forked from sheetjs/docs.sheetjs.com
Perl JE demo refresh
This commit is contained in:
parent
c4d9ba0948
commit
7f0bda6af6
@ -36,15 +36,43 @@ This demo was tested in the following configurations:
|
||||
| Date | Platform |
|
||||
|:-----------|:--------------------------------------------------------------|
|
||||
| 2024-06-19 | Apple M2 Max 12-Core CPU + 30-Core GPU (32 GB unified memory) |
|
||||
| 2024-06-28 | NVIDIA RTX 4090 (24 GB VRAM) + i9-10910 (128 GB RAM) |
|
||||
| 2024-06-19 | NVIDIA RTX 4080 SUPER (16 GB VRAM) + i9-10910 (128 GB RAM) |
|
||||
| 2024-06-19 | NVIDIA RTX 3090 (24 GB VRAM) + Ryzen 9 3900XT (128 GB RAM) |
|
||||
|
||||
This explanation was verified against LangChain 0.2.
|
||||
SheetJS users have verified this demo in other configurations:
|
||||
|
||||
<details>
|
||||
<summary><b>Other tested configurations</b> (click to show)</summary>
|
||||
|
||||
| Demo | Platform |
|
||||
|:------------|:-------------------------------------------------------------|
|
||||
| LangChainJS | NVIDIA RTX 4070 Ti (12 GB VRAM) + Ryzen 7 5800x (64 GB RAM) |
|
||||
| LangChainJS | NVIDIA RTX 3090 (24 GB VRAM) + Ryzen 9 3900XT (128 GB RAM) |
|
||||
| LangChainJS | NVIDIA RTX 3060 (12 GB VRAM) + i5-11400 (32 GB RAM) |
|
||||
| LangChainJS | NVIDIA RTX 2080 (12 GB VRAM) + i7-9700K (16 GB RAM) |
|
||||
| LangChainJS | NVIDIA RTX 2060 (6 GB VRAM) + Ryzen 5 3600 (32 GB RAM) |
|
||||
| LangChainJS | NVIDIA GTX 1080 (8 GB VRAM) + Ryzen 7 5800x (64 GB RAM) |
|
||||
|
||||
</details>
|
||||
|
||||
Special thanks to:
|
||||
|
||||
- [`@Rasmus`](https://tengstedt.dev/)
|
||||
- [Ben Halverson](https://benhalverson.dev/)
|
||||
- [Navid Nami](https://github.com/CaseoJKL)
|
||||
- [`@Smor`](https://smor.dev/)
|
||||
- [`@timbr`](https://timbr.dev/)
|
||||
|
||||
:::
|
||||
|
||||
## CSV Loader
|
||||
|
||||
:::note pass
|
||||
|
||||
This explanation was verified against LangChain 0.2.
|
||||
|
||||
:::
|
||||
|
||||
Document loaders generate data objects ("documents") and associated metadata
|
||||
from data sources.
|
||||
|
||||
@ -638,12 +666,22 @@ export default class LoadOfSheet extends BufferLoader {
|
||||
The demo performs the query "Which rows have over 40 miles per gallon?" against
|
||||
a [sample cars dataset](pathname:///cd.xls) and displays the results.
|
||||
|
||||
:::note pass
|
||||
|
||||
SheetJS team members have tested this demo on Windows 10 and Windows 11 using
|
||||
PowerShell and Ollama for Windows.
|
||||
|
||||
SheetJS users have also tested this demo within Windows Subsystem for Linux.
|
||||
|
||||
:::
|
||||
|
||||
:::caution pass
|
||||
|
||||
This demo was tested using the ChatQA-1.5 model[^9] in Ollama[^10].
|
||||
|
||||
The tested model requires 9.2GB VRAM. It is strongly recommended to run the demo
|
||||
on a newer Apple Silicon Mac or a PC with an Nvidia GPU with at least 12GB VRAM.
|
||||
The tested model used up to 9.2GB VRAM. It is strongly recommended to run the
|
||||
demo on a newer Apple Silicon Mac or a PC with an Nvidia GPU with at least 12GB
|
||||
VRAM. SheetJS users have tested the demo on systems with as little as 6GB VRAM.
|
||||
|
||||
:::
|
||||
|
||||
@ -665,16 +703,33 @@ curl -LO https://docs.sheetjs.com/loadofsheet/query.mjs
|
||||
curl -LO https://docs.sheetjs.com/loadofsheet/loadofsheet.mjs
|
||||
```
|
||||
|
||||
:::note pass
|
||||
|
||||
In PowerShell, the command may fail with a parameter error:
|
||||
|
||||
```
|
||||
Invoke-WebRequest : A parameter cannot be found that matches parameter name 'LO'.
|
||||
```
|
||||
|
||||
`curl.exe` must be invoked directly:
|
||||
|
||||
```bash
|
||||
curl.exe -LO https://docs.sheetjs.com/loadofsheet/query.mjs
|
||||
curl.exe -LO https://docs.sheetjs.com/loadofsheet/loadofsheet.mjs
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
2) Install the SheetJS NodeJS module:
|
||||
|
||||
<CodeBlock language="bash">{`\
|
||||
npm i --save https://cdn.sheetjs.com/xlsx-${current}/xlsx-${current}.tgz`}
|
||||
</CodeBlock>
|
||||
|
||||
3) Install LangChain and HNSWLib dependencies:
|
||||
3) Install dependencies:
|
||||
|
||||
```bash
|
||||
npm i --save @langchain/community@0.2.0 @langchain/core@0.2.6 langchain@0.2.5 hnswlib-node@3.0.0 peggy@3.0.2
|
||||
npm i --save @langchain/community@0.2.0 @langchain/core@0.2.6 langchain@0.2.5 peggy@3.0.2
|
||||
```
|
||||
|
||||
4) Download the [cars dataset](pathname:///cd.xls):
|
||||
@ -683,6 +738,22 @@ npm i --save @langchain/community@0.2.0 @langchain/core@0.2.6 langchain@0.2.5 hn
|
||||
curl -LO https://docs.sheetjs.com/cd.xls
|
||||
```
|
||||
|
||||
:::note pass
|
||||
|
||||
In PowerShell, the command may fail with a parameter error:
|
||||
|
||||
```
|
||||
Invoke-WebRequest : A parameter cannot be found that matches parameter name 'LO'.
|
||||
```
|
||||
|
||||
`curl.exe` must be invoked directly:
|
||||
|
||||
```bash
|
||||
curl.exe -LO https://docs.sheetjs.com/cd.xls
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
5) Install the `llama3-chatqa:8b-v1.5-q8_0` model using Ollama:
|
||||
|
||||
```bash
|
||||
@ -705,7 +776,7 @@ node query.mjs
|
||||
The demo performs the query "Which rows have over 40 miles per gallon?". It will
|
||||
print the following nine results:
|
||||
|
||||
```js title="Expected output"
|
||||
```js title="Expected output (order of lines may differ)"
|
||||
{ Name: 'volkswagen rabbit custom diesel', MPG: 43.1 }
|
||||
{ Name: 'vw rabbit c (diesel)', MPG: 44.3 }
|
||||
{ Name: 'renault lecar deluxe', MPG: 40.9 }
|
||||
|
@ -41,7 +41,7 @@ This demo was tested in the following deployments:
|
||||
| Architecture | JS Engine | Pandas | Python | Date |
|
||||
|:-------------|:----------------|:-------|:-------|:-----------|
|
||||
| `darwin-x64` | Duktape `2.7.0` | 2.2.1 | 3.12.2 | 2024-03-15 |
|
||||
| `darwin-arm` | Duktape `2.7.0` | 2.0.3 | 3.11.7 | 2024-02-13 |
|
||||
| `darwin-arm` | Duktape `2.7.0` | 2.2.2 | 3.12.3 | 2024-06-30 |
|
||||
| `win10-x64` | Duktape `2.7.0` | 2.2.1 | 3.12.2 | 2024-03-25 |
|
||||
| `win11-arm` | Duktape `2.7.0` | 2.2.2 | 3.11.5 | 2024-06-20 |
|
||||
| `linux-x64` | Duktape `2.7.0` | 1.5.3 | 3.11.3 | 2024-03-21 |
|
||||
@ -520,7 +520,7 @@ This demo was tested in the following deployments:
|
||||
| Architecture | JS Engine | Polars | Python | Date |
|
||||
|:-------------|:----------------|:--------|:-------|:-----------|
|
||||
| `darwin-x64` | Duktape `2.7.0` | 0.20.15 | 3.12.2 | 2024-03-15 |
|
||||
| `darwin-arm` | Duktape `2.7.0` | 0.20.7 | 3.11.7 | 2024-02-13 |
|
||||
| `darwin-arm` | Duktape `2.7.0` | 0.20.31 | 3.12.3 | 2024-06-30 |
|
||||
| `win10-x64` | Duktape `2.7.0` | 0.20.16 | 3.12.2 | 2024-03-25 |
|
||||
| `win10-arm` | Duktape `2.7.0` | 0.20.31 | 3.11.5 | 2024-06-20 |
|
||||
| `linux-x64` | Duktape `2.7.0` | 0.20.16 | 3.11.3 | 2024-03-21 |
|
||||
@ -612,6 +612,12 @@ sudo apt-get install python3.11-venv
|
||||
|
||||
- `venv` is included in the `python` package in Arch Linux-based platforms.
