### Local Development Setup

Source: https://github.com/lastmile-ai/aiconfig/blob/main/gradio-notebook/README-dev.md

Installs project dependencies and starts the development server for the Gradio Workbook frontend.

```bash
cd gradioworkbook
pip install -r requirements.txt
cd frontend && yarn && yarn dev
```

--------------------------------

### Install Dependencies

Source: https://github.com/lastmile-ai/aiconfig/blob/main/aiconfig-docs/README.md

Run this command to install all project dependencies.

```bash
yarn
```

--------------------------------

### Install Project Dependencies

Source: https://github.com/lastmile-ai/aiconfig/blob/main/python/src/aiconfig/eval/batch_eval_examples/travel/travel_eval.ipynb

Output from the package manager showing the installation of required utilities and libraries.

```bash
Collecting lastmile-utils
  Using cached lastmile_utils-0.0.21-py3-none-any.whl.metadata (901 bytes)
Collecting black==23.11.0 (from lastmile-utils)
  Using cached black-23.11.0-cp310-cp310-macosx_11_0_arm64.whl.metadata (66 kB)
Collecting chardet==5.2.0 (from lastmile-utils)
  Using cached chardet-5.2.0-py3-none-any.whl.metadata (3.4 kB)
Collecting flake8==6.1.0 (from lastmile-utils)
  Using cached flake8-6.1.0-py2.py3-none-any.whl.metadata (3.8 kB)
Collecting isort==5.12.0 (from lastmile-utils)
  Using cached isort-5.12.0-py3-none-any.whl (91 kB)
Collecting jsoncomment==0.4.2 (from lastmile-utils)
  Using cached jsoncomment-0.4.2-py3-none-any.whl (6.8 kB)
Collecting pandas==2.1.2 (from lastmile-utils)
  Using cached pandas-2.1.2-cp310-cp310-macosx_11_0_arm64.whl.metadata (18 kB)
Collecting pydantic==2.4.2 (from lastmile-utils)
  Using cached pydantic-2.4.2-py3-none-any.whl.metadata (158 kB)
Collecting pylint==3.0.2 (from lastmile-utils)
  Using cached pylint-3.0.2-py3-none-any.whl.metadata (12 kB)
Collecting pyright==1.1.335 (from lastmile-utils)
  Using cached pyright-1.1.335-py3-none-any.whl.metadata (5.7 kB)
Collecting pytest==7.4.3 (from lastmile-utils)
  Using cached pytest-7.4.3-py3-none-any.whl.metadata (7.9 kB)
Collecting python-dotenv==1.0.0 (from lastmile-utils)
  Using cached python_dotenv-1.0.0-py3-none-any.whl (19 kB)
Collecting result==0.16.0 (from lastmile-utils)
  Using cached result-0.16.0-py3-none-any.whl.metadata (857 bytes)
Collecting autoflake==2.2.1 (from lastmile-utils)
  Using cached autoflake-2.2.1-py3-none-any.whl.metadata (7.3 kB)
Collecting pyflakes>=3.0.0 (from autoflake==2.2.1->lastmile-utils)
  Using cached pyflakes-3.2.0-py2.py3-none-any.whl.metadata (3.5 kB)
Collecting tomli>=2.0.1 (from autoflake==2.2.1->lastmile-utils)
  Using cached tomli-2.0.1-py3-none-any.whl (12 kB)
Collecting click>=8.0.0 (from black==23.11.0->lastmile-utils)
  Using cached click-8.1.7-py3-none-any.whl.metadata (3.0 kB)
Collecting mypy-extensions>=0.4.3 (from black==23.11.0->lastmile-utils)
  Using cached mypy_extensions-1.0.0-py3-none-any.whl (4.7 kB)
Collecting packaging>=22.0 (from black==23.11.0->lastmile-utils)
  Using cached packaging-23.2-py3-none-any.whl.metadata (3.2 kB)
Collecting pathspec>=0.9.0 (from black==23.11.0->lastmile-utils)
  Using cached pathspec-0.12.1-py3-none-any.whl.metadata (21 kB)
Collecting platformdirs>=2 (from black==23.11.0->lastmile-utils)
  Using cached platformdirs-4.1.0-py3-none-any.whl.metadata (11 kB)
Collecting typing-extensions>=4.0.1 (from black==23.11.0->lastmile-utils)
  Using cached typing_extensions-4.9.0-py3-none-any.whl.metadata (3.0 kB)
Collecting mccabe<0.8.0,>=0.7.0 (from flake8==6.1.0->lastmile-utils)
  Using cached mccabe-0.7.0-py2.py3-none-any.whl (7.3 kB)
Collecting pycodestyle<2.12.0,>=2.11.0 (from flake8==6.1.0->lastmile-utils)
  Using cached pycodestyle-2.11.1-py2.py3-none-any.whl.metadata (4.5 kB)
Collecting pyflakes>=3.0.0 (from autoflake==2.2.1->lastmile-utils)
  Using cached pyflakes-3.1.0-py2.py3-none-any.whl.metadata (3.5 kB)
Collecting json-spec (from jsoncomment==0.4.2->lastmile-utils)
  Using cached json_spec-0.11.0-py3-none-any.whl (41 kB)
Collecting numpy<2,>=1.22.4 (from pandas==2.1.2->lastmile-utils)
  Using cached numpy-1.26.3-cp310-cp310-macosx_11_0_arm64.whl.metadata (61 kB)
Collecting python-dateutil>=2.8.2 (from pandas==2.1.2->lastmile-utils)
  Using cached python_dateutil-2.8.2-py2.py3-none-any.whl (247 kB)
Collecting pytz>=2020.1 (from pandas==2.1.2->lastmile-utils)
  Using cached pytz-2023.3.post1-py2.py3-none-any.whl.metadata (22 kB)
Collecting tzdata>=2022.1 (from pandas==2.1.2->lastmile-utils)
  Using cached tzdata-2023.4-py2.py3-none-any.whl.metadata (1.4 kB)
Collecting annotated-types>=0.4.0 (from pydantic==2.4.2->lastmile-utils)
  Using cached annotated_types-0.6.0-py3-none-any.whl.metadata (12 kB)
Collecting pydantic-core==2.10.1 (from pydantic==2.4.2->lastmile-utils)
  Using cached pydantic_core-2.10.1-cp310-cp310-macosx_11_0_arm64.whl.metadata (6.5 kB)
Collecting astroid<=3.1.0-dev0,>=3.0.1 (from pylint==3.0.2->lastmile-utils)
  Using cached astroid-3.0.2-py3-none-any.whl.metadata (4.5 kB)
Collecting tomlkit>=0.10.1 (from pylint==3.0.2->lastmile-utils)
  Using cached tomlkit-0.12.3-py3-none-any.whl.metadata (2.7 kB)
Collecting dill>=0.2 (from pylint==3.0.2->lastmile-utils)
  Using cached dill-0.3.7-py3-none-any.whl.metadata (9.9 kB)
Collecting nodeenv>=1.6.0 (from pyright==1.1.335->lastmile-utils)
  Using cached nodeenv-1.8.0-py2.py3-none-any.whl.metadata (21 kB)
Collecting iniconfig (from pytest==7.4.3->lastmile-utils)
  Using cached iniconfig-2.0.0-py3-none-any.whl (5.9 kB)
```

