mirror of
https://github.com/neuml/txtai.git
synced 2026-10-11 21:39:55 +00:00
Update example applications for consistency. Add links to applications hosted on hf spaces. Closes #140
This commit is contained in:
davidmezzetti
@@ -134,8 +134,8 @@ Series of example applications with txtai. Links to hosted versions on [Hugging
|
||||
|
||||
| Application | Description | |
|
||||
|:-------------|:-------------|------:|
|
||||
| [Demo query shell](https://github.com/neuml/txtai/blob/master/examples/demo.py) | Basic similarity search example. Used in the original txtai demo. ||
|
||||
| [Book search](https://github.com/neuml/txtai/blob/master/examples/books.py) | Book similarity search application. Index book descriptions and query using natural language statements. ||
|
||||
| [Basic similarity search](https://github.com/neuml/txtai/blob/master/examples/similarity.py) | Basic similarity search example. Data from the original txtai demo. |[🤗](https://hf.co/spaces/NeuML/similarity)|
|
||||
| [Book search](https://github.com/neuml/txtai/blob/master/examples/books.py) | Book similarity search application. Index book descriptions and query using natural language statements. |*Local run only*|
|
||||
| [Image search](https://github.com/neuml/txtai/blob/master/examples/images.py) | Image similarity search application. Index a directory of images and run searches to identify images similar to the input query. |[🤗](https://hf.co/spaces/NeuML/imagesearch)|
|
||||
| [Wiki search](https://github.com/neuml/txtai/blob/master/examples/wiki.py) | Wikipedia search application. Queries Wikipedia API and summarizes the top result. |[🤗](https://hf.co/spaces/NeuML/wikisummary)|
|
||||
| [Workflow builder](https://github.com/neuml/txtai/blob/master/examples/workflows.py) | Build and execute txtai workflows. Connect summarization, text extraction, transcription, translation and similarity search pipelines together to run unified workflows. |[🤗](https://hf.co/spaces/NeuML/txtai)|
|
||||
|
||||
+2
-2
@@ -51,8 +51,8 @@ Series of example applications with txtai. Links to hosted versions on [Hugging
|
||||
|
||||
| Application | Description | |
|
||||
|:-------------|:-------------|------:|
|
||||
| [Demo query shell](https://github.com/neuml/txtai/blob/master/examples/demo.py) | Basic similarity search example. Used in the original txtai demo. ||
|
||||
| [Book search](https://github.com/neuml/txtai/blob/master/examples/books.py) | Book similarity search application. Index book descriptions and query using natural language statements. ||
|
||||
| [Basic similarity search](https://github.com/neuml/txtai/blob/master/examples/similarity.py) | Basic similarity search example. Data from the original txtai demo. |[🤗](https://hf.co/spaces/NeuML/similarity)|
|
||||
| [Book search](https://github.com/neuml/txtai/blob/master/examples/books.py) | Book similarity search application. Index book descriptions and query using natural language statements. |*Local run only*|
|
||||
| [Image search](https://github.com/neuml/txtai/blob/master/examples/images.py) | Image similarity search application. Index a directory of images and run searches to identify images similar to the input query. |[🤗](https://hf.co/spaces/NeuML/imagesearch)|
|
||||
| [Wiki search](https://github.com/neuml/txtai/blob/master/examples/wiki.py) | Wikipedia search application. Queries Wikipedia API and summarizes the top result. |[🤗](https://hf.co/spaces/NeuML/wikisummary)|
|
||||
| [Workflow builder](https://github.com/neuml/txtai/blob/master/examples/workflows.py) | Build and execute txtai workflows. Connect summarization, text extraction, transcription, translation and similarity search pipelines together to run unified workflows. |[🤗](https://hf.co/spaces/NeuML/txtai)|
|
||||
|
||||
@@ -1,53 +0,0 @@
|
||||
"""
|
||||
Demo shell
|
||||
"""
|
||||
|
||||
from cmd import Cmd
|
||||
|
||||
from txtai.embeddings import Embeddings
|
||||
|
||||
|
||||
class Shell(Cmd):
|
||||
"""
|
||||
Query shell.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
|
||||
self.intro = "query shell"
|
||||
self.prompt = "(search) "
|
||||
|
||||
self.embeddings = None
|
||||
self.data = None
|
||||
|
||||
def preloop(self):
|
||||
# Create embeddings model, backed by sentence-transformers & transformers
|
||||
self.embeddings = Embeddings({"path": "sentence-transformers/nli-mpnet-base-v2"})
|
||||
|
||||
self.data = [
|
||||
"US tops 5 million confirmed virus cases",
|
||||
"Canada's last fully intact ice shelf has suddenly collapsed, forming a Manhattan-sized iceberg",
|
||||
"Beijing mobilises invasion craft along coast as Taiwan tensions escalate",
|
||||
"The National Park Service warns against sacrificing slower friends in a bear attack",
|
||||
"Maine man wins $1M from $25 lottery ticket",
|
||||
"Make huge profits without work, earn up to $100,000 a day",
|
||||
]
|
||||
|
||||
def default(self, line):
|
||||
# Get index of best section that best matches query
|
||||
uid = self.embeddings.similarity(line, self.data)[0][0]
|
||||
print(self.data[uid])
|
||||
print()
|
||||
|
||||
|
||||
def main():
|
||||
"""
|
||||
Shell execution loop.
