Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update server docs to use v2 infer endpoints #1643

Merged
merged 2 commits into from
Apr 17, 2024
Merged

Update server docs to use v2 infer endpoints #1643

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9dc5c75
Update server docs to use v2 infer endpoints
mgoin Apr 11, 2024
e6e728c
Merge branch 'main' into update-server-infer-docs
mgoin Apr 17, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/use-cases/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,7 @@ Making a request:
import requests

# Uvicorn is running on this port
url = 'http://0.0.0.0:5543/predict'
url = 'http://0.0.0.0:5543/v2/models/sentiment_analysis/infer'

# send the data
obj = {"sequences": "Sending requests to DeepSparse Server is fast and easy!"}
Expand Down
2 changes: 1 addition & 1 deletion docs/use-cases/cv/embedding-extraction.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,7 @@ deepsparse.server --config_file config.yaml
Make requests to the server:
```python
import requests, json
url = "http://0.0.0.0:5543/predict/from_files"
url = "http://0.0.0.0:5543/v2/models/embedding_extraction-0/infer/from_files"
paths = ["lion.jpeg"]
files = [("request", open(img, 'rb')) for img in paths]
resp = requests.post(url=url, files=files)
Expand Down
4 changes: 2 additions & 2 deletions docs/use-cases/cv/image-segmentation-yolact.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -188,7 +188,7 @@ Run inference:
import requests
import json

url = 'http://0.0.0.0:5543/predict/from_files'
url = 'http://0.0.0.0:5543/v2/models/yolact/infer/from_files'
path = ['thailand.jpeg'] # list of images for inference
files = [('request', open(img, 'rb')) for img in path]
resp = requests.post(url=url, files=files)
Expand Down Expand Up @@ -217,7 +217,7 @@ Run inference:
import requests
import json

url = 'http://0.0.0.0:5543/predict/from_files'
url = 'http://0.0.0.0:5543/v2/models/yolact/infer/from_files'
path = ['thailand.jpeg'] # list of images for inference
files = [('request', open(img, 'rb')) for img in path]
resp = requests.post(url=url, files=files)
Expand Down
4 changes: 2 additions & 2 deletions docs/use-cases/cv/object-detection-yolov5.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -230,7 +230,7 @@ Making a request.
import requests
import json

url = 'http://0.0.0.0:5543/predict/from_files'
url = 'http://0.0.0.0:5543/v2/models/yolo/infer/from_files'
path = ['basilica.jpg'] # list of images for inference
files = [('request', open(img, 'rb')) for img in path]
resp = requests.post(url=url, files=files)
Expand Down Expand Up @@ -271,7 +271,7 @@ Making a request:
```python
import requests, json

url = 'http://0.0.0.0:5543/predict/from_files'
url = 'http://0.0.0.0:5543/v2/models/yolo/infer/from_files'
path = ['basilica.jpg'] # list of images for inference
files = [('request', open(img, 'rb')) for img in path]
resp = requests.post(url=url, files=files)
Expand Down
2 changes: 1 addition & 1 deletion docs/use-cases/general/scheduler.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -158,7 +158,7 @@ Run inference:
import requests

# Uvicorn is running on this port
url = 'http://0.0.0.0:5543/predict'
url = 'http://0.0.0.0:5543/v2/models/sentiment_analysis/infer'

# send the data
obj = {"sequences": "Sending requests to DeepSparse Server is fast and easy!"}
Expand Down
2 changes: 1 addition & 1 deletion docs/use-cases/nlp/question-answering.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -230,7 +230,7 @@ Here is an example client request, using the Python requests library for formatt
import requests

# Uvicorn is running on this port
url = 'http://0.0.0.0:5543/predict'
url = 'http://0.0.0.0:5543/v2/models/question_answering/infer'

# send the data
obj = {
Expand Down
4 changes: 2 additions & 2 deletions docs/use-cases/nlp/sentiment-analysis.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -259,7 +259,7 @@ Here is an example client request, using the Python `requests` library for forma
import requests

# Uvicorn is running on this port
url = 'http://0.0.0.0:5543/predict'
url = 'http://0.0.0.0:5543/v2/models/sentiment_analysis/infer'

# send the data
obj = {"sequences": "Sending requests to DeepSparse Server is fast and easy!"}
Expand Down Expand Up @@ -297,7 +297,7 @@ Making a request:
import requests

# Uvicorn is running on this port
url = 'http://0.0.0.0:5543/predict'
url = 'http://0.0.0.0:5543/v2/models/sentiment_analysis/infer'