--------------------------------

### Install Dependencies

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/Function-Calling-OpenAI/typescript/README.md

Navigate to the cookbook directory and install project dependencies using yarn.

```bash
cd aiconfig/cookbooks/Function-Calling-OpenAI/typescript && yarn
```

--------------------------------

### Install Dependencies

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/RAG-with-ChromaDB/RAG_with_AIConfig.ipynb

Install the required packages for AIConfig and ChromaDB.

```python
!pip install python-aiconfig
!pip install chromadb
```

--------------------------------

### Install and Configure Environment

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/Create-AIConfig-Programmatically/create_aiconfig_programmatically.ipynb

Install the required package and load the OpenAI API key from a .env file.

```python
!pip install python-aiconfig

# Create ~/.env file with this line: export OPENAI_API_KEY=<your key here>
# You can get your key from https://platform.openai.com/api-keys 
import openai
import dotenv
import os
dotenv.load_dotenv()
openai.api_key = os.getenv("OPENAI_API_KEY")
```

--------------------------------

### Install and Configure Environment

Source: https://github.com/lastmile-ai/aiconfig/blob/main/python/demo/aiconfig_demo.ipynb

Installs the required package and initializes the OpenAI API key from environment variables.

```python
#1 install the package
%pip install python-aiconfig

from dotenv import load_dotenv
import openai
import os

load_dotenv()

openai.api_key = os.getenv("OPENAI_API_KEY")
```

