update utility
This commit is contained in:
zachary62
parent
8e13414687
commit
21744b7a3f
|
|
@ -54,7 +54,6 @@ Agentic Coding should be a collaboration between Human System Design and Agent I
|
|||
- *Output*: a vector of 3072 floats
|
||||
- *Necessity:* Used by the second node to embed text
|
||||
|
||||
|
||||
4. **Node Design**: Plan how each node will read and write data, and use utility functions.
|
||||
- Start with the shared data design
|
||||
- For simple systems, use an in-memory dictionary.
|
||||
|
|
@ -66,7 +65,6 @@ Agentic Coding should be a collaboration between Human System Design and Agent I
|
|||
- `exec`: Call the embedding utility function
|
||||
- `post`: Write "embedding" to the shared store
|
||||
|
||||
|
||||
5. **Implementation**: Implement the initial nodes and flows based on the design.
|
||||
- 🎉 If you’ve reached this step, humans have finished the design. Now *Agentic Coding* begins!
|
||||
- **“Keep it simple, stupid!”** Avoid complex features and full-scale type checking.
|
||||
|
|
|
|||
|
|
@ -25,7 +25,7 @@ We model the LLM workflow as a **Graph + Shared Store**:
|
|||
- [Flow](./core_abstraction/flow.md) connects nodes through **Actions** (labeled edges).
|
||||
- [Shared Store](./core_abstraction/communication.md) enables communication between nodes within flows.
|
||||
- [Batch](./core_abstraction/batch.md) nodes/flows allow for data-intensive tasks.
|
||||
- [(Advanced) Async](./core_abstraction/async.md) nodes/flows allow waiting for asynchronous tasks.
|
||||
- [Async](./core_abstraction/async.md) nodes/flows allow waiting for asynchronous tasks.
|
||||
- [(Advanced) Parallel](./core_abstraction/parallel.md) nodes/flows handle I/O-bound tasks.
|
||||
|
||||
<div align="center">
|
||||
|
|
@ -49,15 +49,20 @@ From there, it’s easy to implement popular design patterns:
|
|||
|
||||
## Utility Function
|
||||
|
||||
We provide utility functions not in *codes*, but in *docs*:
|
||||
We **DON'T** provide built-in utility functions. Instead, please implement your own. I believe it is a **bad practice** to provide vendor-specific implementations in a general framework:
|
||||
|
||||
- **Vendor APIs change frequently**. Hardcoding them makes maintenance a nightmare.
|
||||
- You may need **flexibility** to switch vendors, use fine-tuned models, or deploy local LLMs.
|
||||
- You may need **optimizations** like prompt caching, request batching, or response streaming.
|
||||
|
||||
However, we provide example implementations for commonly used utility functions.
|
||||
|
||||
- [LLM Wrapper](./utility_function/llm.md)
|
||||
- [Tool](./utility_function/tool.md)
|
||||
- [(Optional) Viz and Debug](./utility_function/viz.md)
|
||||
- [(Optional) Web Search](./utility_function/websearch.md)
|
||||
- [(Optional) Chunking](./utility_function/chunking.md)
|
||||
- [(Optional) Embedding](./utility_function/embedding.md)
|
||||
- [(Optional) Vector Databases](./utility_function/vector.md)
|
||||
- [(Optional) Text-to-Speech](./utility_function/text_to_speech.md)
|
||||
- [Viz and Debug](./utility_function/viz.md)
|
||||
- [Web Search](./utility_function/websearch.md)
|
||||
- [Chunking](./utility_function/chunking.md)
|
||||
- [Embedding](./utility_function/embedding.md)
|
||||
- [Vector Databases](./utility_function/vector.md)
|
||||
- [Text-to-Speech](./utility_function/text_to_speech.md)
|
||||
|
||||
## Ready to build your Apps? [Learn Agentic Coding!](./guide.md)
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
layout: default
|
||||
title: "Text Chunking"
|
||||
parent: "Utility Function"
|
||||
nav_order: 5
|
||||
nav_order: 4
|
||||
---
|
||||
|
||||
# Text Chunking
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
layout: default
|
||||
title: "Embedding"
|
||||
parent: "Utility Function"
|
||||
nav_order: 6
|
||||
nav_order: 5
|
||||
---
|
||||
|
||||
# Embedding
|
||||
|
|
|
|||
|
|
@ -7,7 +7,7 @@ nav_order: 1
|
|||
|
||||
# LLM Wrappers
|
||||
|
||||
We **don't** provide built-in LLM wrappers. Instead, please implement your own or check out libraries like [litellm](https://github.com/BerriAI/litellm).
|
||||
Check out libraries like [litellm](https://github.com/BerriAI/litellm).
|
||||
Here, we provide some minimal example implementations:
|
||||
|
||||
1. OpenAI
|
||||
|
|
@ -141,8 +141,3 @@ def call_llm(prompt):
|
|||
return response
|
||||
```
|
||||
|
||||
## Why Not Provide Built-in LLM Wrappers?
|
||||
I believe it is a **bad practice** to provide LLM-specific implementations in a general framework:
|
||||
- **LLM APIs change frequently**. Hardcoding them makes maintenance a nightmare.
|
||||
- You may need **flexibility** to switch vendors, use fine-tuned models, or deploy local LLMs.
|
||||
- You may need **optimizations** like prompt caching, request batching, or response streaming.
|
||||
|
|
@ -2,7 +2,7 @@
|
|||
layout: default
|
||||
title: "Text-to-Speech"
|
||||
parent: "Utility Function"
|
||||
nav_order: 8
|
||||
nav_order: 7
|
||||
---
|
||||
|
||||
# Text-to-Speech
|
||||
|
|
|
|||
|
|
@ -1,199 +0,0 @@
|
|||
---
|
||||
layout: default
|
||||
title: "Tool"
|
||||
parent: "Utility Function"
|
||||
nav_order: 2
|
||||
---
|
||||
|
||||
# Tool
|
||||
|
||||
Similar to LLM wrappers, we **don't** provide built-in tools. Here, we recommend some *minimal* (and incomplete) implementations of commonly used tools. These examples can serve as a starting point for your own tooling.
|
||||
|
||||
---
|
||||
|
||||
## 1. Embedding Calls
|
||||
|
||||
```python
|
||||
def get_embedding(text):
|
||||
from openai import OpenAI
|
||||
client = OpenAI(api_key="YOUR_API_KEY_HERE")
|
||||
r = client.embeddings.create(
|
||||
model="text-embedding-ada-002",
|
||||
input=text
|
||||
)
|
||||
return r.data[0].embedding
|
||||
|
||||
get_embedding("What's the meaning of life?")
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 2. Vector Database (Faiss)
|
||||
|
||||
```python
|
||||
import faiss
|
||||
import numpy as np
|
||||
|
||||
def create_index(embeddings):
|
||||
dim = len(embeddings[0])
|
||||
index = faiss.IndexFlatL2(dim)
|
||||
index.add(np.array(embeddings).astype('float32'))
|
||||
return index
|
||||
|
||||
def search_index(index, query_embedding, top_k=5):
|
||||
D, I = index.search(
|
||||
np.array([query_embedding]).astype('float32'),
|
||||
top_k
|
||||
)
|
||||
return I, D
|
||||
|
||||
index = create_index(embeddings)
|
||||
search_index(index, query_embedding)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 3. Local Database
|
||||
|
||||
```python
|
||||
import sqlite3
|
||||
|
||||
def execute_sql(query):
|
||||
conn = sqlite3.connect("mydb.db")
|
||||
cursor = conn.cursor()
|
||||
cursor.execute(query)
|
||||
result = cursor.fetchall()
|
||||
conn.commit()
|
||||
conn.close()
|
||||
return result
|
||||
```
|
||||
|
||||
> ⚠️ Beware of SQL injection risk
|
||||
{: .warning }
|
||||
|
||||
---
|
||||
|
||||
## 4. Python Function Execution
|
||||
|
||||
```python
|
||||
def run_code(code_str):
|
||||
env = {}
|
||||
exec(code_str, env)
|
||||
return env
|
||||
|
||||
run_code("print('Hello, world!')")
|
||||
```
|
||||
|
||||
> ⚠️ exec() is dangerous with untrusted input
|
||||
{: .warning }
|
||||
|
||||
|
||||
---
|
||||
|
||||
## 5. PDF Extraction
|
||||
|
||||
If your PDFs are text-based, use PyMuPDF:
|
||||
|
||||
```python
|
||||
import fitz # PyMuPDF
|
||||
|
||||
def extract_text(pdf_path):
|
||||
doc = fitz.open(pdf_path)
|
||||
text = ""
|
||||
for page in doc:
|
||||
text += page.get_text()
|
||||
doc.close()
|
||||
return text
|
||||
|
||||
extract_text("document.pdf")
|
||||
```
|
||||
|
||||
For image-based PDFs (e.g., scanned), OCR is needed. A easy and fast option is using an LLM with vision capabilities:
|
||||
|
||||
```python
|
||||
from openai import OpenAI
|
||||
import base64
|
||||
|
||||
def call_llm_vision(prompt, image_data):
|
||||
client = OpenAI(api_key="YOUR_API_KEY_HERE")
|
||||
img_base64 = base64.b64encode(image_data).decode('utf-8')
|
||||
|
||||
response = client.chat.completions.create(
|
||||
model="gpt-4o",
|
||||
messages=[{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "text", "text": prompt},
|
||||
{"type": "image_url",
|
||||
"image_url": {"url": f"data:image/png;base64,{img_base64}"}}
|
||||
]
|
||||
}]
|
||||
)
|
||||
|
||||
return response.choices[0].message.content
|
||||
|
||||
pdf_document = fitz.open("document.pdf")
|
||||
page_num = 0
|
||||
page = pdf_document[page_num]
|
||||
pix = page.get_pixmap()
|
||||
img_data = pix.tobytes("png")
|
||||
|
||||
call_llm_vision("Extract text from this image", img_data)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 6. Web Crawling
|
||||
|
||||
```python
|
||||
def crawl_web(url):
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
html = requests.get(url).text
|
||||
soup = BeautifulSoup(html, "html.parser")
|
||||
return soup.title.string, soup.get_text()
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
|
||||
## 7. Audio Transcription (OpenAI Whisper)
|
||||
|
||||
```python
|
||||
def transcribe_audio(file_path):
|
||||
import openai
|
||||
audio_file = open(file_path, "rb")
|
||||
transcript = openai.Audio.transcribe("whisper-1", audio_file)
|
||||
return transcript["text"]
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 8. Text-to-Speech (TTS)
|
||||
|
||||
```python
|
||||
def text_to_speech(text):
|
||||
import pyttsx3
|
||||
engine = pyttsx3.init()
|
||||
engine.say(text)
|
||||
engine.runAndWait()
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 9. Sending Email
|
||||
|
||||
```python
|
||||
def send_email(to_address, subject, body, from_address, password):
|
||||
import smtplib
|
||||
from email.mime.text import MIMEText
|
||||
|
||||
msg = MIMEText(body)
|
||||
msg["Subject"] = subject
|
||||
msg["From"] = from_address
|
||||
msg["To"] = to_address
|
||||
|
||||
with smtplib.SMTP_SSL("smtp.gmail.com", 465) as server:
|
||||
server.login(from_address, password)
|
||||
server.sendmail(from_address, [to_address], msg.as_string())
|
||||
```
|
||||
|
|
@ -2,7 +2,7 @@
|
|||
layout: default
|
||||
title: "Vector Databases"
|
||||
parent: "Utility Function"
|
||||
nav_order: 7
|
||||
nav_order: 6
|
||||
---
|
||||
|
||||
# Vector Databases
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
layout: default
|
||||
title: "Viz and Debug"
|
||||
parent: "Utility Function"
|
||||
nav_order: 3
|
||||
nav_order: 2
|
||||
---
|
||||
|
||||
# Visualization and Debugging
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
layout: default
|
||||
title: "Web Search"
|
||||
parent: "Utility Function"
|
||||
nav_order: 4
|
||||
nav_order: 3
|
||||
---
|
||||
# Web Search
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue