Skip to content

Commit c043713

Browse files
montanalowmontanalow
committed
prevent excessive wrapping
1 parent 4c1865d commit c043713

26 files changed

+59
-51
lines changed

‎pgml-cms/docs/SUMMARY.md

Lines changed: 18 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -23,16 +23,16 @@
2323
* [PGML](open-source/pgml/README.md)
2424
* [API](open-source/pgml/api/README.md)
2525
* [pgml.embed()](open-source/pgml/api/pgml.embed.md)
26-
* [pgml.transform()](open-source/pgml/api/pgml.transform/README.md)
27-
* [Fill-Mask](open-source/pgml/api/pgml.transform/fill-mask.md)
28-
* [Question answering](open-source/pgml/api/pgml.transform/question-answering.md)
29-
* [Summarization](open-source/pgml/api/pgml.transform/summarization.md)
30-
* [Text classification](open-source/pgml/api/pgml.transform/text-classification.md)
31-
* [Text Generation](open-source/pgml/api/pgml.transform/text-generation.md)
32-
* [Text-to-Text Generation](open-source/pgml/api/pgml.transform/text-to-text-generation.md)
33-
* [Token Classification](open-source/pgml/api/pgml.transform/token-classification.md)
34-
* [Translation](open-source/pgml/api/pgml.transform/translation.md)
35-
* [Zero-shot Classification](open-source/pgml/api/pgml.transform/zero-shot-classification.md)
26+
* [pgml.transform()](open-source/pgml/guides/llms/README.md)
27+
* [Fill-Mask](open-source/pgml/guides/llms/fill-mask.md)
28+
* [Question answering](open-source/pgml/guides/llms/question-answering.md)
29+
* [Summarization](open-source/pgml/guides/llms/summarization.md)
30+
* [Text classification](open-source/pgml/guides/llms/text-classification.md)
31+
* [Text Generation](open-source/pgml/guides/llms/text-generation.md)
32+
* [Text-to-Text Generation](open-source/pgml/guides/llms/text-to-text-generation.md)
33+
* [Token Classification](open-source/pgml/guides/llms/token-classification.md)
34+
* [Translation](open-source/pgml/guides/llms/translation.md)
35+
* [Zero-shot Classification](open-source/pgml/guides/llms/zero-shot-classification.md)
3636
* [pgml.transform_stream()](open-source/pgml/api/pgml.transform_stream.md)
3737
* [pgml.deploy()](open-source/pgml/api/pgml.deploy.md)
3838
* [pgml.decompose()](open-source/pgml/api/pgml.decompose.md)
@@ -41,13 +41,13 @@
4141
* [pgml.predict()](open-source/pgml/api/pgml.predict/README.md)
4242
* [Batch Predictions](open-source/pgml/api/pgml.predict/batch-predictions.md)
4343
* [pgml.train()](open-source/pgml/api/pgml.train/README.md)
44-
* [Regression](open-source/pgml/api/pgml.train/regression.md)
45-
* [Classification](open-source/pgml/api/pgml.train/classification.md)
46-
* [Clustering](open-source/pgml/api/pgml.train/clustering.md)
47-
* [Decomposition](open-source/pgml/api/pgml.train/decomposition.md)
48-
* [Data Pre-processing](open-source/pgml/api/pgml.train/data-pre-processing.md)
49-
* [Hyperparameter Search](open-source/pgml/api/pgml.train/hyperparameter-search.md)
50-
* [Joint Optimization](open-source/pgml/api/pgml.train/joint-optimization.md)
44+
* [Regression](open-source/pgml/guides/supervised-learning/regression.md)
45+
* [Classification](open-source/pgml/guides/supervised-learning/classification.md)
46+
* [Clustering](open-source/pgml/guides/supervised-learning/clustering.md)
47+
* [Decomposition](open-source/pgml/guides/supervised-learning/decomposition.md)
48+
* [Data Pre-processing](open-source/pgml/guides/supervised-learning/data-pre-processing.md)
49+
* [Hyperparameter Search](open-source/pgml/guides/supervised-learning/hyperparameter-search.md)
50+
* [Joint Optimization](open-source/pgml/guides/supervised-learning/joint-optimization.md)
5151
* [pgml.tune()](open-source/pgml/api/pgml.tune.md)
5252
* [Guides](open-source/pgml/guides/README.md)
5353
* [Embeddings](open-source/pgml/guides/embeddings/README.md)
@@ -58,7 +58,7 @@
5858
* [Normalization](open-source/pgml/guides/embeddings/vector-normalization.md)
5959
* [Search](open-source/pgml/guides/improve-search-results-with-machine-learning.md)
6060
* [Chatbots](open-source/pgml/guides/chatbots/README.md)
61-
* [Supervised Learning](open-source/pgml/guides/supervised-learning.md)
61+
* [Supervised Learning](open-source/pgml/guides/supervised-learning/supervised-learning.md)
6262
* [Unified RAG](open-source/pgml/guides/unified-rag.md)
6363
* [Natural Language Processing](open-source/pgml/guides/natural-language-processing.md)
6464
* [Vector database](open-source/pgml/guides/vector-database.md)