--------------------------------

### Install Lastmile Utilities and List Packages

Source: https://github.com/lastmile-ai/aiconfig/blob/main/python/src/aiconfig/eval/examples/travel/travel_eval.ipynb

Installs the lastmile-utils package and verifies its installation by listing installed packages. Ensure the installed version matches or exceeds the one specified in aiconfig/python/requirements.txt.

```python
# Package installs & environment setup
!pip3 install lastmile-utils --force
# If you see errors, no worries you can generally ignore. Just make sure that the 
# following output matches with the version specified in the 
# aiconfig/python/requirements.txt file (or is a higher version)
!pip3 list | grep lastmile-utils
```

--------------------------------

### Install Yarn

Source: https://github.com/lastmile-ai/aiconfig/blob/main/gradio-notebook/README-dev.md

Installs yarn globally using npm. Ensure Node.js is installed first.

```bash
sudo npm install --global yarn
```

--------------------------------

### RAG Query Output Example

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/RAG-with-Model-Graded-Eval-v2/rag_demo.ipynb

Example output showing the initial query being processed. This indicates the system is starting the retrieval process.

```text
Output:\nQuerying for: What was the price of flour sold in Boston?
```

--------------------------------

### Install Published Extension

Source: https://github.com/lastmile-ai/aiconfig/blob/main/extensions/HuggingFace/python/README.md

Standard installation command for the published Hugging Face extension.

```bash
pip3 install aiconfig-extension-hugging-face
```

--------------------------------

### Install and Link Extension for Local Development

Source: https://github.com/lastmile-ai/aiconfig/blob/main/extensions/HuggingFace/python/README.md

Commands to build and install the extension from source for local development environments.

```bash
pip3 install build && cd python && python -m build && pip3 install dist/*.whl
```

```bash
pip3 install -e .
```

```bash
pip3 uninstall aiconfig-extension-hugging-face && pip3 install aiconfig-extension-hugging-face
```

--------------------------------

### Start Local Development Server

Source: https://github.com/lastmile-ai/aiconfig/blob/main/aiconfig-docs/README.md

Starts a local development server that reflects changes live without requiring a restart.

```bash
yarn start
```

--------------------------------

### Install and Configure Environment

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/Getting-Started/getting_started.ipynb

Installs the python-aiconfig package and initializes the OpenAI API key from a .env file.

```python
!pip install python-aiconfig

# Create .env file at aiconfig/.env containing the following line:
# OPENAI_API_KEY=<your key here>
# You can get your key from https://platform.openai.com/api-keys 
import openai
import dotenv
import os
dotenv.load_dotenv()
openai.api_key = os.getenv("OPENAI_API_KEY")
```

--------------------------------

### Install AIConfig (Python/Node.js)

Source: https://context7.com/lastmile-ai/aiconfig/llms.txt

Install the AIConfig framework using pip for Python or npm for Node.js.

```bash
# Python installation
pip install python-aiconfig
```

```bash
# Node.js installation
npm install aiconfig
```

--------------------------------

### Install and Configure AIConfig

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/Function-Calling-OpenAI/python/Function_Calling_with_OpenAI.ipynb

Install the required package and initialize the OpenAI API key from an environment file.

```python
# Install AIConfig package
!pip3 install python-aiconfig

# Create .env file at aiconfig/.env containing the following line: 
# OPENAI_API_KEY=<your key here>
# You can get your key from https://platform.openai.com/api-keys
import openai
import dotenv
import os
dotenv.load_dotenv()
openai.api_key = os.getenv("OPENAI_API_KEY")
```

--------------------------------

### Execute Llama example script

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/llama/typescript/README.md

Run the example TypeScript file using ts-node.

```bash
npx ts-node ask-llama.ts
```

--------------------------------

### Install Node.js AIConfig

Source: https://github.com/lastmile-ai/aiconfig/blob/main/README.md

Install the Node.js package for AIConfig using npm or yarn.

```bash
npm install aiconfig
```

```bash
yarn add aiconfig
```

--------------------------------

### Install AIConfig with npm

Source: https://github.com/lastmile-ai/aiconfig/blob/main/aiconfig-docs/docs/getting-started.md

Use this command to install the Node.js AIConfig package using npm.

```bash
npm install aiconfig
```

