Implement CLI for finetuning

README.md

@@ -123,37 +123,37 @@ In this updated schema, we use the `Field` class from `pydantic` to add descript
 !!! note "Code, schema, and prompt"
      We can run `openai_schema` to see exactly what the API will see, notice how the docstrings, attributes, types, and field descriptions are now part of the schema. This describes on this library's core philosophies.
 
-    ```python hl_lines="2 3"
-    class UserDetails(OpenAISchema):
-        "Correctly extracted user information"
-        name: str = Field(..., description="User's full name")
-        age: int
-
-    UserDetails.openai_schema
-    ```
-
-    ```json hl_lines="3 8"
-    {
-    "name": "UserDetails",
-    "description": "Correctly extracted user information",
-    "parameters": {
-        "type": "object",
-        "properties": {
-        "name": {
-            "description": "User's full name",
-            "type": "string"
-        },
-        "age": {
-            "type": "integer"
-        }
-        },
-        "required": [
-        "age",
-        "name"
-        ]
-    }
+```python hl_lines="2 3"
+class UserDetails(OpenAISchema):
+    "Correctly extracted user information"
+    name: str = Field(..., description="User's full name")
+    age: int
+
+UserDetails.openai_schema
+```
+
+```json hl_lines="3 8"
+{
+"name": "UserDetails",
+"description": "Correctly extracted user information",
+"parameters": {
+    "type": "object",
+    "properties": {
+    "name": {
+        "description": "User's full name",
+        "type": "string"
+    },
+    "age": {
+        "type": "integer"
     }
-    ```
+    },
+    "required": [
+    "age",
+    "name"
+    ]
+}
+}
+```
 
 ### Section 3: Calling the ChatCompletion
 

docs/finetune.md

@@ -0,0 +1,89 @@
+# Using the Command Line Interface
+The instructor CLI provides functionalities for managing fine-tuning jobs on OpenAI.
+
+## Creating a Fine-Tuning Job
+
+### View Jobs Options
+
+```sh
+$ instructor jobs --help          
+
+Usage: instructor jobs [OPTIONS] COMMAND [ARGS]...
+
+  Monitor and create fine tuning jobs
+
+Options:
+  --help  Show this message and exit.
+
+Commands:
+  cancel            Cancel a fine-tuning job.
+  create-from-file  Create a fine-tuning job from a file.
+  create-from-id    Create a fine-tuning job from an existing ID.
+  list              Monitor the status of the most recent fine-tuning jobs.
+```
+
+### Create from File
+
+The create-from-file command uploads and trains a model in a single step:
+
+```sh
+$ instructor jobs create-from-file transformed_data.jsonl 
+```
+
+### Create from ID
+
+The create-from-id command uses an uploaded file and trains a model
+
+```sh
+$ instructor files upload transformed_data.jsonl 
+$ instructor files list
+...
+$ instructor jobs create-from-file <file_id>
+```
+
+
+### Viewing Files and Jobs
+
+#### Viewing Jobs
+
+```sh
+$ instructor jobs list 
+
+OpenAI Fine Tuning Job Monitoring                                                
+┏━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━━━━┓
+┃                ┃              ┃                ┃     Completion ┃                 ┃                ┃        ┃                 ┃
+┃ Job ID         ┃ Status       ┃  Creation Time ┃           Time ┃ Model Name      ┃ File ID        ┃ Epochs ┃ Base Model      ┃
+┡━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━━━━┩
+│ ftjob-PWo6uwk… │ 🚫 cancelled │     2023-08-23 │            N/A │                 │ file-F7lJg6Z4… │ 3      │ gpt-3.5-turbo-… │
+│                │              │       23:10:54 │                │                 │                │        │                 │
+│ ftjob-1whjva8… │ 🚫 cancelled │     2023-08-23 │            N/A │                 │ file-F7lJg6Z4… │ 3      │ gpt-3.5-turbo-… │
+│                │              │       22:47:05 │                │                 │                │        │                 │
+│ ftjob-wGoBDld… │ 🚫 cancelled │     2023-08-23 │            N/A │                 │ file-F7lJg6Z4… │ 3      │ gpt-3.5-turbo-… │
+│                │              │       22:44:12 │                │                 │                │        │                 │
+│ ftjob-yd5aRTc… │ ✅ succeeded │     2023-08-23 │     2023-08-23 │ ft:gpt-3.5-tur… │ file-IQxAUDqX… │ 3      │ gpt-3.5-turbo-… │
+│                │              │       14:26:03 │       15:02:29 │                 │                │        │                 │
+└────────────────┴──────────────┴────────────────┴────────────────┴─────────────────┴────────────────┴────────┴─────────────────┘
+                                    Automatically refreshes every 5 seconds, press Ctrl+C to exit
+```
+
+
+#### Viewing Files
+
+```sh
+$ instructor files list 
+
+OpenAI Files                                                      
+┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━━┓                         
+┃ File ID                       ┃ Size (bytes) ┃ Creation Time       ┃ Filename ┃ Purpose   ┃                         
+┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━━┩                         
+│ file-0lw2BSNRUlXZXRRu2beCCWjl │       369523 │ 2023-08-23 23:31:57 │ file     │ fine-tune │                         
+│ file-IHaUXcMEykmFUp1kt2puCDEq │       369523 │ 2023-08-23 23:09:35 │ file     │ fine-tune │                         
+│ file-ja9vRBf0FydEOTolaa3BMqES │       369523 │ 2023-08-23 22:42:29 │ file     │ fine-tune │                         
+│ file-F7lJg6Z47CREvmx4kyvyZ6Sn │       369523 │ 2023-08-23 22:42:03 │ file     │ fine-tune │                         
+│ file-YUxqZPyJRl5GJCUTw3cNmA46 │       369523 │ 2023-08-23 22:29:10 │ file     │ fine-tune │                         
+└───────────────────────────────┴──────────────┴─────────────────────┴──────────┴───────────┘   
+```
+
+
+## Conclusion
+The instructor CLI offers an intuitive interface for managing OpenAI's fine-tuning jobs and related files. By utilizing simple commands, you can create, monitor, and manage your fine-tuning tasks with ease. Feel free to explore further options and parameters by using the --help flag with any command.