# send the data
obj = {"sequences": "Sending requests to DeepSparse Server is fast and easy!"}
Expand Down
15 changes: 8 additions & 7 deletions docs/use-cases/nlp/text-classification.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -325,7 +325,7 @@ Making a request:
import requests

# Uvicorn is running on this port
url = 'http://0.0.0.0:5543/predict'
url = 'http://0.0.0.0:5543/v2/models/text_classification/infer'

# send the data
obj = {"sequences": "Sending requests to DeepSparse Server is fast and easy!"}
Expand All @@ -351,14 +351,15 @@ Making a request:
import requests

# Uvicorn is running on this port
url = 'http://0.0.0.0:5543/predict'
url = "http://0.0.0.0:5543/v2/models/text_classification/infer"

# send the data
obj = {
"sequences": [[
"The text classification pipeline is fast and easy to use!",
"The pipeline for text classification makes it simple to get started"
]]}
"sequences": [
["The pipeline for text classification makes it simple to get started"],
["The text classification pipeline is fast and easy to use!"],
]
}
resp = requests.post(url=url, json=obj)

# recieve the post-processed output
Expand Down Expand Up @@ -391,7 +392,7 @@ Making a request:
import requests

# Uvicorn is running on this port
url = 'http://0.0.0.0:5543/predict'
url = 'http://0.0.0.0:5543/v2/models/text_classification/infer'

# send the data
obj = {"sequences": "Sending requests to DeepSparse Server is fast and easy!"}
Expand Down
4 changes: 2 additions & 2 deletions docs/use-cases/nlp/token-classification.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -228,7 +228,7 @@ Here is an example client request, using the Python requests library for formatt
import requests

# Uvicorn is running on this port
url = 'http://0.0.0.0:5543/predict'
url = 'http://0.0.0.0:5543/v2/models/token_classification/infer'
# send the data
obj = {"inputs": "Mary is flying from Nairobi to New York to attend a conference"}
resp = requests.post(url=url, json=obj)
Expand Down Expand Up @@ -261,7 +261,7 @@ Making a request:
import requests

# Uvicorn is running on this port
url = 'http://0.0.0.0:5543/predict'
url = 'http://0.0.0.0:5543/v2/models/token_classification/infer'

# send the data
obj = {"inputs": "Mary is flying from Nairobi to New York to attend a conference",}
Expand Down
4 changes: 2 additions & 2 deletions docs/use-cases/nlp/transformers-embedding-extraction.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -155,7 +155,7 @@ Here is an example client request, using the Python `requests` library for forma
import requests

# Uvicorn is running on this port
url = 'http://0.0.0.0:5543/predict'
url = 'http://0.0.0.0:5543/v2/models/transformers_embedding_extraction/infer'

# send the data
obj = {"inputs": "The transformers embedding extraction Pipeline is the best!"}
Expand Down Expand Up @@ -191,7 +191,7 @@ Making requests:
```python
import requests, json
# Uvicorn is running on this port
url = 'http://0.0.0.0:5543/predict'
url = 'http://0.0.0.0:5543/v2/models/transformers_embedding_extraction/infer'

# send the data
obj = {"inputs": "The transformers embedding extraction Pipeline is the best!"}
Expand Down
4 changes: 2 additions & 2 deletions docs/use-cases/nlp/zero-shot-text-classification.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -199,7 +199,7 @@ Making a request:
import requests

# Uvicorn is running on this port
url = 'http://0.0.0.0:5543/predict'
url = 'http://0.0.0.0:5543/v2/models/zero_shot_text_classification/infer'

# send the data
obj = {
Expand Down Expand Up @@ -238,7 +238,7 @@ Making a request:
import requests

# Uvicorn is running on this port
url = 'http://0.0.0.0:5543/predict'
url = 'http://0.0.0.0:5543/v2/models/zero_shot_text_classification/infer'

# send the data
obj = {"sequences": ["The Boston Red Sox are my favorite baseball team!"]}
Expand Down
4 changes: 2 additions & 2 deletions examples/ultralytics-yolo/ultralytics-readmes/deepsparse-readme.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -145,8 +145,8 @@ import requests, json
path = ['basilica.jpg']
files = [('request', open(img, 'rb')) for img in path]

# send request over HTTP to /predict/from_files endpoint
url = 'http://0.0.0.0:5543/predict/from_files'
# send request over HTTP to /v2/models/yolo/infer/from_files endpoint
url = 'http://0.0.0.0:5543/v2/models/yolo/infer/from_files'
resp = requests.post(url=url, files=files)

# response is returned in JSON
Expand Down
Loading