Build with E2E: Enhancing Python Code Generation with Updated Documentation Using Llama 3

June 24, 2024

In this article, we will showcase how to use a hosted Llama 3 to generate code based on API documentation provided by any platform. The method is fairly simple: use Ollama to create a Llama 3 endpoint, harness prompt engineering, and leverage the Beautiful Soup library to generate API methods from documentation pages. As an example, we will use NewsAPI, which allows you to search worldwide news with code.

The key thing to keep in mind here is - the open-source LLM will not browse, download, and parse content for you; instead, you need to create the scaffolding to get the content, clean it up, and provide it as part of the LLM prompt, in order to finally generate the documentation.

Let’s get started.

Prerequisite: Launch a GPU Node on E2E Cloud

Since we'll be using Llama 3, we need a cloud GPU node. For this, you have two options on E2E Cloud.

First, sign up to E2E Cloud if you haven’t - https://myaccount.e2enetworks.com

Next, launch a cloud GPU node. Pick one which has at least 16GB of GPU RAM available. If you are creating this setup for a large software dev company, you should go for H100 or A100 clusters.

To launch a cloud GPU node, click on ‘Compute’ on the left sidebar.

Guide to Building API Coding Assistant Using Llama 3

Prerequisites

Python Environment: Ensure you have Python installed.

Required Libraries: Install the following Python libraries:


pip install requests beautifulsoup4 python-dotenv ollama

The Python Script

Below is the complete Python script that can parse a documentation page, extract the documentation content, and use Llama 3 to generate code snippets.

Explanation

Grab Documentation Content: The scrape_webpage function sends a GET request to the provided URL and retrieves the HTML content.
Parsing HTML: Beautiful Soup is used to parse the HTML content and extract the text.


import requests
from bs4 import BeautifulSoup


def scrape_webpage(url):
    try:
        # Send a GET request to the URL
        response = requests.get(url)


        # Check if the request was successful (status code 200)
        if response.status_code == 200:
            # Create a BeautifulSoup object to parse the HTML content
            soup = BeautifulSoup(response.text, 'html.parser')


            # Extract the desired data from the parsed HTML
            # For example, to extract all the text from the page:
            text = soup.get_text()




            return text
        else:
            print(f"Failed to retrieve the webpage. Status code: {response.status_code}")
            return None


    except requests.exceptions.RequestException as e:
        print(f"An error occurred while making the request: {e}")
        return None


import os
import requests
from bs4 import BeautifulSoup
import ollama




# Example usage:
url = "https://newsapi.org/docs/endpoints/everything"  # Replace with the URL of the documentation website you want to scrape




# Extract text from the HTML content
text = scrape_webpage(url)




prompt = (
    "Read the provided text (ignore the HTML code) from below and generate clear, well-documented example methods"
    "that illustrate how to use the described APIs effectively in Python language only. Each example should include necessary code comments"
    "and be ready to use in a real-world application. \n"
    f"API_Documentation: {text} "
)




# Generate chat completion




response = ollama.chat(model='llama3', messages=[
{
    'role': 'user',
    'content': prompt,
},
])




print(response['message']['content'])
    # Print the completion response

Running the Script

Execute the script to see the generated code snippet:


python script.py

Results

When you execute the above code, you will see that it will provide you with output on the lines of:

Output:

—-


Here are some example methods that illustrate how to use the described APIs effectively in Python language:

**Example 1: Searching for news articles using keywords**

```
import requests

# Set your API key and search query
api_key = "YOUR_API_KEY"
search_query = "bitcoin"

# Construct the URL with the API endpoint and parameters
url = f"https://newsapi.org/v2/everything?q={search_query}&apiKey={api_key}"

# Send a GET request to the API endpoint
response = requests.get(url)

# Check if the response was successful (200 OK)
if response.status_code == 200:
    # Parse the JSON response
    data = response.json()

    # Print the total number of results
    print(f"Total results: {data['totalResults']}")

    # Iterate over the articles and print some information
    for article in data["articles"]:
        print(f"Source: {article['source']['name']}")
        print(f"Title: {article['title']}")
        print(f"URL: {article['url']}")
else:
    print("Error:", response.status_code)
```