--------------------------------

### Install Python Dependencies

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/RAG-with-Model-Graded-Eval-v2/rag_demo.ipynb

Use these commands to install the required python-aiconfig and chromadb packages, and load environment variables.

```python
%pip install python-aiconfig==1.1.27
%pip install chromadb

import dotenv
dotenv.load_dotenv()
```

--------------------------------

### Install Groq Extension for AIConfig

Source: https://github.com/lastmile-ai/aiconfig/blob/main/extensions/Groq/README.md

Install the Groq extension using pip. This enables AIConfig to interact with Groq models.

```bash
pip3 install aiconfig-extension-groq
```

--------------------------------

### Install AIConfig and Set Up OpenAI API Key

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/OpenAI-ChatCompletion-AIConfigWrapper/openai_wrapper.ipynb

Install the AIConfig package and configure your OpenAI API key using a .env file. Ensure you have the necessary environment variables set.

```python
# Install AIConfig package
!pip3 install python-aiconfig

# Create ~/.env file with this line: export OPENAI_API_KEY=<your key here>
# You can get your key from https://platform.openai.com/api-keys 
import openai
import dotenv
import os
dotenv.load_dotenv()
openai.api_key = os.getenv("OPENAI_API_KEY")
```

--------------------------------

### Example RAG Queries

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/RAG-with-Model-Graded-Eval-v2/rag_demo.ipynb

A list of example queries to be used with the RAG system. Uncomment specific queries to test different scenarios.

```python
queries = [\n     "What was the price of flour sold in Boston?",\n     "When and why did the british Blockade happen?",\n     "What happened during the burning of the Assembly houses in Canada in 1812?",\n     \n    # "What are some of the most important events in US history?"    \n    # "What happ the American declaration of war against England in 1812",\n    # "What happened during the burning of the Assembly houses in Canada in 1812?",\n    "Elaborate on Napoleon",\n    # "The close alliance between Great Britain and Russia",\n    # "The loss of the Bank of the United States",\n    # "The loss of the Massachusetts and Connecticut banks",\n    # "The Battle of the Thames in 1813",\n    # "The campaigns of General Dearborn and General Wilkinson",\n    # "The blockades and conflicts with British ships, including the battles of Chesapeake and Argus",\n    # "Privateering by the US during the war",\n    # "The last embargo implemented by the US in an attempt to obtain concessions from England",\n    # "The involvement of Russia and England in the war",\n    # "The financial challenges faced by the US Treasury",\n    # "The changing attitudes and perceptions of the British press towards the US during the war",\n    # "The opposition to the war by Federalists, particularly in Massachusetts.",\n]
```

--------------------------------

### Initialize ChromaDB and Query

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/RAG-with-ChromaDB/RAG_with_AIConfig.ipynb

Create a collection of curriculum documents and perform a similarity search.

```python
# import ChromaDB and set up the Chroma client
import chromadb
chroma_client = chromadb.Client()

# Create a collection of curriculums
collection = chroma_client.create_collection(name="curriculum")

# Add documents for a math curriculum, physics curriculum, and a chemistry curriculum
collection.add(
    documents=["math", "physics", "chemistry"],
    metadatas=[
        {
            "source": """Subject: Mathematics

            Course 1: Number Sense and Operations
            - Place value
            - Number patterns and relationships
            - Addition, subtraction, multiplication, and division
            - Problem-solving techniques

            Course 2: Algebra
            - Variables and expressions
            - Equations and inequalities
            - Patterns and functions"""
        },
        {
            "source": """Subject: Physics

            Course 1: Introduction to Physics
            - Scientific method and inquiry skills
            - Measurement and scientific notation
            - Physical quantities and units

            Course 2: Motion and Forces
            - Position, distance, and displacement
            - Speed,
            - velocity, and acceleration
            - Newton's laws of motion"""
        },
        {
            "source": """Subject: Chemistry

            Course 1: Introduction to Chemistry
            - Matter and its properties
            - Atoms, elements, and compounds
            - Chemical symbols and formulas"""
        }
    ],
    ids=["id1", "id2", "id3"]
)

# Query the vector database for the closest context to the student question
context = collection.query(
    query_texts=["What is the sum of the first 103 numbers"],
    n_results=1
)

print(context)
```

--------------------------------

### Get Output Text by Prompt Name (TypeScript)

Source: https://context7.com/lastmile-ai/aiconfig/llms.txt

Retrieve the text content of a prompt's output using the prompt name. This example also demonstrates how to get the latest output object associated with a specific prompt.

```typescript
import { AIConfigRuntime } from "aiconfig";

async function getOutput() {
    const config = AIConfigRuntime.load("travel.aiconfig.json");

    await config.run("get_activities");

    // Get output text by prompt name
    const text = config.getOutputText("get_activities");
    console.log(`Activities:\n${text}`);

    // Get latest output
    const latestOutput = config.getLatestOutput("get_activities");
    console.log("Latest output:", latestOutput);
}

getOutput();
```

--------------------------------

### Get Output Text by Prompt Name (Python)

Source: https://context7.com/lastmile-ai/aiconfig/llms.txt

Retrieve the text content of a prompt's output after running inference. This example shows how to get the output text using the prompt name and also by specifying a particular output object.

```python
from aiconfig import AIConfigRuntime, InferenceOptions
import asyncio

config = AIConfigRuntime.load("travel.aiconfig.json")

async def get_output():
    await config.run("get_activities", options=InferenceOptions(stream=True))

    # Get output text by prompt name
    text = config.get_output_text("get_activities")
    print(f"Activities:\n{text}")

    # Get output text with specific output object
    prompt = config.get_prompt("get_activities")
    if prompt.outputs:
        latest_output = prompt.outputs[-1]
        text = config.get_output_text(prompt, latest_output)
        print(f"Latest output:\n{text}")

asyncio.run(get_output())
```

--------------------------------

### Install and Verify AIConfig Dependencies

Source: https://github.com/lastmile-ai/aiconfig/blob/main/python/src/aiconfig/eval/batch_eval_examples/travel/travel_eval.ipynb

Installs the required lastmile-utils package and verifies the installed version.

```python
!pip3 install lastmile-utils --force
!pip3 list | grep lastmile-utils
```

--------------------------------

### Initialize and Define Book Recommendation Prompt

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/Function-Calling-OpenAI/python/Function_Calling_with_OpenAI.ipynb

Initializes AIConfigRuntime and defines a prompt for book recommendations, including OpenAI function definitions for listing, searching, and getting book details.

```python
config = AIConfigRuntime.create(name="Book Finder", description="Use OpenAI function calling to help recommend books")
model = "gpt-3.5-turbo"
data = {
    "model": model,
    "messages": [
        {
            "role": "system",
            "content": "Please use our book database, which you can access using functions to answer the following questions."
        },
        {
            "role": "user",
            "content": "I really enjoyed reading {{book}}, could you recommend me a book that is similar and tell me why?"
        }
    ],
    "functions": [
        {
          "name": "list",
          "description": "list queries books by genre, and returns a list of names of books",
          "parameters": {
            "type": "object",
            "properties": {
              "genre": {
                "type": "string",
                "enum": [
                  "mystery",
                  "nonfiction",
                  "memoir",
                  "romance",
                  "historical"
                ]
              }
            }
          }
        },
        {
          "name": "search",
          "description": "search queries books by their name and returns a list of book names and their ids",
          "parameters": {
            "type": "object",
            "properties": {
              "name": {
                "type": "string"
              }
            }
          }
        },
        {
          "name": "get",
          "description": "get returns a book's detailed information based on the id of the book. Note that this does not accept names, and only IDs, which you can get by using search.",
          "parameters": {
            "type": "object",
            "properties": {
              "id": {
                "type": "string"
              }
            }
          }
        }
    ]
}

new_prompts = await config.serialize(model, data, prompt_name="recommend_book", params={"book": "To Kill a Mockingbird"})
config.add_prompt(prompt_name="recommend_book", prompt_data=new_prompts[0])
```

--------------------------------

### Install Project Dependencies

Source: https://github.com/lastmile-ai/aiconfig/blob/main/python/README_dev.md

Install the necessary Python packages for development and testing. The `-e` flag installs the package in editable mode, reflecting local changes.

```bash
pip install -r requirements.txt
```

```bash
pip install -e .
```

```bash
pip install -r requirements-dev.txt
```

--------------------------------

### Start AIConfig Editor

Source: https://github.com/lastmile-ai/aiconfig/blob/main/python/src/aiconfig/editor/README.md

Launch the editor server pointing to a specific configuration file.

```bash
aiconfig edit  --aiconfig-path=/my/path'
```

--------------------------------

### Install Development Dependencies

Source: https://github.com/lastmile-ai/aiconfig/blob/main/python/src/aiconfig/editor/README.md

Install the local python package in editable mode.

```bash
pip3 install -e ./python
alias aiconfig="python3 -m 'aiconfig.scripts.aiconfig_cli'"
```

--------------------------------

### Initialize AIConfigRuntime

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/Create-AIConfig-Programmatically/create_aiconfig_programmatically.ipynb

Create a new AIConfigRuntime instance with a specified name and description.

```python
from aiconfig import AIConfigRuntime
new_config = AIConfigRuntime.create("create_programmatically_demo", "This is a demo of creating a config programmatically")
```

--------------------------------

### Install LlamaModelParser Extension

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/llama/python/README.md

Install the required AIConfig packages via pip.

```bash
pip install python-aiconfig aiconfig-extension-llama
```

--------------------------------

### Install AIConfig package

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/Anyscale/Function_Calling_with_Mixtral.ipynb

Install the necessary Python package to use AIConfig.

```python
# Install AIConfig package
!pip3 install python-aiconfig
```

--------------------------------

### Install AIConfig CLI

Source: https://github.com/lastmile-ai/aiconfig/blob/main/python/src/aiconfig/editor/README.md

Install the package and set a shell alias for easier access.

```bash
pip3 install python-aiconfig; alias aiconfig="python3 -m 'aiconfig.scripts.aiconfig_cli'"
```

--------------------------------

### Activate Development Environment

Source: https://github.com/lastmile-ai/aiconfig/blob/main/python/src/aiconfig/editor/README.md

Switch to the configured development environment.

```bash
conda activate my_environment_name
```

--------------------------------

### CLI Example for RAG Query

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/RAG-with-Model-Graded-Eval-v2/rag_demo.ipynb

Demonstrates how to run the RAG query functionality from the command line. Replace placeholders with actual values.

```bash
!python rag.py query "In July, flour sold at Boston for _?" -k=10 --chroma-collection-name us_history_volume_7
```

--------------------------------

### Deploy Website (Using SSH)

Source: https://github.com/lastmile-ai/aiconfig/blob/main/aiconfig-docs/README.md

Builds the website and deploys it using SSH. Assumes SSH is configured for deployment.

```bash
USE_SSH=true yarn deploy
```

--------------------------------

### Install Python AIConfig

Source: https://github.com/lastmile-ai/aiconfig/blob/main/README.md

Install the Python package for AIConfig using pip or poetry.

```bash
pip3 install python-aiconfig
```

```bash
poetry add python-aiconfig
```

--------------------------------

### Run AIConfig Prompts with Python SDK

Source: https://github.com/lastmile-ai/aiconfig/blob/main/README.md

Load an AIConfig file, set up streaming options, and run a prompt with dependencies. This example demonstrates how to execute the 'gen_itinerary' prompt and save the updated configuration with outputs.

```python
# load your AIConfig
from aiconfig import AIConfigRuntime, InferenceOptions
import asyncio

config = AIConfigRuntime.load("travel.aiconfig.json")

# setup streaming
inference_options = InferenceOptions(stream=True)

# run a prompt
async def gen_nyc_itinerary():
  gen_itinerary_response = await config.run("gen_itinerary", params = {"order_by" : "location"}, options=inference_options, run_with_dependencies=True)

asyncio.run(gen_nyc_itinerary())

# save the aiconfig to disk and serialize outputs from the model run
config.save('updated_travel.aiconfig.json', include_outputs=True)
```

--------------------------------

### ChromaDB Output Logs

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/RAG-with-ChromaDB/RAG_with_AIConfig.ipynb

Example output logs from the ChromaDB initialization and query process.

```text
Output:
/root/.cache/chroma/onnx_models/all-MiniLM-L6-v2/onnx.tar.gz: 100%|██████████| 79.3M/79.3M [00:01<00:00, 47.6MiB/s]
```

```text
Output:
{'ids': [['id1']], 'distances': [[1.5048770904541016]], 'metadatas': [[{'source': 'Subject: Mathematics\n\n            Course 1: Number Sense and Operations\n            - Place value\n            - Number patterns and relationships\n            - Addition, subtraction, multiplication, and division\n            - Problem-solving techniques\n\n            Course 2: Algebra\n            - Variables and expressions\n            - Equations and inequalities\n            - Patterns and functions'}]], 'embeddings': None, 'documents': [['math']], 'uris': None, 'data': None}
```

--------------------------------

### Start AIConfig Editor

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/Gradio/README.md

Use this command to launch the AIConfig editor with specified configuration and parser paths. Ensure you are in the correct directory after cloning the repository.

```bash
aiconfig_path=./cookbooks/Gradio/huggingface.aiconfig.json
parsers_path=./cookbooks/Gradio/aiconfig_model_registry.py
aiconfig edit --aiconfig-path=$aiconfig_path --parsers-module-path=$parsers_path
```

--------------------------------

### Install Python Dependencies

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/RAG-with-MongoDB/mongodb_aiconfig_rag.ipynb

Install the necessary libraries for MongoDB, PDF processing, LangChain, and AIConfig.

```python
# Install python dependencies. Run Once.
# MongoDB reccomends `python -m pip install "pymongo[srv]"==3.11` or whatever version of python you are using
%pip install pymongo
%pip install pypdf
%pip install langchain
%pip install langchain_community
%pip install langchain_openai
%pip install python-aiconfig
```

--------------------------------

### Create an AIConfig

Source: https://github.com/lastmile-ai/aiconfig/blob/main/python/README.md

Use `AIConfigRuntime.create` to initialize a new AIConfig with a name and description.

```python
config = AIConfigRuntime.create("aiconfig name", "description")
```

--------------------------------

### Install LlamaModelParser dependencies

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/llama/typescript/README.md

Install the required AIConfig and Llama extension packages via yarn.

```bash
yarn add aiconfig
yarn add aiconfig-extension-llama
```

--------------------------------

### Install AIConfig with Yarn

Source: https://github.com/lastmile-ai/aiconfig/blob/main/aiconfig-docs/docs/getting-started.md

Use this command to install the Node.js AIConfig package using yarn.

```bash
yarn add aiconfig
```

--------------------------------

### Setup Streaming

Source: https://github.com/lastmile-ai/aiconfig/blob/main/aiconfig-docs/docs/getting-started.md

Configure inference options to enable streaming responses from the model.

```python
inference_options = InferenceOptions(stream=True)
```

```typescript
async function travelWithGPT() {
  const aiConfig = AIConfigRuntime.load(
    path.join(__dirname, "travel.aiconfig.json")
  );

  const options: InferenceOptions = {
    callbacks: {
      streamCallback: (data: any, _acc: any, _idx: any) => {
        // Write streamed content to console
        process.stdout.write(data?.content || "\n");
      },
    },
  };
}

travelWithGPT();
```

--------------------------------

### Execute recommend_book prompt

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/Anyscale/Function_Calling_with_Mixtral.ipynb

Runs a prompt with specified parameters and inference options.

```python
params = {"book":"Where the Crawdads Sing"}
inference_options = InferenceOptions(stream=False)

completion = await config.run("recommend_book", params, options=inference_options)
print(completion)
```

--------------------------------

### Install AIConfig with Poetry

Source: https://github.com/lastmile-ai/aiconfig/blob/main/aiconfig-docs/docs/getting-started.md

Use this command to install the python AIConfig package using poetry.

```bash
poetry add python-aiconfig
```

--------------------------------

### Execute Prompt with Parameters

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/Basic-Prompt-Routing/assistant.ipynb

Run a specific prompt within the configuration using provided parameters and retrieve the output text.

```python
# Run a single prompt (with streaming).

params = {"student_question": math_question}

await config.run("router", params)
topic = config.get_output_text("router")

dest_prompt = topic.lower()
dest_prompt
```

--------------------------------

### Install AIConfig with Pip

Source: https://github.com/lastmile-ai/aiconfig/blob/main/aiconfig-docs/docs/getting-started.md

Use this command to install the python AIConfig package using pip.

```bash
pip install --user python-aiconfig
```

--------------------------------

### Load and Run Gemini Prompts

Source: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/Gemini/Gemini.ipynb

Load an existing AIConfig file and prepare it for execution with inference options.

```python
# Load the config you just created
from aiconfig import CallbackManager, InferenceOptions
aiconfig = AIConfigRuntime.load("gemini_demo.aiconfig.json")

aiconfig.callback_manager = CallbackManager([]) # Skip Logging, Google Colab forwards logs to stdout
inference_options = InferenceOptions(stream=True)
```

```python
# Config.run() handles the complex things for you
```