|
||||
|
||||
- macOS systems with a Python version from Homebrew:
|
||||
|
||||
```bash
|
||||
brew install pyenv-virtualenv
|
||||
```
|
||||
|
||||
After installing `venv`, the following commands set up the virtual environment:
|
||||
|
||||
```bash
|
||||
|
@ -129,8 +129,9 @@ This demo was tested in the following environments:
|
||||
|
||||
| NodeJS | Date | Dependencies |
|
||||
|:----------|:-----------|:------------------------------------|
|
||||
| `18.19.1` | 2024-02-23 | ExpressJS 4.18.2 + Formidable 2.1.2 |
|
||||
| `20.11.1` | 2024-02-23 | ExpressJS 4.18.2 + Formidable 2.1.2 |
|
||||
| `18.20.3` | 2024-06-30 | ExpressJS 4.19.2 + Formidable 2.1.2 |
|
||||
| `20.15.0` | 2024-06-30 | ExpressJS 4.19.2 + Formidable 2.1.2 |
|
||||
| `22.3.0` | 2024-06-30 | ExpressJS 4.19.2 + Formidable 2.1.2 |
|
||||
|
||||
:::
|
||||
|
||||
@ -145,7 +146,7 @@ echo '{ "type": "module" }' > package.json
|
||||
1) Install the dependencies:
|
||||
|
||||
<CodeBlock language="bash">{`\
|
||||
npm i --save https://cdn.sheetjs.com/xlsx-${current}/xlsx-${current}.tgz express@4.18.2 formidable@2.1.2`}
|
||||
npm i --save https://cdn.sheetjs.com/xlsx-${current}/xlsx-${current}.tgz express@4.19.2 formidable@2.1.2`}
|
||||
</CodeBlock>
|
||||
|
||||
2) Create a worker script `worker.js` that listens for messages. When a message
|
||||
|
@ -139,9 +139,6 @@ db.readTransaction(tx =>
|
||||
Using `book_new` and `book_append_sheet`[^5], a workbook object can be created.
|
||||
This workbook is typically exported to the filesystem with `writeFile`[^6].
|
||||
|
||||
|
||||
|
||||
|
||||
## Live Demo
|
||||
|
||||
:::note Tested Deployments
|
||||
@ -150,15 +147,15 @@ This browser demo was tested in the following environments:
|
||||
|
||||
| Browser | Date |
|
||||
|:------------|:-----------|
|
||||
| Chrome 118 | 2024-02-11 |
|
||||
| Chrome 118 | 2024-06-29 |
|
||||
|
||||
Browsers that do not support WebSQL will throw errors:
|
||||
|
||||
| Browser | Date | Error Message |
|
||||
|:------------|:-----------|:------------------------------|
|
||||
| Chrome 120 | 2024-02-11 | `openDatabase is not defined` |
|
||||
| Safari 17.4 | 2024-03-15 | `Web SQL is deprecated` |
|
||||
| Firefox 122 | 2024-03-15 | `openDatabase is not defined` |
|
||||
| Chrome 126 | 2024-06-29 | `openDatabase is not defined` |
|
||||
| Safari 17.1 | 2024-06-29 | `Web SQL is deprecated` |
|
||||
| Firefox 127 | 2024-06-29 | `openDatabase is not defined` |
|
||||
|
||||
:::
|
||||
|
||||
|
@ -22,9 +22,8 @@ Each browser demo was tested in the following environments:
|
||||
|
||||
| Browser | Date | Notes
|
||||
|:------------|:-----------|:-------------------------|
|
||||
| Chrome 121 | 2024-02-21 | |
|
||||
| Safari 17.3 | 2024-02-21 | `text/rtf` not supported |
|
||||
| Brave 1.59 | 2024-02-21 | |
|
||||
| Chrome 126 | 2024-06-30 | |
|
||||
| Safari 17.3 | 2024-06-30 | `text/rtf` not supported |
|
||||
|
||||
:::
|
||||
|
||||
|
@ -171,7 +171,7 @@ npm install
|
||||
"version": "0.0.0",
|
||||
"author": "**",
|
||||
// highlight-next-line
|
||||
"description": "Sample Extension using SheetJS to interact with Chrome",
|
||||
"description": "Sample Extension using SheetJS to interact with Chrome",
|
||||
```
|
||||
|
||||
3) Edit `manifest.ts` and add to the `permissions` array:
|
||||
|
@ -18,14 +18,18 @@ OSA originally supported the "AppleScript" language. Modern macOS releases
|
||||
[SheetJS](https://sheetjs.com) is a JavaScript library for reading and writing
|
||||
data from spreadsheets.
|
||||
|
||||
This demo uses SheetJS in OSA Scripts to pull data from a spreadsheet. We'll
|
||||
explore how to use SheetJS libraries in AppleScript and JavaScript scripts. The
|
||||
["Complete Demo"](#complete-demo) parses workbooks and generates CSV rows.
|
||||
|
||||
:::note Tested Environments
|
||||
|
||||
This demo was tested in the following environments:
|
||||
|
||||
| macOS | Language | Date |
|
||||
|:---------|:------------------|:-----------|
|
||||
| `14.3.1` | AppleScript (OSA) | 2024-02-21 |
|
||||
| `14.3.1` | JavaScript (JXA) | 2024-02-21 |
|
||||
| macOS | Language | Date |
|
||||
|:-------|:------------------|:-----------|
|
||||
| `14.5` | AppleScript (OSA) | 2024-06-30 |
|
||||
| `14.5` | JavaScript (JXA) | 2024-06-30 |
|
||||
|
||||
:::
|
||||
|
||||
@ -263,5 +267,16 @@ chmod +x sheetosa.scpt
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
||||
If successful, CSV rows from the first worksheet will be printed:
|
||||
|
||||
```
|
||||
Name,Index
|
||||
Bill Clinton,42
|
||||
GeorgeW Bush,43
|
||||
Barack Obama,44
|
||||
Donald Trump,45
|
||||
Joseph Biden,46
|
||||
```
|
||||
|
||||
[^1]: See ["Introduction to AppleScript Overview"](https://developer.apple.com/library/archive/documentation/AppleScript/Conceptual/AppleScriptX/AppleScriptX.html) in the Apple Developer documentation for more details.
|
||||
[^2]: See ["Introduction to JavaScript for Automation Release Notes"](https://developer.apple.com/library/archive/releasenotes/InterapplicationCommunication/RN-JavaScriptForAutomation/Articles/Introduction.html) in the Apple Developer documentation for more details.