|
||||
"""
|
||||
|
||||
Shell().cmdloop()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
+72
-49
@@ -1,8 +1,8 @@
|
||||
"""
|
||||
Streamlit version of https://colab.research.google.com/github/neuml/txtai/blob/master/examples/13_Similarity_search_with_images.ipynb
|
||||
Builds a similarity index for a directory of images
|
||||
|
||||
Requires streamlit and torchvision to be installed.
|
||||
pip install streamlit torchvision
|
||||
Requires streamlit to be installed.
|
||||
pip install streamlit
|
||||
"""
|
||||
|
||||
import glob
|
||||
@@ -16,67 +16,90 @@ from PIL import Image
|
||||
from txtai.embeddings import Embeddings
|
||||
|
||||
|
||||
def images(directory):
|
||||
class Application:
|
||||
"""
|
||||
Generator that loops over each image in a directory.
|
||||
|
||||
Args:
|
||||
directory: directory with images
|
||||
Main application
|
||||
"""
|
||||
|
||||
for path in glob.glob(directory + "/*jpg") + glob.glob(directory + "/*png"):
|
||||
yield (path, Image.open(path), None)
|
||||
def __init__(self, directory):
|
||||
"""
|
||||
Creates a new application.
|
||||
|
||||
Args:
|
||||
directory: directory of images
|
||||
"""
|
||||
|
||||
self.embeddings = self.build(directory)
|
||||
|
||||
def build(self, directory):
|
||||
"""
|
||||
Builds an image embeddings index.
|
||||
|
||||
Args:
|
||||
directory: directory with images
|
||||
|
||||
Returns:
|
||||
Embeddings index
|
||||
"""
|
||||
|
||||
embeddings = Embeddings({"method": "sentence-transformers", "path": "clip-ViT-B-32"})
|
||||
embeddings.index(self.images(directory))
|
||||
|
||||
# Update model to support multilingual queries
|
||||
embeddings.config["path"] = "sentence-transformers/clip-ViT-B-32-multilingual-v1"
|
||||
embeddings.model = embeddings.loadVectors()
|
||||
|
||||
return embeddings
|
||||
|
||||
def images(self, directory):
|
||||
"""
|
||||
Generator that loops over each image in a directory.
|
||||
|
||||
Args:
|
||||
directory: directory with images
|
||||
"""
|
||||
|
||||
for path in glob.glob(directory + "/*jpg") + glob.glob(directory + "/*png"):
|
||||
yield (path, Image.open(path), None)
|
||||
|
||||
def run(self):
|
||||
"""
|
||||
Runs a Streamlit application.
|
||||
"""
|
||||
|
||||
st.title("Image search")
|
||||
|
||||
st.markdown("This application shows how images and text can be embedded into the same space to support similarity search. ")
|
||||
st.markdown(
|
||||
"[sentence-transformers](https://github.com/UKPLab/sentence-transformers/tree/master/examples/applications/image-search) "
|
||||
+ "recently added support for the [OpenAI CLIP model](https://github.com/openai/CLIP). This model embeds text and images into "
|
||||
+ "the same space, enabling image similarity search. txtai can directly utilize these models."
|
||||
)
|
||||
|
||||
query = st.text_input("Search query:")
|
||||
if query:
|
||||
index, _ = self.embeddings.search(query, 1)[0]
|
||||
st.image(Image.open(index))
|
||||
|
||||
|
||||
@st.cache(allow_output_mutation=True)
|
||||
def build(directory):
|
||||
def create(directory):
|
||||
"""
|
||||
Builds an image embeddings index.
|
||||
Creates and caches a Streamlit application.
|
||||
|
||||
Args:
|
||||
directory: directory with images
|
||||
directory: directory of images to index
|
||||
|
||||
Returns:
|
||||
Embeddings index
|
||||
Application
|
||||
"""
|
||||
|
||||
embeddings = Embeddings({"method": "sentence-transformers", "path": "clip-ViT-B-32"})
|
||||
embeddings.index(images(directory))
|
||||
|
||||
# Update model to support multilingual queries
|
||||
embeddings.config["path"] = "sentence-transformers/clip-ViT-B-32-multilingual-v1"
|
||||
embeddings.model = embeddings.loadVectors()
|
||||
|
||||
return embeddings
|
||||
|
||||
|
||||
def app(directory):
|
||||
"""
|
||||
Streamlit application that runs searches against an image embeddings index.