**Example 2: Searching for news articles using specific sources**

```
import requests

# Set your API key and search query
api_key = "YOUR_API_KEY"
source_ids = ["techcrunch.com", "thenextweb.com"]

# Construct the URL with the API endpoint and parameters
url = f"https://newsapi.org/v2/everything?domains={ ','.join(source_ids) }&apiKey={api_key}"

# Send a GET request to the API endpoint
response = requests.get(url)

# Check if the response was successful (200 OK)
if response.status_code == 200:
    # Parse the JSON response
    data = response.json()

    # Print the total number of results
    print(f"Total results: {data['totalResults']}")

    # Iterate over the articles and print some information
    for article in data["articles"]:
        print(f"Source: {article['source']['name']}")
        print(f"Title: {article['title']}")
        print(f"URL: {article['url']}")
else:
    print("Error:", response.status_code)
```

**Example 3: Searching for news articles using a specific date range**

```
import requests

# Set your API key and search query
api_key = "YOUR_API_KEY"
start_date = "2024-06-16T00:00:00"
end_date = "2024-06-17T23:59:59"

# Construct the URL with the API endpoint and parameters
url = f"https://newsapi.org/v2/everything?q=apple&from={start_date}&to={end_date}&sortBy=popularity&apiKey={api_key}"

# Send a GET request to the API endpoint
response = requests.get(url)

# Check if the response was successful (200 OK)
if response.status_code == 200:
    # Parse the JSON response
    data = response.json()

    # Print the total number of results
    print(f"Total results: {data['totalResults']}")

    # Iterate over the articles and print some information
    for article in data["articles"]:
        print(f"Source: {article['source']['name']}")
        print(f"Title: {article['title']}")
        print(f"URL: {article['url']}")
else:
    print("Error:", response.status_code)
```

These examples demonstrate how to use the News API to search for news articles based on keywords, specific sources, and date ranges. You can modify these examples to suit your specific use case and requirements.

Now, this was a simple response. Let’s see if the LLM can generate the exact function that we can use.

To do this, we will modify the script.py slightly, so as to update the prompt.


# Question from the developer
question = "Show how to get all articles for a particular date"

prompt = (
    "Read the Question and the provided API_Documentation text (ignore the HTML code) from below and generate clear, well-documented methods"
    "that illustrate how to use the described APIs effectively in Python language only. It should include necessary code comments"
    "and be ready to use in a real-world application. \n"
    f"Question: {question}"
    f"API_Documentation: {text} "
)

Using this, the result we get is the following:


# Question from the developer
Here is a Python example that illustrates how to use the `newsapi` API to get all articles for a particular date:
```python
import requests

# Set your API key here
API_KEY = "YOUR_API_KEY_HERE"

def get_articles(date):
    # Construct the API request URL
    url = f"https://newsapi.org/v2/everything"
    params = {
        "apiKey": API_KEY,
        "from": date,  # Use the provided date format (e.g. 2024-06-17)
        "to": date,
        "sortBy": "publishedAt",  # Sort by publication date
        "pageSize": 100,  # Limit the number of results per page
    }

    # Make the API request
    response = requests.get(url, params=params)

    # Check if the request was successful
    if response.status_code == 200:
        # Parse the JSON response
        data = response.json()

        # Extract the articles from the response
        articles = data["articles"]

        return articles
    else:
        print("Error:", response.status_code)
        return None

# Example usage:
date = "2024-06-17"
articles = get_articles(date)

if articles is not None:
    for article in articles:
        print(article["title"])
```
This code defines a `get_articles` function that takes a date string as input, constructs the API request URL with the specified parameters (including the date), makes the request, and extracts the articles from the response. The example usage shows how to call this function with a specific date and print out the titles of the resulting articles.

Note that you should replace `YOUR_API_KEY_HERE` with your actual API key from NewsAPI.

This looks great. We have essentially built a system which can refer to a documentation endpoint and generate code based on questions you ask. And the best part is this - you control the entire stack, so no API costs, no leakage of sensitive data.

Now, let’s move to the next step, where we integrate this with Visual Studio Code, the preferred development environment for many developers. For this, we will use the extension Continue.dev.

Bonus Step: Integrate with VS Code

Continue.dev is an innovative AI-powered development tool designed to streamline and enhance the software development process. Continue.dev leverages LLMs to provide real-time code suggestions, error detection, and intelligent refactoring recommendations. This tool not only improves coding efficiency but also helps maintain high code quality by identifying potential issues early in the development cycle.

To integrate this script into VSCode using the Continue.dev extension, follow these steps:

Install Continue.dev Extension:some text
- Open VSCode.
- Go to the Extensions view by clicking on the Extensions icon in the Activity Bar on the side of the window or by pressing Ctrl+Shift+X.
- Search for "Continue.dev" and click Install on the Continue.dev extension.
- Follow the setup instructions provided by the Continue.dev extension documentation to configure it for your project. This typically involves setting up any necessary API keys and configuring the extension to recognize your development environment.

Testing if Continue.dev Is Installed Properly

Select the part of the code you want to edit and press CTRL+L to use continue.dev. For example:

‍

It can also work as a co-pilot for you.

Integrating Llama 3 with Continue

Launch the Ollama server on 0.0.0.0 so that it can be accessed by external ips.


OLLAMA_HOST=0.0.0.0 ollama serve

The server will be hosted on the default port 11434. Now pull Llama 3 into your local server.


ollama pull llama3

Open Continue and click on the + sign and then open config.json.

‍

Add the following to the model's list.

Then we’ll write a custom slash command.

This command will allow Continue to read the API documentation, and then generate sample methods on how to use the API. In the same config.json, add the following to the customCommands list.


"customCommands": [
    {
      "name": "example_api",
      "prompt": "Read the provided API documentation (selected text) and generate clear, well-documented example methods that illustrate how to use the described APIs effectively. Each example should include necessary code comments and be ready to use in a real-world application.",
      "description": "Write example functions from API documentation"


    },

Now in the IDE, whenever you type /example_api along with the selected API documentation, the continue chat-interface will help you out with the example functions.

Conclusion

By combining web scraping, real-time documentation extraction, and advanced language models like Llama 3, developers can significantly enhance their productivity. This approach not only ensures that the code is up-to-date but also allows for rapid prototyping and development. Try integrating this method into your workflow and experience the benefits of automated code generation.Open-source LLMs, like Llama 3 or Mistral 7, offer a powerful leverage: companies can fine-tune and create an endpoint, and use it to build AI assistants that are deeply integrated into their internal workflow. This strategy is being used to build AI assistants for developers, analysts, content creators, and others. In this regard, coding assistants are particularly powerful, as they reduce development time and increase developer productivity, thus giving the company a significant edge over competition.

Sign up for Free Trial

Latest Blogs

September 2, 2024

Step-by-Step Guide to Building a Speech and Voice AI Assistant Using ASR with Llama 3.1

September 2, 2024

Building an E-Commerce Voice AI Chatbot Using Llama 3.1, Vector Search, and TTS Engine

August 30, 2024

A Complete Guide To Customer Acquisition For Startups

Any business is enlivened by its customers. Therefore, a strategy to constantly bring in new clients is an ongoing requirement. In this regard, having a proper customer acquisition strategy can be of great importance.

So, if you are just starting your business, or planning to expand it, read on to learn more about this concept.

The problem with customer acquisition

As an organization, when working in a diverse and competitive market like India, you need to have a well-defined customer acquisition strategy to attain success. However, this is where most startups struggle. Now, you may have a great product or service, but if you are not in the right place targeting the right demographic, you are not likely to get the results you want.

To resolve this, typically, companies invest, but if that is not channelized properly, it will be futile.

So, the best way out of this dilemma is to have a clear customer acquisition strategy in place.

How can you create the ideal customer acquisition strategy for your business?

Define what your goals are

You need to define your goals so that you can meet the revenue expectations you have for the current fiscal year. You need to find a value for the metrics –

MRR – Monthly recurring revenue, which tells you all the income that can be generated from all your income channels.
CLV – Customer lifetime value tells you how much a customer is willing to spend on your business during your mutual relationship duration.
CAC – Customer acquisition costs, which tells how much your organization needs to spend to acquire customers constantly.
Churn rate – It tells you the rate at which customers stop doing business.

All these metrics tell you how well you will be able to grow your business and revenue.

Identify your ideal customers

You need to understand who your current customers are and who your target customers are. Once you are aware of your customer base, you can focus your energies in that direction and get the maximum sale of your products or services. You can also understand what your customers require through various analytics and markers and address them to leverage your products/services towards them.

Choose your channels for customer acquisition

How will you acquire customers who will eventually tell at what scale and at what rate you need to expand your business? You could market and sell your products on social media channels like Instagram, Facebook and YouTube, or invest in paid marketing like Google Ads. You need to develop a unique strategy for each of these channels.

Communicate with your customers

If you know exactly what your customers have in mind, then you will be able to develop your customer strategy with a clear perspective in mind. You can do it through surveys or customer opinion forms, email contact forms, blog posts and social media posts. After that, you just need to measure the analytics, clearly understand the insights, and improve your strategy accordingly.

Combining these strategies with your long-term business plan will bring results. However, there will be challenges on the way, where you need to adapt as per the requirements to make the most of it. At the same time, introducing new technologies like AI and ML can also solve such issues easily. To learn more about the use of AI and ML and how they are transforming businesses, keep referring to the blog section of E2E Networks.

‍

Reference Links

https://www.helpscout.com/customer-acquisition/

https://www.cloudways.com/blog/customer-acquisition-strategy-for-startups/

https://blog.hubspot.com/service/customer-acquisition

This is a decorative image for: Constructing 3D objects through Deep Learning

October 18, 2022

Image-based 3D Object Reconstruction State-of-the-Art and trends in the Deep Learning Era

3D reconstruction is one of the most complex issues of deep learning systems. There have been multiple types of research in this field, and almost everything has been tried on it — computer vision, computer graphics and machine learning, but to no avail. However, that has resulted in CNN or convolutional neural networks foraying into this field, which has yielded some success.

The Main Objective of the 3D Object Reconstruction

Developing this deep learning technology aims to infer the shape of 3D objects from 2D images. So, to conduct the experiment, you need the following:

Highly calibrated cameras that take a photograph of the image from various angles.
Large training datasets can predict the geometry of the object whose 3D image reconstruction needs to be done. These datasets can be collected from a database of images, or they can be collected and sampled from a video.

By using the apparatus and datasets, you will be able to proceed with the 3D reconstruction from 2D datasets.

State-of-the-art Technology Used by the Datasets for the Reconstruction of 3D Objects

The technology used for this purpose needs to stick to the following parameters:

Input

Training with the help of one or multiple RGB images, where the segmentation of the 3D ground truth needs to be done. It could be one image, multiple images or even a video stream.

The testing will also be done on the same parameters, which will also help to create a uniform, cluttered background, or both.

Output

The volumetric output will be done in both high and low resolution, and the surface output will be generated through parameterisation, template deformation and point cloud. Moreover, the direct and intermediate outputs will be calculated this way.

Network architecture used

The architecture used in training is 3D-VAE-GAN, which has an encoder and a decoder, with TL-Net and conditional GAN. At the same time, the testing architecture is 3D-VAE, which has an encoder and a decoder.

Training used

The degree of supervision used in 2D vs 3D supervision, weak supervision along with loss functions have to be included in this system. The training procedure is adversarial training with joint 2D and 3D embeddings. Also, the network architecture is extremely important for the speed and processing quality of the output images.

Practical applications and use cases

Volumetric representations and surface representations can do the reconstruction. Powerful computer systems need to be used for reconstruction.

Given below are some of the places where 3D Object Reconstruction Deep Learning Systems are used:

3D reconstruction technology can be used in the Police Department for drawing the faces of criminals whose images have been procured from a crime site where their faces are not completely revealed.
It can be used for re-modelling ruins at ancient architectural sites. The rubble or the debris stubs of structures can be used to recreate the entire building structure and get an idea of how it looked in the past.
They can be used in plastic surgery where the organs, face, limbs or any other portion of the body has been damaged and needs to be rebuilt.
It can be used in airport security, where concealed shapes can be used for guessing whether a person is armed or is carrying explosives or not.
It can also help in completing DNA sequences.

So, if you are planning to implement this technology, then you can rent the required infrastructure from E2E Networks and avoid investing in it. And if you plan to learn more about such topics, then keep a tab on the blog section of the website.

‍

Reference Links

https://tongtianta.site/paper/68922

https://github.com/natowi/3D-Reconstruction-with-Deep-Learning-Methods

This is a decorative image for: Comprehensive Guide to Deep Q-Learning for Data Science Enthusiasts

October 18, 2022

A Comprehensive Guide To Deep Q-Learning For Data Science Enthusiasts

For all data science enthusiasts who would love to dig deep, we have composed a write-up about Q-Learning specifically for you all. Deep Q-Learning and Reinforcement learning (RL) are extremely popular these days. These two data science methodologies use Python libraries like TensorFlow 2 and openAI’s Gym environment.

So, read on to know more.

What is Deep Q-Learning?

Deep Q-Learning utilizes the principles of Q-learning, but instead of using the Q-table, it uses the neural network. The algorithm of deep Q-Learning uses the states as input and the optimal Q-value of every action possible as the output. The agent gathers and stores all the previous experiences in the memory of the trained tuple in the following order:

State> Next state> Action> Reward

The neural network training stability increases using a random batch of previous data by using the experience replay. Experience replay also means the previous experiences stocking, and the target network uses it for training and calculation of the Q-network and the predicted Q-Value. This neural network uses openAI Gym, which is provided by taxi-v3 environments.

Now, any understanding of Deep Q-Learning is incomplete without talking about Reinforcement Learning.

What is Reinforcement Learning?

Reinforcement is a subsection of ML. This part of ML is related to the action in which an environmental agent participates in a reward-based system and uses Reinforcement Learning to maximize the rewards. Reinforcement Learning is a different technique from unsupervised learning or supervised learning because it does not require a supervised input/output pair. The number of corrections is also less, so it is a highly efficient technique.

Now, the understanding of reinforcement learning is incomplete without knowing about Markov Decision Process (MDP). MDP is involved with each state that has been presented in the results of the environment, derived from the state previously there. The information which composes both states is gathered and transferred to the decision process. The task of the chosen agent is to maximize the awards. The MDP optimizes the actions and helps construct the optimal policy.

For developing the MDP, you need to follow the Q-Learning Algorithm, which is an extremely important part of data science and machine learning.

What is Q-Learning Algorithm?

The process of Q-Learning is important for understanding the data from scratch. It involves defining the parameters, choosing the actions from the current state and also choosing the actions from the previous state and then developing a Q-table for maximizing the results or output rewards.

The 4 steps that are involved in Q-Learning:

Initializing parameters – The RL (reinforcement learning) model learns the set of actions that the agent requires in the state, environment and time.
Identifying current state – The model stores the prior records for optimal action definition for maximizing the results. For acting in the present state, the state needs to be identified and perform an action combination for it.
Choosing the optimal action set and gaining the relevant experience – A Q-table is generated from the data with a set of specific states and actions, and the weight of this data is calculated for updating the Q-Table to the following step.
Updating Q-table rewards and next state determination – After the relevant experience is gained and agents start getting environmental records. The reward amplitude helps to present the subsequent step.

In case the Q-table size is huge, then the generation of the model is a time-consuming process. This situation requires Deep Q-learning.

Hopefully, this write-up has provided an outline of Deep Q-Learning and its related concepts. If you wish to learn more about such topics, then keep a tab on the blog section of the E2E Networks website.

Reference Links

https://analyticsindiamag.com/comprehensive-guide-to-deep-q-learning-for-data-science-enthusiasts/

https://medium.com/@jereminuerofficial/a-comprehensive-guide-to-deep-q-learning-8aeed632f52f

October 13, 2022

GAUDI: A Neural Architect for Immersive 3D Scene Generation

The evolution of artificial intelligence in the past decade has been staggering, and now the focus is shifting towards AI and ML systems to understand and generate 3D spaces. As a result, there has been extensive research on manipulating 3D generative models. In this regard, Apple’s AI and ML scientists have developed GAUDI, a method specifically for this job.

An introduction to GAUDI

The GAUDI 3D immersive technique founders named it after the famous architect Antoni Gaudi. This AI model takes the help of a camera pose decoder, which enables it to guess the possible camera angles of a scene. Hence, the decoder then makes it possible to predict the 3D canvas from almost every angle.

What does GAUDI do?

GAUDI can perform multiple functions –

The extensions of these generative models have a tremendous effect on ML and computer vision. Pragmatically, such models are highly useful. They are applied in model-based reinforcement learning and planning world models, SLAM is s, or 3D content creation.
Generative modelling for 3D objects has been used for generating scenes using graf, pigan, and gsn, which incorporate a GAN (Generative Adversarial Network). The generator codes radiance fields exclusively. Using the 3D space in the scene along with the camera pose generates the 3D image from that point. This point has a density scalar and RGB value for that specific point in 3D space. This can be done from a 2D camera view. It does this by imposing 3D datasets on those 2D shots. It isolates various objects and scenes and combines them to render a new scene altogether.
GAUDI also removes GANs pathologies like mode collapse and improved GAN.
GAUDI also uses this to train data on a canonical coordinate system. You can compare it by looking at the trajectory of the scenes.

How is GAUDI applied to the content?

The steps of application for GAUDI have been given below:

Each trajectory is created, which consists of a sequence of posed images (These images are from a 3D scene) encoded into a latent representation. This representation which has a radiance field or what we refer to as the 3D scene and the camera path is created in a disentangled way. The results are interpreted as free parameters. The problem is optimized by and formulation of a reconstruction objective.
This simple training process is then scaled to trajectories, thousands of them creating a large number of views. The model samples the radiance fields totally from the previous distribution that the model has learned.
The scenes are thus synthesized by interpolation within the hidden space.
The scaling of 3D scenes generates many scenes that contain thousands of images. During training, there is no issue related to canonical orientation or mode collapse.
A novel de-noising optimization technique is used to find hidden representations that collaborate in modelling the camera poses and the radiance field to create multiple datasets with state-of-the-art performance in generating 3D scenes by building a setup that uses images and text.

To conclude, GAUDI has more capabilities and can also be used for sampling various images and video datasets. Furthermore, this will make a foray into AR (augmented reality) and VR (virtual reality). With GAUDI in hand, the sky is only the limit in the field of media creation. So, if you enjoy reading about the latest development in the field of AI and ML, then keep a tab on the blog section of the E2E Networks website.

‍

Reference Links

https://www.researchgate.net/publication/362323995_GAUDI_A_Neural_Architect_for_Immersive_3D_Scene_Generation

https://www.technology.org/2022/07/31/gaudi-a-neural-architect-for-immersive-3d-scene-generation/

https://www.patentlyapple.com/2022/08/apple-has-unveiled-gaudi-a-neural-architect-for-immersive-3d-scene-generation.html