|
||||
|
@ -145,17 +145,17 @@ This demo was tested in the following deployments:
|
||||
|
||||
| Node Version | Date | Node Status when tested |
|
||||
|:-------------|:-----------|:------------------------|
|
||||
| `0.12.18` | 2024-02-23 | End-of-Life |
|
||||
| `4.9.1` | 2024-02-23 | End-of-Life |
|
||||
| `6.17.1` | 2024-02-23 | End-of-Life |
|
||||
| `8.17.0` | 2024-02-23 | End-of-Life |
|
||||
| `10.24.1` | 2024-02-23 | End-of-Life |
|
||||
| `12.22.12` | 2024-02-23 | End-of-Life |
|
||||
| `14.21.3` | 2024-02-23 | End-of-Life |
|
||||
| `16.20.2` | 2024-02-23 | End-of-Life |
|
||||
| `18.19.1` | 2024-02-23 | Maintenance LTS |
|
||||
| `20.11.1` | 2024-02-23 | Active LTS |
|
||||
| `22.0.0` | 2024-04-25 | Current |
|
||||
| `0.12.18` | 2024-06-30 | End-of-Life |
|
||||
| `4.9.1` | 2024-06-30 | End-of-Life |
|
||||
| `6.17.1` | 2024-06-30 | End-of-Life |
|
||||
| `8.17.0` | 2024-06-30 | End-of-Life |
|
||||
| `10.24.1` | 2024-06-30 | End-of-Life |
|
||||
| `12.22.12` | 2024-06-30 | End-of-Life |
|
||||
| `14.21.3` | 2024-06-30 | End-of-Life |
|
||||
| `16.20.2` | 2024-06-30 | End-of-Life |
|
||||
| `18.20.3` | 2024-06-30 | Maintenance LTS |
|
||||
| `20.15.0` | 2024-06-30 | Active LTS |
|
||||
| `22.3.0` | 2024-06-30 | Current |
|
||||
|
||||
While streaming methods work in End-of-Life versions of NodeJS, production
|
||||
deployments should upgrade to a Current or LTS version of NodeJS.
|
||||
@ -220,8 +220,8 @@ Each browser demo was tested in the following environments:
|
||||
|
||||
| Browser | Date |
|
||||
|:------------|:-----------|
|
||||
| Chrome 121 | 2024-02-23 |
|
||||
| Safari 17.3 | 2024-02-23 |
|
||||
| Chrome 126 | 2024-06-30 |
|
||||
| Safari 17.3 | 2024-06-30 |
|
||||
|
||||
:::
|
||||
|
||||
|
@ -405,7 +405,7 @@ This demo was tested in the following deployments:
|
||||
| Architecture | Version | PHP | Date |
|
||||
|:-------------|:--------|:---------|:-----------|
|
||||
| `darwin-x64` | `2.7.0` | `8.3.4` | 2024-03-15 |
|
||||
| `darwin-arm` | `2.7.0` | `8.3.2` | 2024-02-13 |
|
||||
| `darwin-arm` | `2.7.0` | `8.3.8` | 2024-06-30 |
|
||||
| `linux-x64` | `2.7.0` | `8.2.7` | 2024-03-21 |
|
||||
| `linux-arm` | `2.7.0` | `8.2.18` | 2024-05-25 |
|
||||
|
||||
@ -547,7 +547,7 @@ This demo was tested in the following deployments:
|
||||
| Architecture | Version | Python | Date |
|
||||
|:-------------|:--------|:---------|:-----------|
|
||||
| `darwin-x64` | `2.7.0` | `3.12.2` | 2024-03-15 |
|
||||
| `darwin-arm` | `2.7.0` | `3.11.7` | 2024-02-13 |
|
||||
| `darwin-arm` | `2.7.0` | `3.12.3` | 2024-06-30 |
|
||||
| `linux-x64` | `2.7.0` | `3.11.3` | 2024-03-21 |
|
||||
| `linux-arm` | `2.7.0` | `3.11.2` | 2024-05-25 |
|
||||
|
||||
@ -1015,7 +1015,7 @@ This demo was tested in the following deployments:
|
||||
| Architecture | Version | Date |
|
||||
|:-------------|:--------|:-----------|
|
||||
| `darwin-x64` | `2.2.0` | 2024-03-15 |
|
||||
| `darwin-arm` | `2.2.0` | 2024-02-13 |
|
||||
| `darwin-arm` | `2.2.0` | 2024-06-30 |
|
||||
| `linux-x64` | `2.2.0` | 2024-03-21 |
|
||||
| `linux-arm` | `2.2.0` | 2024-05-25 |
|
||||
|
||||
|
@ -319,7 +319,7 @@ Swift on MacOS supports JavaScriptCore without additional dependencies.
|
||||
| Architecture | Swift | Date |
|
||||
|:-------------|:--------|:-----------|
|
||||
| `darwin-x64` | `5.10` | 2024-04-04 |
|
||||
| `darwin-arm` | `5.9.2` | 2024-02-21 |
|
||||
| `darwin-arm` | `5.10` | 2024-06-30 |
|
||||
|
||||
**Compiled**
|
||||
|
||||
|
@ -1,5 +1,6 @@
|
||||
---
|
||||
title: Perl + JE
|
||||
title: Data Processing with JE
|
||||
sidebar_label: Perl + JE
|
||||
pagination_prev: demos/bigdata/index
|
||||
pagination_next: solutions/input
|
||||
---
|
||||
@ -14,17 +15,35 @@ C engine like [`JavaScript::Duktape`](/docs/demos/engines/duktape#perl)
|
||||
|
||||
:::
|
||||
|
||||
JE is a pure-Perl JavaScript engine.
|
||||
[`JE`](https://metacpan.org/pod/JE) is a pure-Perl JavaScript engine.
|
||||
|
||||
The [ExtendScript build](/docs/getting-started/installation/extendscript) can be
|
||||
parsed and evaluated in a JE context.
|
||||
[SheetJS](https://sheetjs.com) is a JavaScript library for reading and writing
|
||||
data from spreadsheets.
|
||||
|
||||
This demo uses JE and SheetJS to pull data from a spreadsheet and print CSV
|
||||
rows. We'll explore how to load SheetJS in a JE context and process spreadsheets
|
||||
from Perl scripts.
|
||||
|
||||
The ["Complete Example"](#complete-example) section includes a complete script
|
||||
for reading data from XLS files, printing CSV rows, and writing FODS workbooks.
|
||||
|
||||
## Integration Details
|
||||
|
||||
The engine deviates from ES3. Modifying prototypes can fix some behavior:
|
||||
The [SheetJS ExtendScript build](/docs/getting-started/installation/extendscript)
|
||||
can be parsed and evaluated in a JE context.
|
||||
|
||||
```js
|
||||
The engine deviates from ES3. Modifying prototypes can fix some behavior:
|
||||
|
||||
<details>
|
||||
<summary><b>Required shim to support JE</b> (click to show)</summary>
|
||||
|
||||
The following features are implemented:
|
||||
|
||||
- simple string `charCodeAt`
|
||||
- Number `charCodeAt` (to work around string `split` bug)
|
||||
- String `match` (to work around a bug when there are no matches)
|
||||
|
||||
```js title="Required shim to support JE"
|
||||
/* String#charCodeAt is missing */
|
||||
var string = "";
|
||||
for(var i = 0; i < 256; ++i) string += String.fromCharCode(i);
|
||||
@ -45,6 +64,8 @@ String.prototype.match = function(p) {
|
||||
};
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
When loading the ExtendScript build, the BOM must be removed:
|
||||
|
||||
```perl
|
||||
@ -106,9 +127,9 @@ This demo was tested in the following deployments:
|
||||
|
||||
| Architecture | Version | Date |
|
||||
|:-------------|:--------|:-----------|
|
||||
| `darwin-x64` | `0.066` | 2024-02-13 |
|
||||
| `darwin-x64` | `0.066` | 2024-06-29 |
|
||||
| `darwin-arm` | `0.066` | 2024-05-25 |
|
||||
| `linux-x64` | `0.066` | 2024-02-13 |
|
||||
| `linux-x64` | `0.066` | 2024-06-29 |
|
||||
| `linux-arm` | `0.066` | 2024-05-25 |
|
||||
|
||||
:::
|
||||
@ -119,7 +140,23 @@ This demo was tested in the following deployments:
|
||||
cpan install JE File::Slurp
|
||||
```
|
||||
|
||||
2) Download the [ExtendScript build](/docs/getting-started/installation/extendscript):
|
||||
:::note pass
|
||||
|
||||
There were permissions errors in some test runs:
|
||||
|
||||
```
|
||||
mkdir /Library/Perl/5.30/File: Permission denied at /System/Library/Perl/5.30/ExtUtils/Install.pm line 489.
|
||||
```
|
||||
|
||||
On macOS, the commands should be run through `sudo`:
|
||||
|
||||
```bash
|
||||
sudo cpan install JE File::Slurp
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
2) Download the [SheetJS ExtendScript build](/docs/getting-started/installation/extendscript):
|
||||
|
||||
<CodeBlock language="bash">{`\
|
||||
curl -LO https://cdn.sheetjs.com/xlsx-${current}/package/dist/xlsx.extendscript.js`}
|
||||
@ -131,7 +168,7 @@ curl -LO https://cdn.sheetjs.com/xlsx-${current}/package/dist/xlsx.extendscript.
|
||||
curl -LO https://docs.sheetjs.com/perl/SheetJE.pl
|
||||
```
|
||||
|
||||
4) Download a test file and run:
|
||||
4) Download the [test file](pathname:///cd.xls) and run:
|
||||
|
||||
```bash
|
||||
curl -LO https://docs.sheetjs.com/cd.xls
|
||||
|
@ -1,7 +1,9 @@
|
||||
import { existsSync } from 'fs';
|
||||
/* NOTE: hnswlib-node@3.0.0 does not install on a fresh Windows 11 setup */
|
||||
// import { existsSync } from 'fs';
|
||||
import { ChatOllama } from "@langchain/community/chat_models/ollama";
|
||||
import { OllamaEmbeddings } from "@langchain/community/embeddings/ollama"
|
||||
import { HNSWLib } from "@langchain/community/vectorstores/hnswlib";
|
||||
// import { HNSWLib } from "@langchain/community/vectorstores/hnswlib";
|
||||
import { MemoryVectorStore } from "langchain/vectorstores/memory";
|
||||
import { SelfQueryRetriever } from "langchain/retrievers/self_query";
|
||||
import { FunctionalTranslator } from "@langchain/core/structured_query";
|
||||
|
||||
@ -9,12 +11,19 @@ import LoadOfSheet from "./loadofsheet.mjs";
|
||||
|
||||
const modelName = "llama3-chatqa:8b-v1.5-q8_0";
|
||||
|
||||
console.log(`Using model ${modelName}`);
|
||||
|
||||
const model = new ChatOllama({ baseUrl: "http://localhost:11434", model: modelName });
|
||||
const embeddings = new OllamaEmbeddings({model: modelName});
|
||||
|
||||
console.time("load of sheet");
|
||||
const loader = new LoadOfSheet("./cd.xls");
|
||||
const docs = await loader.load();
|
||||
console.timeEnd("load of sheet");
|
||||
|
||||
console.time("vector store");
|
||||
const vectorstore = await MemoryVectorStore.fromDocuments(docs, embeddings);
|
||||
/*
|
||||
const vectorstore = await (async() => {
|
||||
if(!existsSync("store/hnswlib.index")) {
|
||||
const vectorstore = await HNSWLib.fromDocuments(docs, embeddings);
|
||||
@ -23,7 +32,10 @@ const vectorstore = await (async() => {
|
||||
}
|
||||
return await HNSWLib.load("store", embeddings);
|
||||
})();
|
||||
*/
|
||||
console.timeEnd("vector store");
|
||||
|
||||
console.time("query");
|
||||
const selfQueryRetriever = SelfQueryRetriever.fromLLM({
|
||||
llm: model,
|
||||
vectorStore: vectorstore,
|
||||
@ -36,4 +48,6 @@ const selfQueryRetriever = SelfQueryRetriever.fromLLM({
|
||||
const res = await selfQueryRetriever.invoke(
|
||||
"Which rows have over 40 miles per gallon?"
