Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commitf9c445a

Browse files
authored
Updated Docs (#949)
1 parentd48a4b2 commitf9c445a

File tree

3 files changed

+100
-67
lines changed

3 files changed

+100
-67
lines changed

‎pgml-sdks/rust/pgml/javascript/README.md‎

Lines changed: 66 additions & 66 deletions
Original file line numberDiff line numberDiff line change
@@ -86,9 +86,9 @@ const main = async () => {
8686
Continuing within`constmain`
8787

8888
```javascript
89-
model = pgml.newModel();
90-
splitter = pgml.newSplitter();
91-
pipeline = pgml.Pipeline("my_javascript_pipeline", model, splitter);
89+
constmodel = pgml.newModel();
90+
constsplitter = pgml.newSplitter();
91+
constpipeline = pgml.newPipeline("my_javascript_pipeline", model, splitter);
9292
await collection.add_pipeline(pipeline);
9393
```
9494

@@ -213,7 +213,7 @@ Documents are dictionaries with two required keys: `id` and `text`. All other ke
213213
214214
**Upsert documents with metadata**
215215
```javascript
216-
documents= [
216+
constdocuments= [
217217
{
218218
id:"Document 1",
219219
text:"Here are the contents of Document 1",
@@ -225,7 +225,7 @@ documents = [
225225
random_key:"this will be metadata for the document"
226226
}
227227
]
228-
collection=Collection("test_collection")
228+
constcollection=pgml.newCollection("test_collection")
229229
awaitcollection.upsert_documents(documents)
230230
```
231231
@@ -237,16 +237,16 @@ Pipelines are required to perform search. See the [Pipelines Section](#pipelines
237237
238238
**Basic vector search**
239239
```javascript
240-
collection=pgml.newCollection("test_collection")
241-
pipeline=pgml.newPipeline("test_pipeline")
242-
results=awaitcollection.query().vector_recall("Why is PostgresML the best?", pipeline).fetch_all()
240+
constcollection=pgml.newCollection("test_collection")
241+
constpipeline=pgml.newPipeline("test_pipeline")
242+
constresults=awaitcollection.query().vector_recall("Why is PostgresML the best?", pipeline).fetch_all()
243243
```
244244
245245
**Vector search with custom limit**
246246
```javascript
247-
collection=pgml.newCollection("test_collection")
248-
pipeline=pgml.newPipeline("test_pipeline")
249-
results=awaitcollection.query().vector_recall("Why is PostgresML the best?", pipeline).limit(10).fetch_all()
247+
constcollection=pgml.newCollection("test_collection")
248+
constpipeline=pgml.newPipeline("test_pipeline")
249+
constresults=awaitcollection.query().vector_recall("Why is PostgresML the best?", pipeline).limit(10).fetch_all()
250250
```
251251
252252
#### Metadata Filtering
@@ -255,15 +255,15 @@ We provide powerful and flexible arbitrarly nested metadata filtering based off
255255
256256
**Vector search with $eq metadata filtering**
257257
```javascript
258-
collection=pgml.newCollection("test_collection")
259-
pipeline=pgml.newPipeline("test_pipeline")
260-
results=awaitcollection.query()
258+
constcollection=pgml.newCollection("test_collection")
259+
constpipeline=pgml.newPipeline("test_pipeline")
260+
constresults=awaitcollection.query()
261261
.vector_recall("Here is some query", pipeline)
262262
.limit(10)
263263
.filter({
264-
"metadata": {
265-
"uuid": {
266-
"$eq":1
264+
metadata: {
265+
uuid: {
266+
$eq:1
267267
}
268268
}
269269
})
@@ -274,15 +274,15 @@ The above query would filter out all documents that do not contain a key `uuid`
274274
275275
**Vector search with $gte metadata filtering**
276276
```javascript
277-
collection=pgml.newCollection("test_collection")
278-
pipeline=pgml.newPipeline("test_pipeline")
279-
results=awaitcollection.query()
277+
constcollection=pgml.newCollection("test_collection")
278+
constpipeline=pgml.newPipeline("test_pipeline")
279+
constresults=awaitcollection.query()
280280
.vector_recall("Here is some query", pipeline)
281281
.limit(10)
282282
.filter({
283-
"metadata": {
284-
"index": {
285-
"$gte":3
283+
metadata: {
284+
index: {
285+
$gte:3
286286
}
287287
}
288288
})
@@ -294,31 +294,31 @@ The above query would filter out all documents that do not contain a key `index`
294294
295295
**Vector search with $or and $and metadata filtering**
296296
```javascript
297-
collection=pgml.newCollection("test_collection")
298-
pipeline=pgml.newPipeline("test_pipeline")
299-
results=awaitcollection.query()
297+
constcollection=pgml.newCollection("test_collection")
298+
constpipeline=pgml.newPipeline("test_pipeline")
299+
constresults=awaitcollection.query()
300300
.vector_recall("Here is some query", pipeline)
301301
.limit(10)
302302
.filter({
303-
"metadata": {
304-
"$or": [
303+
metadata: {
304+
$or: [
305305
{
306-
"$and": [
306+
$and: [
307307
{
308-
"$eq": {
309-
"uuid":1
308+
uuid: {
309+
$eq:1
310310
}
311311
},
312312
{
313-
"$lt": {
314-
"index":100
313+
index: {
314+
$lt:100
315315
}
316316
}
317317
]
318318
},
319319
{
320-
"special": {
321-
"$ne": True
320+
special: {
321+
$ne:true
322322
}
323323
}
324324
]
@@ -334,15 +334,15 @@ The above query would filter out all documents that do not have a key `special`
334334
If full text search is enabled for the associated Pipeline, documents can be first filtered by full text search and then recalled by embedding similarity.
335335
336336
```javascript
337-
collection=pgml.newCollection("test_collection")
338-
pipeline=pgml.newPipeline("test_pipeline")
339-
results=awaitcollection.query()
337+
constcollection=pgml.newCollection("test_collection")
338+
constpipeline=pgml.newPipeline("test_pipeline")
339+
constresults=awaitcollection.query()
340340
.vector_recall("Here is some query", pipeline)
341341
.limit(10)
342342
.filter({
343-
"full_text": {
344-
"configuration":"english",
345-
"text":"Match Me"
343+
full_text: {
344+
configuration:"english",
345+
text:"Match Me"
346346
}
347347
})
348348
.fetch_all()
@@ -362,20 +362,20 @@ Models are used for embedding chuncked documents. We support most every open sou
362362
363363
**Create a default Model "intfloat/e5-small" with default parameters: {}**
364364
```javascript
365-
model=pgml.newModel()
365+
constmodel=pgml.newModel()
366366
```
367367
368368
**Create a Model with custom parameters**
369369
```javascript
370-
model=pgml.newModel(
371-
name="hkunlp/instructor-base",
372-
parameters={instruction:"Represent the Wikipedia document for retrieval:"}
370+
constmodel=pgml.newModel(
371+
"hkunlp/instructor-base",
372+
{instruction:"Represent the Wikipedia document for retrieval:"}
373373
)
374374
```
375375
376376
**Use an OpenAI model**
377377
```javascript
378-
model=pgml.newModel(name="text-embedding-ada-002", source="openai")
378+
constmodel=pgml.newModel(name="text-embedding-ada-002", source="openai")
379379
```
380380
381381
### Splitters
@@ -384,14 +384,14 @@ Splitters are used to split documents into chunks before embedding them. We supp
384384
385385
**Create a default Splitter "recursive_character" with default parameters: {}**
386386
```javascript
387-
splitter=pgml.newSplitter()
387+
constsplitter=pgml.newSplitter()
388388
```
389389
390390
**Create a Splitter with custom parameters**
391391
```javascript
392-
splitter=pgml.newSplitter(
393-
name="recursive_character",
394-
parameters={chunk_size:1500, chunk_overlap:40}
392+
constsplitter=pgml.newSplitter(
393+
"recursive_character",
394+
{chunk_size:1500, chunk_overlap:40}
395395
)
396396
```
397397
@@ -402,9 +402,9 @@ When adding a Pipeline to a collection it is required that Pipeline has a Model
402402
The first time a Pipeline is added to a Collection it will automatically chunk and embed any documents already in that Collection.
403403
404404
```javascript
405-
model=pgml.newModel()
406-
splitter=pgml.newSplitter()
407-
pipeline=pgml.newPipeline("test_pipeline", model, splitter)
405+
constmodel=pgml.newModel()
406+
constsplitter=pgml.newSplitter()
407+
constpipeline=pgml.newPipeline("test_pipeline", model, splitter)
408408
awaitcollection.add_pipeline(pipeline)
409409
```
410410
@@ -415,9 +415,9 @@ Pipelines can take additional arguments enabling full text search. When full tex
415415
For more information on full text search please see: [Postgres Full Text Search](https://www.postgresql.org/docs/15/textsearch.html).
416416
417417
```javascript
418-
model=pgml.newModel()
419-
splitter=pgml.newSplitter()
420-
pipeline=pgml.newPipeline("test_pipeline", model, splitter, {
418+
constmodel=pgml.newModel()
419+
constsplitter=pgml.newSplitter()
420+
constpipeline=pgml.newPipeline("test_pipeline", model, splitter, {
421421
"full_text_search": {
422422
active: True,
423423
configuration:"english"
@@ -431,9 +431,9 @@ await collection.add_pipeline(pipeline)
431431
Pipelines are a required argument when performing vector search. After a Pipeline has been added to a Collection, the Model and Splitter can be omitted when instantiating it.
432432
433433
```javascript
434-
pipeline=pgml.newPipeline("test_pipeline")
435-
collection=pgml.newCollection("test_collection")
436-
results=awaitcollection.query().vector_recall("Why is PostgresML the best?", pipeline).fetch_all()
434+
constpipeline=pgml.newPipeline("test_pipeline")
435+
constcollection=pgml.newCollection("test_collection")
436+
constresults=awaitcollection.query().vector_recall("Why is PostgresML the best?", pipeline).fetch_all()
437437
```
438438
439439
### Enabling, Disabling, and Removing Pipelines
@@ -442,26 +442,26 @@ Pipelines can be disabled or removed to prevent them from running automatically
442442
443443
**Disable a Pipeline**
444444
```javascript
445-
pipeline=pgml.newPipeline("test_pipeline")
446-
collection=pgml.newCollection("test_collection")
445+
constpipeline=pgml.newPipeline("test_pipeline")
446+
constcollection=pgml.newCollection("test_collection")
447447
awaitcollection.disable_pipeline(pipeline)
448448
```
449449
450450
Disabling a Pipeline prevents it from running automatically, but leaves all chunks and embeddings already created by that Pipeline in the database.
451451
452452
**Enable a Pipeline**
453453
```javascript
454-
pipeline=pgml.newPipeline("test_pipeline")
455-
collection=pgml.newCollection("test_collection")
454+
constpipeline=pgml.newPipeline("test_pipeline")
455+
constcollection=pgml.newCollection("test_collection")
456456
awaitcollection.enable_pipeline(pipeline)
457457
```
458458
459459
Enabling a Pipeline will cause it to automatically run and chunk and embed all documents it may have missed while disabled.
460460
461461
**Remove a Pipeline**
462462
```javascript
463-
pipeline=pgml.newPipeline("test_pipeline")
464-
collection=pgml.newCollection("test_collection")
463+
constpipeline=pgml.newPipeline("test_pipeline")
464+
constcollection=pgml.newCollection("test_collection")
465465
awaitcollection.remove_pipeline(pipeline)
466466
```
467467
@@ -478,4 +478,4 @@ This javascript library is generated from our core rust-sdk. Please check [rust-
478478
- [x]`hybrid_search` functionality that does a combination of`vector_search` and`text_search`. [Issue](https://github.com/postgresml/postgresml/issues/665)
479479
- [x] Ability to call and manage OpenAI embeddings for comparison purposes. [Issue](https://github.com/postgresml/postgresml/issues/666)
480480
- [x] Perform chunking on the DB with multiple langchain splitters. [Issue](https://github.com/postgresml/postgresml/issues/668)
481-
- [ ] Save`vector_search` history for downstream monitoring of model performance. [Issue](https://github.com/postgresml/postgresml/issues/667)
481+
- [ ] Save`vector_search` history for downstream monitoring of model performance. [Issue](https://github.com/postgresml/postgresml/issues/667)

‎pgml-sdks/rust/pgml/javascript/examples/getting-started/package-lock.json‎

Lines changed: 33 additions & 0 deletions
Some generated files are not rendered by default. Learn more aboutcustomizing how changed files appear on GitHub.

‎pgml-sdks/rust/pgml/javascript/examples/getting-started/package.json‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,6 +10,6 @@
1010
"license":"ISC",
1111
"dependencies": {
1212
"dotenv":"^16.3.1",
13-
"pgml":"^0.1.6"
13+
"pgml":"^0.9.0"
1414
}
1515
}

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp