Skip to content

Commit

Permalink
docs(README): Fix quick starts examples (#875)
Browse files Browse the repository at this point in the history 
Closes #872
<!-- ELLIPSIS_HIDDEN -->


----

> [!IMPORTANT]
> Fixes and updates quick start examples in `README.md`, including
search query count, API placeholders, and workflow steps.
> 
>   - **Quick Example**:
>     - Change number of search queries from 100 to 30.
>     - Update `api_key` and `url` placeholders in `tools` section.
> - Modify `main` workflow steps for clarity and accuracy, including
`prompt`, `evaluate`, and `tool` steps.
>   - **Misc**:
>     - Add `num_questions` to `input_schema`.
>     - Adjust `parallelism` from 10 to 5 in web search step.
>     - Limit Discord message content to 2000 characters.
> 
> <sup>This description was created by </sup>[<img alt="Ellipsis"
src="https://img.shields.io/badge/Ellipsis-blue?color=175173">](https://www.ellipsis.dev?ref=julep-ai%2Fjulep&utm_source=github&utm_medium=referral)<sup>
for 7063583. It will automatically
update as commits are pushed.</sup>


<!-- ELLIPSIS_HIDDEN -->
  • Loading branch information
@HamadaSalhab
HamadaSalhab authored Nov 23, 2024
1 parent f27c4a1 commit 7810756
Showing 1 changed file with 60 additions and 60 deletions.
120 changes: 60 additions & 60 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -28,14 +28,12 @@
---

> [!NOTE]
> 👨‍💻 Here for the devfest.ai event? Join our [Discord](https://discord.com/invite/JTSBGRZrzj) and check out the details below.
>
> Get your API key [here](https://dashboard-dev.julep.ai).
<details>
<summary><b>🌟 Contributors and DevFest.AI Participants</b> (Click to expand)</summary>
<summary><b>Contributions 🌟</b> (Click to expand)</summary>

## 🌟 Call for Contributors!
## Call for Contributors 🌟

We're excited to welcome new contributors to the Julep project! We've created several "good first issues" to help you get started. Here's how you can contribute:

Expand All @@ -45,41 +43,34 @@ We're excited to welcome new contributors to the Julep project! We've created se

Your contributions, big or small, are valuable to us. Let's build something amazing together! 🚀

### 🎉 DevFest.AI October 2024

Exciting news! We're participating in DevFest.AI throughout October 2024! 🗓️

- Contribute to Julep during this event and get a chance to win awesome Julep merch and swag! 🎁
- Join developers from around the world in contributing to AI repositories and participating in amazing events.
- A big thank you to DevFest.AI for organizing this fantastic initiative!

> [!TIP]
> Ready to join the fun? **[Tweet that you are participating](https://twitter.com/intent/tweet?text=Pumped%20to%20be%20participating%20in%20%40devfestai%20with%20%40julep_ai%20building%20%23ai%20%23agents%20%23workflows%20Let's%20gooo!%20https%3A%2F%2Fgit.new%2Fjulep)** and let's get coding! 🖥️
![Julep DevFest.AI](https://media.giphy.com/media/YjyUeyotft6epaMHtU/giphy.gif)

</details>

<!-- START doctoc generated TOC please keep comment here to allow auto update -->
<!-- DON'T EDIT THIS SECTION, INSTEAD RE-RUN doctoc TO UPDATE -->
<h3>📖 Table of Contents</h3>

- [Call for Contributors 🌟](#call-for-contributors-)
- [Introduction](#introduction)
- [Key Features](#key-features)
- [Quick Example](#quick-example)
- [Installation](#installation)
- [Python Quick Start 🐍](#python-quick-start-)
- [Node.js Quick Start 🟩](#nodejs-quick-start-)
- [Step 1: Create an Agent](#step-1-create-an-agent)
- [Components](#components)
- [Mental Model](#mental-model)
- [Concepts](#concepts)
- [Understanding Tasks](#understanding-tasks)
- [Lifecycle of a Task](#lifecycle-of-a-task)
- [Types of Workflow Steps](#types-of-workflow-steps)
- [Common Steps](#common-steps)
- [Key-Value Steps](#key-value-steps)
- [Iteration Steps](#iteration-steps)
- [Conditional Steps](#conditional-steps)
- [Other Control Flow](#other-control-flow)
- [Tool Types](#tool-types)
- [User-defined `functions`](#user-defined-functions)
- [`system` tools](#system-tools)
- [Available `system` resources and operations](#available-system-resources-and-operations)
- [Built-in `integrations`](#built-in-integrations)
- [Direct `api_calls`](#direct-api_calls)
- [Integrations](#integrations)
Expand Down Expand Up @@ -135,7 +126,7 @@ While many AI applications are limited to simple, linear chains of prompts and A
Imagine a Research AI agent that can do the following:

1. **Take a topic**,
2. **Come up with 100 search queries** for that topic,
2. **Come up with 30 search queries** for that topic,
3. Perform those web **searches in parallel**,
4. **Summarize** the results,
5. Send the **summary to Discord**.
Expand All @@ -155,6 +146,9 @@ input_schema:
topic:
type: string
description: The main topic to research
num_questions:
type: integer
description: The number of search queries to generate

# Define the tools that the agent can use
tools:
Expand All @@ -163,12 +157,12 @@ tools:
integration:
provider: brave
setup:
api_key: BSAqES7dj9d... # dummy key
api_key: <your-brave-api-key>

- name: discord_webhook
type: api_call
api_call:
url: https://eobuxj02se0n.m.pipedream.net # dummy requestbin
url: https://discord.com/api/webhooks/<your-webhook-id>/<your-webhook-token>
method: POST
headers:
Content-Type: application/json
Expand All @@ -180,52 +174,57 @@ tools:

# Define the main workflow
main:
- prompt:
- role: system
content: >-
You are a research assistant.
Generate 100 diverse search queries related to the topic:
{{inputs[0].topic}}
- prompt:
- role: system
content: >-
You are a research assistant.
Generate {{inputs[0].num_questions|default(30, true)}} diverse search queries related to the topic:
{{inputs[0].topic}}
Write one query per line.
unwrap: true
Write one query per line.
unwrap: true

# Evaluate the search queries using a simple python expression
- evaluate:
search_queries: "_.split('\n')"
# Evaluate the search queries using a simple python expression
- evaluate:
search_queries: "_.split(NEWLINE)"

# Run the web search in parallel for each query
- over: "_.search_queries"
map:
tool: web_search
arguments:
query: "_"
parallelism: 10
# Run the web search in parallel for each query
- over: "_.search_queries"
map:
tool: web_search
arguments:
query: "_"
parallelism: 5

# Collect the results from the web search
- evaluate:
results: "'\n'.join([item.result for item in _])"
# Collect the results from the web search
- evaluate:
search_results: _

# Summarize the results
- prompt:
- role: system
content: >
You are a research summarizer. Create a comprehensive summary of the following research results on the topic {{inputs[0].topic}}.
The summary should be well-structured, informative, and highlight key findings and insights:
{{_.results}}
unwrap: true
settings:
model: gpt-4o-mini
# Summarize the results
- prompt:
- role: system
content: >
You are a research summarizer. Create a comprehensive summary of the following research results on the topic {{inputs[0].topic}}.
The summary should be well-structured, informative, and highlight key findings and insights. Keep the summary concise and to the point.
The length of the summary should be less than 150 words.
Here are the search results:
{{_.search_results}}
unwrap: true
settings:
model: gpt-4o-mini

# Send the summary to Discord
- tool: discord_webhook
arguments:
content: |-
f'''
**Research Summary for {inputs[0].topic}**
- evaluate:
discord_message: |-
f'''
**Research Summary for {inputs[0].topic}**
{_}
'''
{_}
'''
# Send the summary to Discord
- tool: discord_webhook
arguments:
json_:
content: _.discord_message[:2000] # Discord has a 2000 character limit
```
In this example, Julep will automatically manage parallel executions, retry failed steps, resend API requests, and keep the tasks running reliably until completion.
Expand Down Expand Up @@ -331,6 +330,7 @@ description: Create a story based on an idea.
tools:
- name: research_wikipedia
type: integration
integration:
provider: wikipedia
method: search
Expand Down

0 comments on commit 7810756

Please sign in to comment.