instructor/cli/cli.py

@@ -0,0 +1,11 @@
+import typer
+import instructor.cli.jobs as jobs
+import instructor.cli.files as files
+
+app = typer.Typer(
+    name="instructor-ft",
+    help="A CLI for fine-tuning OpenAI's models",
+)
+
+app.add_typer(jobs.app, name="jobs", help="Monitor and create fine tuning jobs")
+app.add_typer(files.app, name="files", help="Manage files on OpenAI's servers")

instructor/cli/files.py

@@ -0,0 +1,123 @@
+from typing import List
+from typing_extensions import Annotated
+from rich.live import Live
+from rich.table import Table
+from rich.spinner import Spinner
+from rich.console import Console
+
+from datetime import datetime
+import openai
+import typer
+import time
+
+app = typer.Typer()
+console = Console()
+
+
+# Sample response data
+def generate_file_table(files: List[openai.File]) -> Table:
+    table = Table(
+        title="OpenAI Files",
+    )
+    table.add_column("File ID", style="dim")
+    table.add_column("Size (bytes)", justify="right")
+    table.add_column("Creation Time")
+    table.add_column("Filename")
+    table.add_column("Purpose")
+
+    for file in files:
+        table.add_row(
+            file["id"],
+            str(file["bytes"]),
+            str(datetime.fromtimestamp(file["created_at"])),
+            file["filename"],
+            file["purpose"],
+        )
+
+    return table
+
+
+def get_files(limit: int = 5) -> List[openai.File]:
+    files = openai.File.list(limit=limit)["data"]  # type: ignore
+    files = sorted(files, key=lambda x: x["created_at"], reverse=True)
+    return files[:limit]
+
+
+def get_file_status(file_id: str) -> str:
+    response = openai.File.retrieve(file_id)
+    return response["status"]
+
+
+@app.command(
+    help="Upload a file to OpenAI's servers, will monitor the upload status until it is processed",
+)
+def upload(
+    filepath: str = typer.Argument(..., help="Path to the file to upload"),
+    purpose: str = typer.Option("fine-tune", help="Purpose of the file"),
+    poll: int = typer.Option(5, help="Polling interval in seconds"),
+):
+    with open(filepath, "rb") as file:
+        response = openai.File.create(file=file, purpose=purpose)
+    file_id = response["id"]
+    with console.status(f"Monitoring upload: {file_id}...") as status:
+        status.spinner_style = "dots"
+        while True:
+            file_status = get_file_status(file_id)
+            if file_status == "processed":
+                console.log(f"[bold green]File {file_id} uploaded successfully!")
+                break
+            time.sleep(poll)
+
+
+@app.command(
+    help="Download a file from OpenAI's servers",
+)
+def download(
+    file_id: str = typer.Argument(..., help="ID of the file to download"),
+    output: str = typer.Argument(..., help="Output path for the downloaded file"),
+):
+    with console.status(
+        f"[bold green]Downloading file {file_id}...", spinner="dots"
+    ) as status:
+        content = openai.File.download(file_id)
+        with open(output, "wb") as file:
+            file.write(content)
+        console.log(f"[bold green]File {file_id} downloaded successfully!")
+
+
+@app.command(
+    help="Delete a file from OpenAI's servers",
+)
+def delete(file_id: str = typer.Argument(..., help="ID of the file to delete")):
+    with console.status(
+        f"[bold red]Deleting file {file_id}...", spinner="dots"
+    ) as status:
+        try:
+            openai.File.delete(file_id)
+            console.log(f"[bold red]File {file_id} deleted successfully!")
+        except Exception as e:
+            console.log(f"[bold red]Error deleting file {file_id}: {e}")
+            return
+
+
+@app.command(
+    help="Monitor the status of a file on OpenAI's servers",
+)
+def status(
+    file_id: str = typer.Argument(..., help="ID of the file to check the status of")
+):
+    with console.status(f"Monitoring status of file {file_id}...") as status:
+        while True:
+            file_status = get_file_status(file_id)
+            status.update(f"File status: {file_status}")
+            if file_status in ["pending", "processed"]:
+                break
+            time.sleep(5)
+
+
+@app.command(
+    help="List the files on OpenAI's servers",
+)
+def list(limit: int = typer.Option(5, help="Limit the number of files to list")):
+    files = get_files(limit=limit)
+    console.log(generate_file_table(files))