|
||||
|
||||
Args:
|
||||
directory: directory with images
|
||||
"""
|
||||
|
||||
# Build embeddings index
|
||||
embeddings = build(directory)
|
||||
|
||||
st.title("Image search")
|
||||
|
||||
st.markdown("This application shows how images and text can be embedded into the same space to support similarity search. ")
|
||||
st.markdown(
|
||||
"[sentence-transformers](https://github.com/UKPLab/sentence-transformers/tree/master/examples/applications/image-search) "
|
||||
+ "recently added support for the [OpenAI CLIP model](https://github.com/openai/CLIP). This model embeds text and images into "
|
||||
+ "the same space, enabling image similarity search. txtai can directly utilize these models."
|
||||
)
|
||||
|
||||
query = st.text_input("Search query:")
|
||||
if query:
|
||||
index, _ = embeddings.search(query, 1)[0]
|
||||
st.image(Image.open(index))
|
||||
return Application(directory)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
os.environ["TOKENIZERS_PARALLELISM"] = "false"
|
||||
|
||||
app(sys.argv[1])
|
||||
# Create and run application
|
||||
app = create(sys.argv[1])
|
||||
app.run()
|
||||
|
||||
@@ -0,0 +1,73 @@
|
||||
"""
|
||||
Basic similarity search example. Used in the original txtai demo.
|
||||
|
||||
Requires streamlit to be installed.
|
||||
pip install streamlit
|
||||
"""
|
||||
|
||||
import os
|
||||
|
||||
import streamlit as st
|
||||
|
||||
from txtai.embeddings import Embeddings
|
||||
|
||||
|
||||
class Application:
|
||||
"""
|
||||
Main application.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
"""
|
||||
Creates a new application.
|
||||
"""
|
||||
|
||||
# Create embeddings model, backed by sentence-transformers & transformers
|
||||
self.embeddings = Embeddings({"path": "sentence-transformers/nli-mpnet-base-v2"})
|
||||
|
||||
def run(self):
|
||||
"""
|
||||
Runs a Streamlit application.
|
||||
"""
|
||||
|
||||
st.title("Similarity Search")
|
||||
st.markdown("This application runs a basic similarity search that identifies the best matching row for a query.")
|
||||
|
||||
data = [
|
||||
"US tops 5 million confirmed virus cases",
|
||||
"Canada's last fully intact ice shelf has suddenly collapsed, forming a Manhattan-sized iceberg",
|
||||
"Beijing mobilises invasion craft along coast as Taiwan tensions escalate",
|
||||
"The National Park Service warns against sacrificing slower friends in a bear attack",
|
||||
"Maine man wins $1M from $25 lottery ticket",
|
||||
"Make huge profits without work, earn up to $100,000 a day",
|
||||
]
|
||||
|
||||
data = st.text_area("Data", value="\n".join(data))
|
||||
query = st.text_input("Query")
|
||||
|
||||
data = data.split("\n")
|
||||
|
||||
if query:
|
||||
# Get index of best section that best matches query
|
||||
uid = self.embeddings.similarity(query, data)[0][0]
|
||||
st.write(data[uid])
|
||||
|
||||
|
||||
@st.cache(allow_output_mutation=True)
|
||||
def create():
|
||||
"""
|
||||
Creates and caches a Streamlit application.
|
||||
|
||||
Returns:
|
||||
Application
|
||||
"""
|
||||
|
||||
return Application()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
os.environ["TOKENIZERS_PARALLELISM"] = "false"
|
||||
|
||||
# Create and run application
|
||||
app = create()
|
||||
app.run()
|
||||
+1
-4
@@ -1,11 +1,8 @@
|
||||
"""
|
||||
Application that queries Wikipedia API and summarizes the top result.
|
||||
|
||||
Install Streamlit
|
||||
Requires streamlit to be installed.
|
||||
pip install streamlit
|
||||
|
||||
Run application
|
||||
streamlit run wiki.py
|
||||
"""
|
||||
|
||||
import os
|
||||
|
||||
@@ -64,12 +64,12 @@ class Server(uvicorn.Server):
|
||||
|
||||
class Application:
|
||||
"""
|
||||
Streamlit application.
|
||||
Main application.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
"""
|
||||
Creates a new Streamlit application.
|
||||
Creates a new application.
|
||||
"""
|
||||
|
||||
# Component options
|
||||
|
||||
Reference in New Issue
Block a user