|
||||
);
|
||||
console.timeEnd("query");
|
||||
|
||||
res.forEach(({metadata}) => { console.log({ Name: metadata.Name, MPG: metadata.Miles_per_Gallon }); });
|
||||
|
21
tests/bigdata-stream-nodejs.sh
Executable file
21
tests/bigdata-stream-nodejs.sh
Executable file
@ -0,0 +1,21 @@
|
||||
#!/bin/bash
|
||||
# https://docs.sheetjs.com/docs/demos/bigdata/stream#nodejs
|
||||
|
||||
cd /tmp
|
||||
rm -rf sheetjs-stream
|
||||
|
||||
mkdir sheetjs-stream
|
||||
cd sheetjs-stream
|
||||
|
||||
npm i --save https://cdn.sheetjs.com/xlsx-0.20.2/xlsx-0.20.2.tgz
|
||||
|
||||
curl -LO https://docs.sheetjs.com/stream/SheetJSNodeJStream.js
|
||||
|
||||
curl -LO https://docs.sheetjs.com/pres.xlsx
|
||||
|
||||
# this version uses `n` to cycle through node versions
|
||||
for n in 0.12 4 6 8 10 12 14 16 18 20 22; do
|
||||
sudo n $n
|
||||
node --version
|
||||
node SheetJSNodeJStream.js pres.xlsx
|
||||
done
|
80
tests/server-express-worker.sh
Executable file
80
tests/server-express-worker.sh
Executable file
@ -0,0 +1,80 @@
|
||||
#!/bin/bash
|
||||
# https://docs.sheetjs.com/docs/demos/net/server#worker-threads
|
||||
|
||||
cd /tmp
|
||||
rm -rf sheetjs-worker
|
||||
|
||||
mkdir sheetjs-worker
|
||||
cd sheetjs-worker
|
||||
echo '{ "type": "module" }' > package.json
|
||||
|
||||
npm i --save https://cdn.sheetjs.com/xlsx-0.20.2/xlsx-0.20.2.tgz express@4.18.2 formidable@2.1.2
|
||||
|
||||
cat >worker.js <<EOF
|
||||
/* load the worker_threads module */
|
||||
import { parentPort } from 'node:worker_threads';
|
||||
|
||||
/* load the SheetJS module and hook to FS */
|
||||
import { set_fs, readFile, write } from 'xlsx';
|
||||
import * as fs from 'fs';
|
||||
set_fs(fs);
|
||||
|
||||
/* the server will send a message with the \`path\` field */
|
||||
parentPort.on('message', (task) => {
|
||||
// read file
|
||||
const wb = readFile(task.path, { dense: true });
|
||||
// send back XLSX
|
||||
parentPort.postMessage(write(wb, { type: "buffer", bookType: "xlsx" }));
|
||||
// remove file
|
||||
fs.unlink(task.path, ()=>{});
|
||||
});
|
||||
EOF
|
||||
|
||||
curl -LO https://docs.sheetjs.com/server/worker_pool.js
|
||||
curl -LO https://docs.sheetjs.com/pres.numbers
|
||||
|
||||
cat >main.mjs <<EOF
|
||||
/* load dependencies */
|
||||
import os from 'node:os';
|
||||
import process from 'node:process'
|
||||
import express from 'express';
|
||||
import formidable from 'formidable';
|
||||
|
||||
/* load worker pool */
|
||||
import WorkerPool from './worker_pool.js';
|
||||
|
||||
const pool = new WorkerPool(os.cpus().length);
|
||||
process.on("beforeExit", () => { pool.close(); })
|
||||
|
||||
/* create server */
|
||||
const app = express();
|
||||
app.post('/', (req, res, next) => {
|
||||
// parse body
|
||||
const form = formidable({});
|
||||
form.parse(req, (err, fields, files) => {
|
||||
// look for "upload" field
|
||||
if(err) return next(err);
|
||||
if(!files["upload"]) return next(new Error("missing \`upload\` file"));
|
||||
|
||||
// send a message to the worker with the path to the uploaded file
|
||||
pool.runTask({ path: files["upload"].filepath }, (err, result) => {
|
||||
if(err) return next(err);
|
||||
// send the file back as an attachment
|
||||
res.attachment("SheetJSPool.xlsx");
|
||||
res.status(200).end(result);
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
// start server
|
||||
app.listen(7262, () => { console.log(\`Example app listening on port 7262\`); });
|
||||
EOF
|
||||
|
||||
# this version uses `n` to cycle through node versions
|
||||
for n in 18 20 22; do
|
||||
sudo n $n
|
||||
node --version
|
||||
npx -y concurrently -k 'node main.mjs' 'sleep 2; curl -X POST -F upload=@pres.numbers http://localhost:7262/ -J -O'
|
||||
npx -y xlsx-cli SheetJSPool.xlsx
|
||||
rm -f SheetJSPool.xlsx
|
||||
done
|
Loading…
Reference in New Issue
Block a user