‎pgml-cms/docs/open-source/pgml/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -18,7 +18,7 @@ See the [API](api/) for a full list of all functions provided by `pgml`.
1818
Common tasks include:
1919
- [Splitting text - pgml.chunk()](api/pgml.chunk)
2020
- [Generating embeddings - pgml.embed()](api/pgml.embed)
21-
- [Generating text - pgml.transform()](api/pgml.transform/text-generation)
21+
- [Generating text - pgml.transform()](guides/llms/text-generation.md)
2222
- [Streaming generated text - pgml.transform_stream()](api/pgml.transform_stream)
2323

2424
## Open-source LLMs

‎pgml-cms/docs/open-source/pgml/api/pgml.train/README.md renamed to ‎pgml-cms/docs/open-source/pgml/api/pgml.train.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -39,12 +39,12 @@ pgml.train(
3939
| `y_column_name` | `'clicked'` | The name of the label (aka "target" or "unknown") column in the training table. |
4040
| `algorithm` | `'xgboost'` | <p>The algorithm to train on the dataset, see the task specific pages for available algorithms:<br><a data-mention href="regression.md">regression.md</a></p><p><a data-mention href="classification.md">classification.md</a><br><a data-mention href="clustering.md">clustering.md</a></p> |
4141
| `hyperparams` | `{ "n_estimators": 25 }` | The hyperparameters to pass to the algorithm for training, JSON formatted. |
42-
| `search` | `grid` | If set, PostgresML will perform a hyperparameter search to find the best hyperparameters for the algorithm. See [hyperparameter-search.md](hyperparameter-search.md "mention") for details. |
42+
| `search` | `grid` | If set, PostgresML will perform a hyperparameter search to find the best hyperparameters for the algorithm. See [hyperparameter-search.md](../guides/supervised-learning/hyperparameter-search.md "mention") for details. |
4343
| `search_params` | `{ "n_estimators": [5, 10, 25, 100] }` | Search parameters used in the hyperparameter search, using the scikit-learn notation, JSON formatted. |
4444
| `search_args` | `{ "n_iter": 10 }` | Configuration parameters for the search, JSON formatted. Currently only `n_iter` is supported for `random` search. |
4545
| `test_size` | `0.25` | Fraction of the dataset to use for the test set and algorithm validation. |
4646
| `test_sampling` | `random` | Algorithm used to fetch test data from the dataset: `random`, `first`, or `last`. |
47-
| `preprocess` | `{"col_name": {"impute": "mean", scale: "standard"}}` | Preprocessing steps to impute NULLS, encode categoricals and scale inputs. See [data-pre-processing.md](data-pre-processing.md "mention") for details. |
47+
| `preprocess` | `{"col_name": {"impute": "mean", scale: "standard"}}` | Preprocessing steps to impute NULLS, encode categoricals and scale inputs. See [data-pre-processing.md](../guides/supervised-learning/data-pre-processing.md "mention") for details. |
4848

4949
!!! example
5050

‎pgml-cms/docs/open-source/pgml/api/pgml.transform/README.md renamed to ‎pgml-cms/docs/open-source/pgml/api/pgml.transform.md

Lines changed: 2 additions & 26 deletions
Original file line numberDiff line numberDiff line change
@@ -160,30 +160,6 @@ transform(
160160
{% endtab %}
161161
{% endtabs %}
162162

