ostruct-cli 0.5.0__tar.gz → 0.6.1__tar.gz

{ostruct_cli-0.5.0 → ostruct_cli-0.6.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ostruct-cli
-Version: 0.5.0
+Version: 0.6.1
 Summary: CLI for OpenAI Structured Output
 Author: Yaniv Golan
 Author-email: yaniv@golan.name
@@ -19,7 +19,7 @@ Requires-Dist: openai (>=1.0.0,<2.0.0)
 Requires-Dist: openai-structured (>=2.0.0,<3.0.0)
 Requires-Dist: pydantic (>=2.6.3,<3.0.0)
 Requires-Dist: pyyaml (>=6.0.2,<7.0.0)
-Requires-Dist: tiktoken (>=0.9.0,<0.10.0)
+Requires-Dist: tiktoken (==0.9.0)
 Requires-Dist: tomli (>=2.0.1,<3.0.0) ; python_version < "3.11"
 Requires-Dist: typing-extensions (>=4.9.0,<5.0.0)
 Requires-Dist: werkzeug (>=3.1.3,<4.0.0)
@@ -37,19 +37,62 @@ Command-line interface for working with OpenAI models and structured output, pow
 
 ## Features
 
-- Generate structured output from natural language using OpenAI models
-- Rich template system for defining output schemas
+- Generate structured JSON output from natural language using OpenAI models and a JSON schema
+- Rich template system for defining prompts (Jinja2-based)
 - Automatic token counting and context window management
 - Streaming support for real-time output
-- Caching system for cost optimization
 - Secure handling of sensitive data
 
 ## Installation
 
+### For Users
+
+To install the latest stable version from PyPI:
+
 ```bash
 pip install ostruct-cli
 ```
 
+### For Developers
+
+If you plan to contribute to the project, see the [Development Setup](#development-setup) section below for instructions on setting up the development environment with Poetry.
+
+## Shell Completion
+
+ostruct-cli supports shell completion for Bash, Zsh, and Fish shells. To enable it:
+
+### Bash
+
+Add this to your `~/.bashrc`:
+
+```bash
+eval "$(_OSTRUCT_COMPLETE=bash_source ostruct)"
+```
+
+### Zsh
+
+Add this to your `~/.zshrc`:
+
+```bash
+eval "$(_OSTRUCT_COMPLETE=zsh_source ostruct)"
+```
+
+### Fish
+
+Add this to your `~/.config/fish/completions/ostruct.fish`:
+
+```fish
+eval (env _OSTRUCT_COMPLETE=fish_source ostruct)
+```
+
+After adding the appropriate line, restart your shell or source the configuration file.
+Shell completion will help you with:
+
+- Command options and their arguments
+- File paths for template and schema files
+- Directory paths for `-d` and `--base-dir` options
+- And more!
+
 ## Quick Start
 
 1. Set your OpenAI API key:
@@ -58,57 +101,193 @@ pip install ostruct-cli
 export OPENAI_API_KEY=your-api-key
 ```
 
-2. Create a task template file `task.j2`:
+### Example 1: Using stdin (Simplest)
 
-```
-Extract information about the person: {{ stdin }}
+1. Create a template file `extract_person.j2`:
+
+```jinja
+Extract information about the person from this text: {{ stdin }}
 ```
 
-3. Create a schema file `schema.json`:
+2. Create a schema file `schema.json`:
 
 ```json
 {
   "type": "object",
   "properties": {
-    "name": {
-      "type": "string",
-      "description": "The person's full name"
-    },
-    "age": {
-      "type": "integer",
-      "description": "The person's age"
-    },
-    "occupation": {
-      "type": "string",
-      "description": "The person's job or profession"
+    "person": {
+      "type": "object",
+      "properties": {
+        "name": {
+          "type": "string",
+          "description": "The person's full name"
+        },
+        "age": {
+          "type": "integer",
+          "description": "The person's age"
+        },
+        "occupation": {
+          "type": "string",
+          "description": "The person's job or profession"
+        }
+      },
+      "required": ["name", "age", "occupation"],
+      "additionalProperties": false
     }
   },
-  "required": ["name", "age", "occupation"]
+  "required": ["person"],
+  "additionalProperties": false
+}
+```
+
+3. Run the CLI:
+
+```bash
+# Basic usage
+echo "John Smith is a 35-year-old software engineer" | ostruct run extract_person.j2 schema.json
+
+# For longer text using heredoc
+cat << EOF | ostruct run extract_person.j2 schema.json
+John Smith is a 35-year-old software engineer
+working at Tech Corp. He has been programming
+for over 10 years.
+EOF
+
+# With advanced options
+echo "John Smith is a 35-year-old software engineer" | \
+  ostruct run extract_person.j2 schema.json \
+  --model gpt-4o \
+  --sys-prompt "Extract precise information about the person" \
+  --temperature 0.7
+```
+
+The command will output:
+
+```json
+{
+  "person": {
+    "name": "John Smith",
+    "age": 35,
+    "occupation": "software engineer"
+  }
 }
 ```
 
-4. Run the CLI:
+### Example 2: Processing a Single File
+
+1. Create a template file `extract_from_file.j2`:
+
+```jinja
+Extract information about the person from this text: {{ text.content }}
+```
+
+2. Use the same schema file `schema.json` as above.
+
+3. Run the CLI:
 
 ```bash
-ostruct run task.j2 schema.json
+# Basic usage
+ostruct run extract_from_file.j2 schema.json -f text input.txt
+
+# With advanced options
+ostruct run extract_from_file.j2 schema.json \
+  -f text input.txt \
+  --model gpt-4o \
+  --max-output-tokens 1000 \
+  --temperature 0.7
 ```
 
-Or with more options:
+The command will output:
+
+```json
+{
+  "person": {
+    "name": "John Smith",
+    "age": 35,
+    "occupation": "software engineer"
+  }
+}
+```
+
+### Example 3: Processing Multiple Files
+
+1. Create a template file `extract_from_profiles.j2`:
+
+```jinja
+Extract information about the people from this data:
+
+{% for profile in profiles %}
+== {{ profile.name }}
+
+{{ profile.content }}
+
+{% endfor %}
+```
+
+2. Use the same schema file `schema.json` as above, but updated for multiple people:
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "people": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The person's full name"
+          },
+          "age": {
+            "type": "integer",
+            "description": "The person's age"
+          },
+          "occupation": {
+            "type": "string",
+            "description": "The person's job or profession"
+          }
+        },
+        "required": ["name", "age", "occupation"],
+        "additionalProperties": false
+      }
+    }
+  },
+  "required": ["people"],
+  "additionalProperties": false
+}
+```
+
+3. Run the CLI:
 
 ```bash
-ostruct run task.j2 schema.json \
-  -f content input.txt \
-  -m gpt-4o \
-  --sys-prompt "You are an expert content analyzer"
+# Basic usage
+ostruct run extract_from_profiles.j2 schema.json -p profiles "profiles/*.txt"
+
+# With advanced options
+ostruct run extract_from_profiles.j2 schema.json \
+  -p profiles "profiles/*.txt" \
+  --model gpt-4o \
+  --sys-prompt "Extract precise information about the person" \
+  --temperature 0.5
 ```
 
-Output:
+The command will output:
 
 ```json
 {
-  "name": "John Smith",
-  "age": 35,
-  "occupation": "software engineer"
+  "people": [
+    {
+      "name": "John Smith",
+      "age": 35,
+      "occupation": "software engineer"
+    },
+    {
+      "name": "Jane Doe",
+      "age": 28,
+      "occupation": "data scientist"
+    }
+  ]
 }
 ```
 

ostruct_cli-0.6.1/README.md

@@ -0,0 +1,376 @@
+# ostruct-cli
+
+[![PyPI version](https://badge.fury.io/py/ostruct-cli.svg)](https://badge.fury.io/py/ostruct-cli)
+[![Python Versions](https://img.shields.io/pypi/pyversions/ostruct-cli.svg)](https://pypi.org/project/ostruct-cli)
+[![Documentation Status](https://readthedocs.org/projects/ostruct/badge/?version=latest)](https://ostruct.readthedocs.io/en/latest/?badge=latest)
+[![CI](https://github.com/yaniv-golan/ostruct/actions/workflows/ci.yml/badge.svg)](https://github.com/yaniv-golan/ostruct/actions/workflows/ci.yml)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+Command-line interface for working with OpenAI models and structured output, powered by the [openai-structured](https://github.com/yaniv-golan/openai-structured) library.
+
+## Features
+
+- Generate structured JSON output from natural language using OpenAI models and a JSON schema
+- Rich template system for defining prompts (Jinja2-based)
+- Automatic token counting and context window management
+- Streaming support for real-time output
+- Secure handling of sensitive data
+
+## Installation
+
+### For Users
+
+To install the latest stable version from PyPI:
+
+```bash
+pip install ostruct-cli
+```
+
+### For Developers
+
+If you plan to contribute to the project, see the [Development Setup](#development-setup) section below for instructions on setting up the development environment with Poetry.
+
+## Shell Completion
+
+ostruct-cli supports shell completion for Bash, Zsh, and Fish shells. To enable it:
+
+### Bash
+
+Add this to your `~/.bashrc`:
+
+```bash
+eval "$(_OSTRUCT_COMPLETE=bash_source ostruct)"
+```
+
+### Zsh
+
+Add this to your `~/.zshrc`:
+
+```bash
+eval "$(_OSTRUCT_COMPLETE=zsh_source ostruct)"
+```
+
+### Fish
+
+Add this to your `~/.config/fish/completions/ostruct.fish`:
+
+```fish
+eval (env _OSTRUCT_COMPLETE=fish_source ostruct)
+```
+
+After adding the appropriate line, restart your shell or source the configuration file.
+Shell completion will help you with:
+
+- Command options and their arguments
+- File paths for template and schema files
+- Directory paths for `-d` and `--base-dir` options
+- And more!
+
+## Quick Start
+
+1. Set your OpenAI API key:
+
+```bash
+export OPENAI_API_KEY=your-api-key
+```
+
+### Example 1: Using stdin (Simplest)
+
+1. Create a template file `extract_person.j2`:
+
+```jinja
+Extract information about the person from this text: {{ stdin }}
+```
+
+2. Create a schema file `schema.json`:
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "person": {
+      "type": "object",
+      "properties": {
+        "name": {
+          "type": "string",
+          "description": "The person's full name"
+        },
+        "age": {
+          "type": "integer",
+          "description": "The person's age"
+        },
+        "occupation": {
+          "type": "string",
+          "description": "The person's job or profession"
+        }
+      },
+      "required": ["name", "age", "occupation"],
+      "additionalProperties": false
+    }
+  },
+  "required": ["person"],
+  "additionalProperties": false
+}
+```
+
+3. Run the CLI:
+
+```bash
+# Basic usage
+echo "John Smith is a 35-year-old software engineer" | ostruct run extract_person.j2 schema.json
+
+# For longer text using heredoc
+cat << EOF | ostruct run extract_person.j2 schema.json
+John Smith is a 35-year-old software engineer
+working at Tech Corp. He has been programming
+for over 10 years.
+EOF
+
+# With advanced options
+echo "John Smith is a 35-year-old software engineer" | \
+  ostruct run extract_person.j2 schema.json \
+  --model gpt-4o \
+  --sys-prompt "Extract precise information about the person" \
+  --temperature 0.7
+```
+
+The command will output:
+
+```json
+{
+  "person": {
+    "name": "John Smith",
+    "age": 35,
+    "occupation": "software engineer"
+  }
+}
+```
+
+### Example 2: Processing a Single File
+
+1. Create a template file `extract_from_file.j2`:
+
+```jinja
+Extract information about the person from this text: {{ text.content }}
+```
+
+2. Use the same schema file `schema.json` as above.
+
+3. Run the CLI:
+
+```bash
+# Basic usage
+ostruct run extract_from_file.j2 schema.json -f text input.txt
+
+# With advanced options
+ostruct run extract_from_file.j2 schema.json \
+  -f text input.txt \
+  --model gpt-4o \
+  --max-output-tokens 1000 \
+  --temperature 0.7
+```
+
+The command will output:
+
+```json
+{
+  "person": {
+    "name": "John Smith",
+    "age": 35,
+    "occupation": "software engineer"
+  }
+}
+```
+
+### Example 3: Processing Multiple Files
+
+1. Create a template file `extract_from_profiles.j2`:
+
+```jinja
+Extract information about the people from this data:
+
+{% for profile in profiles %}
+== {{ profile.name }}
+
+{{ profile.content }}
+
+{% endfor %}
+```
+
+2. Use the same schema file `schema.json` as above, but updated for multiple people:
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "people": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The person's full name"
+          },
+          "age": {
+            "type": "integer",
+            "description": "The person's age"
+          },
+          "occupation": {
+            "type": "string",
+            "description": "The person's job or profession"
+          }
+        },
+        "required": ["name", "age", "occupation"],
+        "additionalProperties": false
+      }
+    }
+  },
+  "required": ["people"],
+  "additionalProperties": false
+}
+```
+
+3. Run the CLI:
+
+```bash
+# Basic usage
+ostruct run extract_from_profiles.j2 schema.json -p profiles "profiles/*.txt"
+
+# With advanced options
+ostruct run extract_from_profiles.j2 schema.json \
+  -p profiles "profiles/*.txt" \
+  --model gpt-4o \
+  --sys-prompt "Extract precise information about the person" \
+  --temperature 0.5
+```
+
+The command will output:
+
+```json
+{
+  "people": [
+    {
+      "name": "John Smith",
+      "age": 35,
+      "occupation": "software engineer"
+    },
+    {
+      "name": "Jane Doe",
+      "age": 28,
+      "occupation": "data scientist"
+    }
+  ]
+}
+```
+
+### About Template Files
+
+Template files use the `.j2` extension to indicate they contain Jinja2 template syntax. This convention:
+
+- Enables proper syntax highlighting in most editors
+- Makes it clear the file contains template logic
+- Follows industry standards for Jinja2 templates
+
+## CLI Options
+
+The CLI revolves around a single subcommand called `run`. Basic usage:
+
+```bash
+ostruct run <TASK_TEMPLATE> <SCHEMA_FILE> [OPTIONS]
+```
+
+Common options include:
+
+- File & Directory Inputs:
+  - `-f <NAME> <PATH>`: Map a single file to a variable name
+  - `-d <NAME> <DIR>`: Map a directory to a variable name
+  - `-p <NAME> <PATTERN>`: Map files matching a glob pattern to a variable name
+  - `-R, --recursive`: Enable recursive directory/pattern scanning
+
+- Variables:
+  - `-V name=value`: Define a simple string variable
+  - `-J name='{"key":"value"}'`: Define a JSON variable
+
+- Model Parameters:
+  - `-m, --model MODEL`: Select the OpenAI model (supported: gpt-4o, o1, o3-mini)
+  - `--temperature FLOAT`: Set sampling temperature (0.0-2.0)
+  - `--max-output-tokens INT`: Set maximum output tokens
+  - `--top-p FLOAT`: Set top-p sampling parameter (0.0-1.0)
+  - `--frequency-penalty FLOAT`: Adjust frequency penalty (-2.0-2.0)
+  - `--presence-penalty FLOAT`: Adjust presence penalty (-2.0-2.0)
+  - `--reasoning-effort [low|medium|high]`: Control model reasoning effort
+
+- System Prompt:
+  - `--sys-prompt TEXT`: Provide system prompt directly
+  - `--sys-file FILE`: Load system prompt from file
+  - `--ignore-task-sysprompt`: Ignore system prompt in template frontmatter
+
+- API Configuration:
+  - `--api-key KEY`: OpenAI API key (defaults to OPENAI_API_KEY env var)
+  - `--timeout FLOAT`: API timeout in seconds (default: 60.0)
+
+## Debug Options
+
+- `--debug-validation`: Show detailed schema validation debugging
+- `--debug-openai-stream`: Enable low-level debug output for OpenAI streaming
+- `--progress-level {none,basic,detailed}`: Set progress reporting level
+  - `none`: No progress indicators
+  - `basic`: Show key operation steps (default)
+  - `detailed`: Show all steps with additional info
+- `--show-model-schema`: Display the generated Pydantic model schema
+- `--verbose`: Enable verbose logging
+- `--dry-run`: Validate and render template without making API calls
+- `--no-progress`: Disable all progress indicators
+
+All debug and error logs are written to:
+
+- `~/.ostruct/logs/ostruct.log`: General application logs
+- `~/.ostruct/logs/openai_stream.log`: OpenAI streaming operations logs
+
+For more detailed documentation and examples, visit our [documentation](https://ostruct.readthedocs.io/).
+
+## Development
+
+To contribute or report issues, please visit our [GitHub repository](https://github.com/yaniv-golan/ostruct).
+
+## Development Setup
+
+1. Clone the repository:
+
+```bash
+git clone https://github.com/yanivgolan/ostruct.git
+cd ostruct
+```
+
+2. Install Poetry if you haven't already:
+
+```bash
+curl -sSL https://install.python-poetry.org | python3 -
+```
+
+3. Install dependencies:
+
+```bash
+poetry install
+```
+
+4. Install openai-structured in editable mode:
+
+```bash
+poetry add --editable ../openai-structured  # Adjust path as needed
+```
+
+5. Run tests:
+
+```bash
+poetry run pytest
+```
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+## License
+
+This project is licensed under the MIT License - see the LICENSE file for details.

{ostruct_cli-0.5.0 → ostruct_cli-0.6.1}/pyproject.toml

@@ -4,7 +4,7 @@
 
     [tool.poetry]
     name = "ostruct-cli"
-    version = "0.5.0"
+    version = "0.6.1"
     description = "CLI for OpenAI Structured Output"
     authors = ["Yaniv Golan <yaniv@golan.name>"]
     readme = "README.md"
@@ -19,13 +19,13 @@
     cachetools = "^5.3.2"
     ijson = "^3.2.3"
     typing-extensions = "^4.9.0"
-    tiktoken = "^0.9.0"
     pyyaml = "^6.0.2"
     tomli = {version = "^2.0.1", python = "<3.11"}
     click = "^8.1.7"
     werkzeug = "^3.1.3"
     openai = "^1.0.0"
     openai-structured = "^2.0.0"
+    tiktoken = "0.9.0"
 
     [tool.poetry.scripts]
     ostruct = "ostruct.cli.cli:main"