,7 +56,7 @@ The system uses a streamlined architecture with a single controller agent that o
 ```
 Controller Agent
 ├── Tools:
-│   ├── run_pipeline (Sequential pipeline execution)
+│   ├── run (Sequential pipeline execution)
 │   └── query_knowledgebase (RAG-based document queries)
 │
 └── Pipeline Stages:
@@ -302,18 +320,18 @@ mfcli init
 ```
 
 You'll be prompted to enter a project name (3-45 characters, alphanumeric with underscores/hyphens allowed). If your directory is a git repository, the repository name will be suggested as the default - simply press Enter to accept it or type a different name. This creates a `multifactor/` folder at the git root (or current directory) containing:
-- `context/` - **Place your hardware design files here for processing**
+- `design/` - **Place your hardware design files here for processing**
 - `config.json` - Project configuration with your project name
 - `file_docket.json` - File tracking and metadata
 - `generated_files/`, `hw_cheat_sheets/`, `data_sheets/`, etc. - Output folders
 
-**3. Place your files in the context folder:**
+**3. Place your files in the design folder:**
 
 ```bash
-# Copy or move your hardware design files to the context folder
+# Copy or move your hardware design files to the design folder
 # Example for git repo at C:\git\my-project\:
-copy *.pdf C:\git\my-project\multifactor\context\
-copy *.csv C:\git\my-project\multifactor\context\
+copy *.pdf C:\git\my-project\multifactor\design\
+copy *.csv C:\git\my-project\multifactor\design\
 ```
 
 **4. Run the pipeline:**
@@ -323,7 +341,7 @@ mfcli run
 ```
 
 This will:
-- Process all supported files in the `multifactor/context/` directory
+- Process all supported files in the `multifactor/design/` directory
 - Skip files that have already been processed (matching MD5 checksum)
 - Prompt for confirmation if a file has been modified (different MD5)
 - Generate BOM CSV files (if schematics are found)
@@ -358,9 +376,56 @@ This ensures efficient processing by only analyzing new or changed files, while
 The `mfcli` tool provides the following commands:
 
 - **`mfcli init`** - Initialize a new project in the current directory
-- **`mfcli run_pipeline`** - Run the analysis pipeline on the current directory
+- **`mfcli run`** - Run the analysis pipeline on the current directory
 - **`mfcli web [--port PORT]`** - Start the web UI (default port: 9999)
-- **`mfcli addfile FILE [--purpose PURPOSE]`** - Add a file to ChromaDB knowledge base
+- **`mfcli add FILE [--purpose PURPOSE]`** - Add a file to ChromaDB knowledge base
+- **`mfcli ls`** - List all files that have been vectorized into the knowledge base
+- **`mfcli rm FILENAME [--yes]`** - Remove files from the knowledge base by filename
+- **`mfcli configure [--check]`** - Interactive setup wizard to configure API keys and settings
+- **`mfcli log-level LEVEL`** - Set the logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL)
+- **`mfcli setup-mcp`** - Auto-configure MCP server for Cline and Claude Code
+- **`mfcli doctor`** - Run system health checks and diagnose issues
+- **`mfcli clean [--accept] [--all]`** - Clean all mfcli app data
+- **`mfcli pre-uninstall`** - Check for running processes before uninstallation
+
+#### Configure Logging Level
+
+Set the logging verbosity level for mfcli operations:
+
+```bash
+# Set to DEBUG for detailed troubleshooting
+mfcli log-level DEBUG
+
+# Set to INFO for normal operation (default)
+mfcli log-level INFO
+
+# Set to WARNING to only see warnings and errors
+mfcli log-level WARNING
+
+# Set to ERROR to only see errors
+mfcli log-level ERROR
+
+# Set to CRITICAL for only critical errors
+mfcli log-level CRITICAL
+```
+
+The log level setting is stored in your configuration file (`~/Multifactor/.env`) and will take effect on the next mfcli command. This is particularly useful when:
+- **DEBUG**: Troubleshooting issues or understanding detailed pipeline operations
+- **INFO**: Normal day-to-day operation with informative messages
+- **WARNING**: Production use where you only want to see potential issues
+- **ERROR**: When you only care about actual errors
+
+**Example:**
+```bash
+# Enable detailed logging for troubleshooting
+mfcli log-level DEBUG
+
+# Run the pipeline with verbose output
+mfcli run
+
+# Return to normal logging
+mfcli log-level INFO
+```
 
 #### Start Web UI
 
@@ -461,7 +526,7 @@ To use the MCP server with Cline (or other MCP-compatible clients), add the foll
    ```bash
    cd /path/to/hardware/files
    mfcli init
-   mfcli run_pipeline
+   mfcli run
    ```
 
 3. **Add the MCP configuration** to your Cline/Claude settings file (see Configuration above)
@@ -485,7 +550,7 @@ To use the MCP server with Cline (or other MCP-compatible clients), add the foll
 - **Solution**: Run the pipeline at least once to create the vector database:
   ```bash
   mfcli init
-  mfcli run_pipeline
+  mfcli run
   ```
 
 **Error**: `MCP server timeout`
@@ -608,12 +673,11 @@ Created within a **"multifactor"** folder at the **git repository root** if you'
 └── multifactor/                 # Parent folder for all project files and outputs
     ├── config.json              # Project configuration (project name, etc.)
     ├── file_docket.json         # File tracking and processing metadata
-    ├── context/                 # Place your hardware design files here for processing
+    ├── design/                  # Place your hardware design files here for processing
     ├── generated_files/         # BOM CSV files generated from schematics
     ├── hw_cheat_sheets/         # JSON cheat sheets (MCU, errata, debug, functional blocks)
     ├── data_sheets/             # Downloaded component datasheets (from BOM processing)
     ├── pdf_parts/               # Extracted PDF parts for analysis
-    ├── agent_instructions/      # (Reserved for future use)
     ├── fw_tasks/                # (Reserved for future use)
     └── requirements/            # (Reserved for future use)
 ```
@@ -624,7 +688,7 @@ If you're in a git repository at `C:\git\my-hardware-project\` and run `mfcli in
 
 - `C:\git\my-hardware-project\multifactor\config.json` - Project configuration
 - `C:\git\my-hardware-project\multifactor\file_docket.json` - File tracking
-- `C:\git\my-hardware-project\multifactor\context\` - Place source files here
+- `C:\git\my-hardware-project\multifactor\design\` - Place source files here
 - `C:\git\my-hardware-project\multifactor\generated_files\` - Generated BOM files
 - `C:\git\my-hardware-project\multifactor\hw_cheat_sheets\` - Cheat sheets
 - `C:\git\my-hardware-project\multifactor\data_sheets\` - Downloaded datasheets
@@ -636,7 +700,7 @@ If you're NOT in a git repository and run `mfcli init` from `C:\Projects\hardwar
 
 - `C:\Projects\hardware\board_v1\multifactor\config.json` - Project configuration
 - `C:\Projects\hardware\board_v1\multifactor\file_docket.json` - File tracking
-- `C:\Projects\hardware\board_v1\multifactor\context\` - Place source files here
+- `C:\Projects\hardware\board_v1\multifactor\design\` - Place source files here
 - `C:\Projects\hardware\board_v1\multifactor\generated_files\` - Generated BOM files
 - `C:\Projects\hardware\board_v1\multifactor\hw_cheat_sheets\` - Cheat sheets
 - `C:\Projects\hardware\board_v1\multifactor\data_sheets\` - Downloaded datasheets
@@ -747,7 +811,7 @@ First, navigate to your hardware files directory and initialize:
 ```bash
 cd /path/to/hardware/files
 mfcli init
-mfcli run_pipeline
+mfcli run
 ```
 
 ### Starting the Web UI
@@ -844,10 +908,10 @@ pytest app/tests/
 #### 4. Pipeline Processing Failures
 
 **Error**: `Could not find metadata file. Please initialize this repo with "mfcli init"`
-- **Solution**: You need to run `mfcli init` in your hardware files directory before running `mfcli run_pipeline`
+- **Solution**: You need to run `mfcli init` in your hardware files directory before running `mfcli run`
 
 **Error**: `File not found`
-- **Solution**: Make sure you're running `mfcli run_pipeline` from within your hardware files directory (where you ran `mfcli init`)
+- **Solution**: Make sure you're running `mfcli run` from within your hardware files directory (where you ran `mfcli init`)
 
 **Error**: `File extension is not supported`
 - **Solution**: Check that your files are in supported formats (PDF, EDIF, CSV, .net, .cir, .asc)

{mfcli-0.2.5 → mfcli-0.2.7}/mfcli/.env.example

@@ -24,17 +24,23 @@ google_api_key=your_google_api_key_here
 # Note: Requires billing enabled on your OpenAI account
 openai_api_key=your_openai_api_key_here
 
-# LlamaParse API Key
-# Used for advanced PDF parsing and text extraction
-# Get your key from: https://cloud.llamaindex.ai/
-llama_cloud_api_key=your_llamaparse_api_key_here
-
 # DigiKey API Credentials
 # Used for automatic datasheet downloads from DigiKey
 # Get your credentials from: https://developer.digikey.com/
 digikey_client_id=your_digikey_client_id_here
 digikey_client_secret=your_digikey_client_secret_here
 
+# ============================================================
+# LOGGING CONFIGURATION
+# ============================================================
+
+# Log level for mfcli operations
+# Available levels: DEBUG, INFO, WARNING, ERROR, CRITICAL
+# Default: INFO
+# Use DEBUG for detailed troubleshooting, INFO for normal operation
+# Change with: mfcli log-level <LEVEL>
+log_level=INFO
+
 # ============================================================
 # VECTOR DATABASE CONFIGURATION
 # ============================================================

{mfcli-0.2.5 → mfcli-0.2.7}/mfcli/agents/controller/agent.py

@@ -4,7 +4,7 @@ from google.adk.agents import Agent
 
 from mfcli.agents.controller.tools import query_knowledgebase, list_projects
 from mfcli.agents.tools.general import load_agent_config
-from mfcli.pipeline.pipeline import run_pipeline
+from mfcli.pipeline.pipeline import run
 
 config_path = Path(__file__).parent / "config.yaml"
 config = load_agent_config(config_path)
@@ -14,6 +14,6 @@ root_agent = Agent(
     model=config.model,
     description=config.description,
     instruction=config.instructions,
-    tools=[run_pipeline, query_knowledgebase, list_projects],
+    tools=[run, query_knowledgebase, list_projects],
     output_key="pipeline_run_output"
 )

{mfcli-0.2.5 → mfcli-0.2.7}/mfcli/agents/controller/config.yaml

@@ -9,7 +9,7 @@ instructions: |
      - The user asks you to analyze documents in a directory
      - If the user does not specify the name of the project to analyze, run the list_projects tool and ask the user to choose it from the returned list first
      - Display the list of projects neatly as a bulleted list
-     - Once the user has chosen a project, you MUST then run the run_pipeline tool to start the pipeline
+     - Once the user has chosen a project, you MUST then run the run tool to start the pipeline
      - Respond to the user with the output from the pipeline
      - You will receive a summary from the completed pipeline about the number of files which were successfully processed, the number that failed and the total
      - You will also receive a list of errors, if any