163+
## Guides
163164

164-
### Supported tasks
165-
166-
PostgresML currently supports most NLP tasks available on Hugging Face:
167-
168-
| Task | Name | Description |
169-
|------|-------------|---------|
170-
| [Fill mask](fill-mask) | `key-mask` | Fill in the blank in a sentence. |
171-
| [Question answering](question-answering) | `question-answering` | Answer a question based on a context. |
172-
| [Summarization](summarization) | `summarization` | Summarize a long text. |
173-
| [Text classification](text-classification) | `text-classification` | Classify a text as positive or negative. |
174-
| [Text generation](text-generation) | `text-generation` | Generate text based on a prompt. |
175-
| [Text-to-text generation](text-to-text-generation) | `text-to-text-generation` | Generate text based on an instruction in the prompt. |
176-
| [Token classification](token-classification) | `token-classification` | Classify tokens in a text. |
177-
| [Translation](translation) | `translation` | Translate text from one language to another. |
178-
| [Zero-shot classification](zero-shot-classification) | `zero-shot-classification` | Classify a text without training data. |
179-
| Conversational | `conversational` | Engage in a conversation with the model, e.g. chatbot. |
180-
181-
### Structured inputs
182-
183-
Both versions of the `pgml.transform()` function also support structured inputs, formatted with JSON. Structured inputs are used with the conversational task, e.g. to differentiate between the system and user prompts. Simply replace the text array argument with an array of JSONB objects.
184-
185-
186-
## Additional resources
187-
188-
- [Hugging Face datasets](https://huggingface.co/datasets)
189-
- [Hugging Face tasks](https://huggingface.co/tasks)
165+
See also: [LLM guides](../guides/llms/) for more examples

‎pgml-cms/docs/open-source/pgml/guides/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@
88
* [Normalization](embeddings/vector-normalization.md)
99
* [Search](improve-search-results-with-machine-learning.md)
1010
* [Chatbots](chatbots/)
11-
* [Supervised Learning](supervised-learning.md)
11+
* [Supervised Learning](supervised-learning/supervised-learning.md)
1212
* [Unified RAG](unified-rag.md)
1313
* [Natural Language Processing](natural-language-processing.md)
1414
* [Vector Database](vector-database.md)

‎pgml-cms/docs/open-source/pgml/guides/llms/README.md

Lines changed: 28 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,28 @@
1+
# LLMs
2+
3+
## Supported tasks
4+
5+
PostgresML currently supports most LLM tasks for Natural Language Processing available on Hugging Face:
6+
7+
| Task | Name | Description |
8+
|---------------------------------------------------------|-------------|---------|
9+
| [Fill mask](../guides/llms/fill-mask.md) | `key-mask` | Fill in the blank in a sentence. |
10+
| [Question answering](../guides/llms/question-answering.md) | `question-answering` | Answer a question based on a context. |
11+
| [Summarization](../guides/llms/summarization.md) | `summarization` | Summarize a long text. |
12+
| [Text classification](../guides/llms/text-classification.md) | `text-classification` | Classify a text as positive or negative. |
13+
| [Text generation](../guides/llms/text-generation.md) | `text-generation` | Generate text based on a prompt. |
14+
| [Text-to-text generation](../guides/llms/text-to-text-generation.md) | `text-to-text-generation` | Generate text based on an instruction in the prompt. |
15+
| [Token classification](../guides/llms/token-classification.md) | `token-classification` | Classify tokens in a text. |
16+
| [Translation](../guides/llms/translation.md) | `translation` | Translate text from one language to another. |
17+
| [Zero-shot classification](../guides/llms/zero-shot-classification.md) | `zero-shot-classification` | Classify a text without training data. |
18+
| Conversational | `conversational` | Engage in a conversation with the model, e.g. chatbot. |
19+
20+
## Structured inputs
21+
22+
Both versions of the `pgml.transform()` function also support structured inputs, formatted with JSON. Structured inputs are used with the conversational task, e.g. to differentiate between the system and user prompts. Simply replace the text array argument with an array of JSONB objects.
23+
24+
25+
## Additional resources
26+
27+
- [Hugging Face datasets](https://huggingface.co/datasets)
28+
- [Hugging Face tasks](https://huggingface.co/tasks)

‎pgml-cms/docs/open-source/pgml/api/pgml.transform/fill-mask.md renamed to ‎pgml-cms/docs/open-source/pgml/guides/llms/fill-mask.md

File renamed without changes.

‎pgml-cms/docs/open-source/pgml/api/pgml.transform/question-answering.md renamed to ‎pgml-cms/docs/open-source/pgml/guides/llms/question-answering.md

File renamed without changes.

‎pgml-cms/docs/open-source/pgml/api/pgml.transform/summarization.md renamed to ‎pgml-cms/docs/open-source/pgml/guides/llms/summarization.md

File renamed without changes.

‎pgml-cms/docs/open-source/pgml/api/pgml.transform/text-classification.md renamed to ‎pgml-cms/docs/open-source/pgml/guides/llms/text-classification.md

File renamed without changes.

0 commit comments

Comments
 (0)
pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy