neuml/txtai
1
0
Fork 0
mirror of https://github.com/neuml/txtai.git synced 2026-10-11 21:39:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update documentation for 6.0, closes #513

Browse Source
This commit is contained in:
davidmezzetti
2023-08-06 13:51:56 -04:00
parent 20d8df17b0
commit a8f8ae6e82
12 changed files with 3597 additions and 150 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+87 -116
View File
@@ -2,9 +2,9 @@
<img src="https://raw.githubusercontent.com/neuml/txtai/master/logo.png"/>
</p>
<h3 align="center">
<p>Semantic search and workflows powered by language models</p>
</h3>
<p align="center">
<b>All-in-one embeddings database</b>
</p>
<p align="center">
<a href="https://github.com/neuml/txtai/releases">
@@ -29,27 +29,18 @@
-------------------------------------------------------------------------------------------------------------------------------------------------------
txtai is an open-source platform for semantic search and workflows powered by language models.
txtai is an all-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows.
![demo](https://raw.githubusercontent.com/neuml/txtai/master/demo.gif)
![architecture](https://raw.githubusercontent.com/neuml/txtai/master/docs/images/architecture.png#gh-light-mode-only)
![architecture](https://raw.githubusercontent.com/neuml/txtai/master/docs/images/architecture-dark.png#gh-dark-mode-only)
Traditional search systems use keywords to find data. Semantic search has an understanding of natural language and identifies results that have the same meaning, not necessarily the same keywords.
Embeddings databases are a union of vector indexes (sparse and dense), graph networks and relational databases. This enables vector search with SQL, topic modeling, retrieval augmented generation and more.
![search](https://raw.githubusercontent.com/neuml/txtai/master/docs/images/search.png#gh-light-mode-only)
![search](https://raw.githubusercontent.com/neuml/txtai/master/docs/images/search-dark.png#gh-dark-mode-only)
txtai builds embeddings databases, which are a union of vector indexes and relational databases. This enables vector search with SQL. Embeddings databases can stand on their own and/or serve as a powerful knowledge source for large language model (LLM) prompts.
Semantic workflows connect language models together to build intelligent applications.
![flows](https://raw.githubusercontent.com/neuml/txtai/master/docs/images/flows.png#gh-light-mode-only)
![flows](https://raw.githubusercontent.com/neuml/txtai/master/docs/images/flows-dark.png#gh-dark-mode-only)
Integrate conversational search, retrieval augmented generation (RAG), LLM chains, automatic summarization, transcription, translation and more.
Embeddings databases can stand on their own and/or serve as a powerful knowledge source for large language model (LLM) prompts.
Summary of txtai features:
- 🔎 Vector search with SQL, object storage, topic modeling, graph analysis, multiple vector index backends ([Faiss](https://github.com/facebookresearch/faiss), [Annoy](https://github.com/spotify/annoy), [Hnswlib](https://github.com/nmslib/hnswlib)) and support for external vector databases
- 🔎 Vector search with SQL, object storage, topic modeling, graph analysis and multiple vector index backends (sparse, dense, hybrid, external)
- 📄 Create embeddings for text, documents, audio, images and video
- 💡 Pipelines powered by language models that run LLM prompts, question-answering, labeling, transcription, translation, summarizations and more
- ↪️️ Workflows to join pipelines together and aggregate business logic. txtai processes can be simple microservices or multi-model workflows.
@@ -58,19 +49,6 @@ Summary of txtai features:
txtai is built with Python 3.8+, [Hugging Face Transformers](https://github.com/huggingface/transformers), [Sentence Transformers](https://github.com/UKPLab/sentence-transformers) and [FastAPI](https://github.com/tiangolo/fastapi)
The following applications are powered by txtai.
![apps](https://raw.githubusercontent.com/neuml/txtai/master/apps.jpg)
| Application | Description |
|:----------|:-------------|
| [txtchat](https://github.com/neuml/txtchat) | Conversational search and workflows for all |
| [paperai](https://github.com/neuml/paperai) | Semantic search and workflows for medical/scientific papers |
| [codequestion](https://github.com/neuml/codequestion) | Semantic search for developers |
| [tldrstory](https://github.com/neuml/tldrstory) | Semantic search for headlines and story text |
In addition to this list, there are also many other [open-source projects](https://github.com/neuml/txtai/network/dependents), [published research](https://scholar.google.com/scholar?q=txtai&hl=en&as_ylo=2022) and closed proprietary/commercial projects that have built on txtai in production.
## Why txtai?
![why](https://raw.githubusercontent.com/neuml/txtai/master/docs/images/why.png#gh-light-mode-only)
@@ -81,9 +59,9 @@ New vector databases, LLM frameworks and everything in between are sprouting up
- Up and running in minutes with [pip](https://neuml.github.io/txtai/install/) or [Docker](https://neuml.github.io/txtai/cloud/)
```python
# Get started in a couple lines
from txtai.embeddings import Embeddings
import txtai
embeddings = Embeddings()
embeddings = txtai.Embeddings()
embeddings.index(["Correct", "Not what we hoped"])
embeddings.search("positive", 1)
#[(0, 0.29862046241760254)]
@@ -101,7 +79,64 @@ curl -X GET "http://localhost:8000/search?query=positive"
- Run local - no need to ship data off to disparate remote services
- Work with micromodels all the way up to large language models (LLMs)
- Low footprint - install additional dependencies and scale up when needed
- [Learn by example](#examples) - notebooks cover all available functionality
- [Learn by example](https://neuml.github.io/txtai/examples) - notebooks cover all available functionality
## Use Cases
The following sections give an overview of the main txtai use cases. A comprehensive set of over 50 [example notebooks and applications](https://neuml.github.io/txtai/examples) are also available.
### Semantic Search
Build semantic/similarity/vector/neural search applications.
![demo](https://raw.githubusercontent.com/neuml/txtai/master/demo.gif)
Traditional search systems use keywords to find data. Semantic search has an understanding of natural language and identifies results that have the same meaning, not necessarily the same keywords.
![search](https://raw.githubusercontent.com/neuml/txtai/master/docs/images/search.png#gh-light-mode-only)
![search](https://raw.githubusercontent.com/neuml/txtai/master/docs/images/search-dark.png#gh-dark-mode-only)
Get started with the following examples.
| Notebook | Description | |
|:----------|:-------------|------:|
| [Introducing txtai](https://github.com/neuml/txtai/blob/master/examples/01_Introducing_txtai.ipynb) [▶️](https://www.youtube.com/watch?v=SIezMnVdmMs) | Overview of the functionality provided by txtai | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/01_Introducing_txtai.ipynb) |
| [Build an Embeddings index with Hugging Face Datasets](https://github.com/neuml/txtai/blob/master/examples/02_Build_an_Embeddings_index_with_Hugging_Face_Datasets.ipynb) | Index and search Hugging Face Datasets | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/02_Build_an_Embeddings_index_with_Hugging_Face_Datasets.ipynb) |
| [Add semantic search to Elasticsearch](https://github.com/neuml/txtai/blob/master/examples/04_Add_semantic_search_to_Elasticsearch.ipynb) | Add semantic search to existing search systems | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/04_Add_semantic_search_to_Elasticsearch.ipynb) |
| [Semantic Graphs](https://github.com/neuml/txtai/blob/master/examples/38_Introducing_the_Semantic_Graph.ipynb) | Explore topics, data connectivity and run network analysis| [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/38_Introducing_the_Semantic_Graph.ipynb) |
| [Embeddings in the Cloud](https://github.com/neuml/txtai/blob/master/examples/43_Embeddings_in_the_Cloud.ipynb) | Load and use an embeddings index from the Hugging Face Hub | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/43_Embeddings_in_the_Cloud.ipynb) |
| [Customize your own embeddings database](https://github.com/neuml/txtai/blob/master/examples/45_Customize_your_own_embeddings_database.ipynb) | Ways to combine vector indexes with relational databases | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/45_Customize_your_own_embeddings_database.ipynb) |
### LLM Orchestration
Prompt-driven search, retrieval augmented generation (RAG), pipelines and workflows that interface with large language models (LLMs).
![llm](https://raw.githubusercontent.com/neuml/txtai/master/docs/images/llm.png)
Integrate conversational search, LLM chains and self-critique.
| Notebook | Description | |
|:----------|:-------------|------:|
| [Prompt-driven search with LLMs](https://github.com/neuml/txtai/blob/master/examples/42_Prompt_driven_search_with_LLMs.ipynb) | Embeddings-guided and Prompt-driven search with Large Language Models (LLMs) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/42_Prompt_driven_search_with_LLMs.ipynb) |
| [Prompt templates and task chains](https://github.com/neuml/txtai/blob/master/examples/44_Prompt_templates_and_task_chains.ipynb) | Build model prompts and connect tasks together with workflows | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/44_Prompt_templates_and_task_chains.ipynb) |
### Language Model Workflows
Language model workflows, also known as semantic workflows, connect language models together to build intelligent applications.
![flows](https://raw.githubusercontent.com/neuml/txtai/master/docs/images/flows.png#gh-light-mode-only)
![flows](https://raw.githubusercontent.com/neuml/txtai/master/docs/images/flows-dark.png#gh-dark-mode-only)
While LLMs are powerful, there are plenty of smaller, more specialized models that work better and faster for specific tasks. This includes models for extractive question-answering, automatic summarization, text-to-speech, transcription and translation.
| Notebook | Description | |
|:----------|:-------------|------:|
| [Run pipeline workflows](https://github.com/neuml/txtai/blob/master/examples/14_Run_pipeline_workflows.ipynb) [▶️](https://www.youtube.com/watch?v=UBMPDCn1gEU) | Simple yet powerful constructs to efficiently process data | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/14_Run_pipeline_workflows.ipynb) |
| [Extractive QA with txtai](https://github.com/neuml/txtai/blob/master/examples/05_Extractive_QA_with_txtai.ipynb) | Introduction to extractive question-answering with txtai | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/05_Extractive_QA_with_txtai.ipynb) |
| [Building abstractive text summaries](https://github.com/neuml/txtai/blob/master/examples/09_Building_abstractive_text_summaries.ipynb) | Run abstractive text summarization | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/09_Building_abstractive_text_summaries.ipynb) |
| [Text to speech generation](https://github.com/neuml/txtai/blob/master/examples/40_Text_to_Speech_Generation.ipynb) | Generate speech from text | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/40_Text_to_Speech_Generation.ipynb) |
| [Transcribe audio to text](https://github.com/neuml/txtai/blob/master/examples/11_Transcribe_audio_to_text.ipynb) | Convert audio files to text | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/11_Transcribe_audio_to_text.ipynb) |
| [Translate text between languages](https://github.com/neuml/txtai/blob/master/examples/12_Translate_text_between_languages.ipynb) | Streamline machine translation and language detection | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/12_Translate_text_between_languages.ipynb) |
## Installation
@@ -116,86 +151,7 @@ pip install txtai
Python 3.8+ is supported. Using a Python [virtual environment](https://docs.python.org/3/library/venv.html) is recommended.
See the detailed [install instructions](https://neuml.github.io/txtai/install) for more information covering
[optional dependencies](https://neuml.github.io/txtai/install/#optional-dependencies), [environment specific prerequisites](https://neuml.github.io/txtai/install/#environment-specific-prerequisites), [installing from source](https://neuml.github.io/txtai/install/#install-from-source), [conda support](https://neuml.github.io/txtai/install/#conda) and how to [run with containers](https://neuml.github.io/txtai/cloud).
## Examples
![examples](https://raw.githubusercontent.com/neuml/txtai/master/docs/images/examples.png#gh-light-mode-only)
![examples](https://raw.githubusercontent.com/neuml/txtai/master/docs/images/examples-dark.png#gh-dark-mode-only)
An abbreviated list of example notebooks and applications giving an overview of txtai are shown below. See the [documentation for the full set of examples](https://neuml.github.io/txtai/examples).
### Semantic Search
Build semantic/similarity/vector/neural search applications.
| Notebook | Description | |
|:----------|:-------------|------:|
| [Introducing txtai](https://github.com/neuml/txtai/blob/master/examples/01_Introducing_txtai.ipynb) [▶️](https://www.youtube.com/watch?v=SIezMnVdmMs) | Overview of the functionality provided by txtai | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/01_Introducing_txtai.ipynb) |
| [Build an Embeddings index with Hugging Face Datasets](https://github.com/neuml/txtai/blob/master/examples/02_Build_an_Embeddings_index_with_Hugging_Face_Datasets.ipynb) | Index and search Hugging Face Datasets | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/02_Build_an_Embeddings_index_with_Hugging_Face_Datasets.ipynb) |
| [Add semantic search to Elasticsearch](https://github.com/neuml/txtai/blob/master/examples/04_Add_semantic_search_to_Elasticsearch.ipynb) | Add semantic search to existing search systems | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/04_Add_semantic_search_to_Elasticsearch.ipynb) |
| [Semantic Graphs](https://github.com/neuml/txtai/blob/master/examples/38_Introducing_the_Semantic_Graph.ipynb) | Explore topics, data connectivity and run network analysis| [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/38_Introducing_the_Semantic_Graph.ipynb) |
| [Embeddings in the Cloud](https://github.com/neuml/txtai/blob/master/examples/43_Embeddings_in_the_Cloud.ipynb) | Load and use an embeddings index from the Hugging Face Hub | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/43_Embeddings_in_the_Cloud.ipynb) |
| [Customize your own embeddings database](https://github.com/neuml/txtai/blob/master/examples/45_Customize_your_own_embeddings_database.ipynb) | Ways to combine vector indexes with relational databases | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/45_Customize_your_own_embeddings_database.ipynb) |
### LLM
Prompt-driven search, retrieval augmented generation (RAG), pipelines and workflows that interface with large language models (LLMs).
| Notebook | Description | |
|:----------|:-------------|------:|
| [Prompt-driven search with LLMs](https://github.com/neuml/txtai/blob/master/examples/42_Prompt_driven_search_with_LLMs.ipynb) | Embeddings-guided and Prompt-driven search with Large Language Models (LLMs) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/42_Prompt_driven_search_with_LLMs.ipynb) |
| [Prompt templates and task chains](https://github.com/neuml/txtai/blob/master/examples/44_Prompt_templates_and_task_chains.ipynb) | Build model prompts and connect tasks together with workflows | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/44_Prompt_templates_and_task_chains.ipynb) |
### Pipelines
Transform data with language model backed pipelines.
| Notebook | Description | |
|:----------|:-------------|------:|
| [Extractive QA with txtai](https://github.com/neuml/txtai/blob/master/examples/05_Extractive_QA_with_txtai.ipynb) | Introduction to extractive question-answering with txtai | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/05_Extractive_QA_with_txtai.ipynb) |
| [Apply labels with zero shot classification](https://github.com/neuml/txtai/blob/master/examples/07_Apply_labels_with_zero_shot_classification.ipynb) | Use zero shot learning for labeling, classification and topic modeling | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/07_Apply_labels_with_zero_shot_classification.ipynb) |
| [Building abstractive text summaries](https://github.com/neuml/txtai/blob/master/examples/09_Building_abstractive_text_summaries.ipynb) | Run abstractive text summarization | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/09_Building_abstractive_text_summaries.ipynb) |
| [Extract text from documents](https://github.com/neuml/txtai/blob/master/examples/10_Extract_text_from_documents.ipynb) | Extract text from PDF, Office, HTML and more | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/10_Extract_text_from_documents.ipynb) |
| [Text to speech generation](https://github.com/neuml/txtai/blob/master/examples/40_Text_to_Speech_Generation.ipynb) | Generate speech from text | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/40_Text_to_Speech_Generation.ipynb) |
| [Transcribe audio to text](https://github.com/neuml/txtai/blob/master/examples/11_Transcribe_audio_to_text.ipynb) | Convert audio files to text | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/11_Transcribe_audio_to_text.ipynb) |
| [Translate text between languages](https://github.com/neuml/txtai/blob/master/examples/12_Translate_text_between_languages.ipynb) | Streamline machine translation and language detection | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/12_Translate_text_between_languages.ipynb) |
| [Generate image captions and detect objects](https://github.com/neuml/txtai/blob/master/examples/25_Generate_image_captions_and_detect_objects.ipynb) | Captions and object detection for images | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/25_Generate_image_captions_and_detect_objects.ipynb) |
### Workflows
Efficiently process data at scale.
| Notebook | Description | |
|:----------|:-------------|------:|
| [Run pipeline workflows](https://github.com/neuml/txtai/blob/master/examples/14_Run_pipeline_workflows.ipynb) [▶️](https://www.youtube.com/watch?v=UBMPDCn1gEU) | Simple yet powerful constructs to efficiently process data | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/14_Run_pipeline_workflows.ipynb) |
| [Workflow Scheduling](https://github.com/neuml/txtai/blob/master/examples/27_Workflow_scheduling.ipynb) | Schedule workflows with cron expressions | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/27_Workflow_scheduling.ipynb) |
| [Push notifications with workflows](https://github.com/neuml/txtai/blob/master/examples/28_Push_notifications_with_workflows.ipynb) | Generate and push notifications with workflows | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/28_Push_notifications_with_workflows.ipynb) |
### Model Training
Train NLP models.
| Notebook | Description | |
|:----------|:-------------|------:|
| [Train a text labeler](https://github.com/neuml/txtai/blob/master/examples/16_Train_a_text_labeler.ipynb) | Build text sequence classification models | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/16_Train_a_text_labeler.ipynb) |
| [Train a QA model](https://github.com/neuml/txtai/blob/master/examples/19_Train_a_QA_model.ipynb) | Build and fine-tune question-answering models | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/19_Train_a_QA_model.ipynb) |
| [Train a language model from scratch](https://github.com/neuml/txtai/blob/master/examples/41_Train_a_language_model_from_scratch.ipynb) | Build new language models | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/41_Train_a_language_model_from_scratch.ipynb) |
### Applications
Series of example applications with txtai. Links to hosted versions on [Hugging Face Spaces](https://hf.co/spaces) also provided.
| Application | Description | |
|:-------------|:-------------|------:|
| [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)|
| [Baseball stats](https://github.com/neuml/txtai/blob/master/examples/baseball.py) | Match historical baseball player stats using vector search. |[🤗](https://hf.co/spaces/NeuML/baseball)|
| [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)|
| [Summarize an article](https://github.com/neuml/txtai/blob/master/examples/article.py) | Summarize an article. Workflow that extracts text from a webpage and builds a summary. |[🤗](https://hf.co/spaces/NeuML/articlesummary)|
| [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)|
See the detailed [install instructions](https://neuml.github.io/txtai/install) for more information covering [optional dependencies](https://neuml.github.io/txtai/install/#optional-dependencies), [environment specific prerequisites](https://neuml.github.io/txtai/install/#environment-specific-prerequisites), [installing from source](https://neuml.github.io/txtai/install/#install-from-source), [conda support](https://neuml.github.io/txtai/install/#conda) and how to [run with containers](https://neuml.github.io/txtai/cloud).
## Model guide
@@ -226,9 +182,20 @@ See the following links to learn more.
- [MTSB Leaderboard](https://hf.co/spaces/mteb/leaderboard)
- [Open LLM Leaderboard](https://hf.co/spaces/HuggingFaceH4/open_llm_leaderboard)
## Documentation
## Powered by txtai
[Full documentation on txtai](https://neuml.github.io/txtai) including configuration settings for embeddings, pipelines, workflows, API and a FAQ with common questions/issues is available.
The following applications are powered by txtai.
![apps](https://raw.githubusercontent.com/neuml/txtai/master/apps.jpg)
| Application | Description |
|:----------|:-------------|
| [txtchat](https://github.com/neuml/txtchat) | Conversational search and workflows for all |
| [paperai](https://github.com/neuml/paperai) | Semantic search and workflows for medical/scientific papers |
| [codequestion](https://github.com/neuml/codequestion) | Semantic search for developers |
| [tldrstory](https://github.com/neuml/tldrstory) | Semantic search for headlines and story text |
In addition to this list, there are also many other [open-source projects](https://github.com/neuml/txtai/network/dependents), [published research](https://scholar.google.com/scholar?q=txtai&hl=en&as_ylo=2022) and closed proprietary/commercial projects that have built on txtai in production.
## Further Reading
@@ -245,6 +212,10 @@ See the following links to learn more.
- [Insights from the txtai console](https://medium.com/neuml/insights-from-the-txtai-console-d307c28e149e)
- [The big and small of txtai](https://medium.com/neuml/the-big-and-small-of-txtai-4ca405c1b82)
## Documentation
[Full documentation on txtai](https://neuml.github.io/txtai) including configuration settings for embeddings, pipelines, workflows, API and a FAQ with common questions/issues is available.
## Contributing
For those who would like to contribute to txtai, please see [this guide](https://github.com/neuml/.github/blob/master/CONTRIBUTING.md).
docs/images/architecture-dark.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 420 KiB

docs/images/architecture.excalidraw
+2076
View File
File diff suppressed because it is too large Load Diff
docs/images/architecture.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 422 KiB

docs/images/llm.excalidraw
+1350
View File
File diff suppressed because it is too large Load Diff
docs/images/llm.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 230 KiB

docs/index.md
+9 -31
View File
@@ -4,9 +4,9 @@
<img src="https://raw.githubusercontent.com/neuml/txtai/master/logo.png"/>
</p>
<h3 align="center">
<p>Semantic search and workflows powered by language models</p>
</h3>
<p align="center">
<b>All-in-one embeddings database</b>
</p>
<p align="center">
<a href="https://github.com/neuml/txtai/releases">
@@ -31,27 +31,18 @@
-------------------------------------------------------------------------------------------------------------------------------------------------------
txtai is an open-source platform for semantic search and workflows powered by language models.
txtai is an all-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows.
![demo](https://raw.githubusercontent.com/neuml/txtai/master/demo.gif)
![architecture](images/architecture.png#gh-light-mode-only)
![architecture](images/architecture-dark.png#gh-dark-mode-only)
Traditional search systems use keywords to find data. Semantic search has an understanding of natural language and identifies results that have the same meaning, not necessarily the same keywords.
Embeddings databases are a union of vector indexes (sparse and dense), graph networks and relational databases. This enables vector search with SQL, topic modeling, retrieval augmented generation and more.
![search](images/search.png#only-light)
![search](images/search-dark.png#only-dark)
txtai builds embeddings databases, which are a union of vector indexes and relational databases. This enables vector search with SQL. Embeddings databases can stand on their own and/or serve as a powerful knowledge source for large language model (LLM) prompts.
Semantic workflows connect language models together to build intelligent applications.
![flows](images/flows.png#only-light)
![flows](images/flows-dark.png#only-dark)
Integrate conversational search, retrieval augmented generation (RAG), LLM chains, automatic summarization, transcription, translation and more.
Embeddings databases can stand on their own and/or serve as a powerful knowledge source for large language model (LLM) prompts.
Summary of txtai features:
- 🔎 Vector search with SQL, object storage, topic modeling, graph analysis, multiple vector index backends ([Faiss](https://github.com/facebookresearch/faiss), [Annoy](https://github.com/spotify/annoy), [Hnswlib](https://github.com/nmslib/hnswlib)) and support for external vector databases
- 🔎 Vector search with SQL, object storage, topic modeling, graph analysis and multiple vector index backends (sparse, dense, hybrid, external)
- 📄 Create embeddings for text, documents, audio, images and video
- 💡 Pipelines powered by language models that run LLM prompts, question-answering, labeling, transcription, translation, summarizations and more
- ↪️️ Workflows to join pipelines together and aggregate business logic. txtai processes can be simple microservices or multi-model workflows.
@@ -59,16 +50,3 @@ Summary of txtai features:
- ☁️ Cloud-native architecture that scales out with container orchestration systems (e.g. Kubernetes)
txtai is built with Python 3.8+, [Hugging Face Transformers](https://github.com/huggingface/transformers), [Sentence Transformers](https://github.com/UKPLab/sentence-transformers) and [FastAPI](https://github.com/tiangolo/fastapi)
The following applications are powered by txtai.
![apps](https://raw.githubusercontent.com/neuml/txtai/master/apps.jpg)
| Application | Description |
|:----------|:-------------|
| [txtchat](https://github.com/neuml/txtchat) | Conversational search and workflows for all |
| [paperai](https://github.com/neuml/paperai) | Semantic search and workflows for medical/scientific papers |
| [codequestion](https://github.com/neuml/codequestion) | Semantic search for developers |
| [tldrstory](https://github.com/neuml/tldrstory) | Semantic search for headlines and story text |
In addition to this list, there are also many other [open-source projects](https://github.com/neuml/txtai/network/dependents), [published research](https://scholar.google.com/scholar?q=txtai&hl=en&as_ylo=2022) and closed proprietary/commercial projects that have built on txtai in production.
docs/poweredby.md
+14
View File
@@ -0,0 +1,14 @@
# Powered by txtai
The following applications are powered by txtai.
![apps](https://raw.githubusercontent.com/neuml/txtai/master/apps.jpg)
| Application | Description |
|:----------|:-------------|
| [txtchat](https://github.com/neuml/txtchat) | Conversational search and workflows for all |
| [paperai](https://github.com/neuml/paperai) | Semantic search and workflows for medical/scientific papers |
| [codequestion](https://github.com/neuml/codequestion) | Semantic search for developers |
| [tldrstory](https://github.com/neuml/tldrstory) | Semantic search for headlines and story text |
In addition to this list, there are also many other [open-source projects](https://github.com/neuml/txtai/network/dependents), [published research](https://scholar.google.com/scholar?q=txtai&hl=en&as_ylo=2022) and closed proprietary/commercial projects that have built on txtai in production.
docs/usecases.md
+56
View File
@@ -0,0 +1,56 @@
# Use Cases
The following sections give an overview of the main txtai use cases. A comprehensive set of over 50 [example notebooks and applications](../examples) are also available.
## Semantic Search
Build semantic/similarity/vector/neural search applications.
![demo](https://raw.githubusercontent.com/neuml/txtai/master/demo.gif)
Traditional search systems use keywords to find data. Semantic search has an understanding of natural language and identifies results that have the same meaning, not necessarily the same keywords.
![search](https://raw.githubusercontent.com/neuml/txtai/master/docs/images/search.png#gh-light-mode-only)
![search](https://raw.githubusercontent.com/neuml/txtai/master/docs/images/search-dark.png#gh-dark-mode-only)
Get started with the following examples.
| Notebook | Description | |
|:----------|:-------------|------:|
| [Introducing txtai](https://github.com/neuml/txtai/blob/master/examples/01_Introducing_txtai.ipynb) [▶️](https://www.youtube.com/watch?v=SIezMnVdmMs) | Overview of the functionality provided by txtai | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/01_Introducing_txtai.ipynb) |
| [Build an Embeddings index with Hugging Face Datasets](https://github.com/neuml/txtai/blob/master/examples/02_Build_an_Embeddings_index_with_Hugging_Face_Datasets.ipynb) | Index and search Hugging Face Datasets | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/02_Build_an_Embeddings_index_with_Hugging_Face_Datasets.ipynb) |
| [Add semantic search to Elasticsearch](https://github.com/neuml/txtai/blob/master/examples/04_Add_semantic_search_to_Elasticsearch.ipynb) | Add semantic search to existing search systems | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/04_Add_semantic_search_to_Elasticsearch.ipynb) |
| [Semantic Graphs](https://github.com/neuml/txtai/blob/master/examples/38_Introducing_the_Semantic_Graph.ipynb) | Explore topics, data connectivity and run network analysis| [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/38_Introducing_the_Semantic_Graph.ipynb) |
| [Embeddings in the Cloud](https://github.com/neuml/txtai/blob/master/examples/43_Embeddings_in_the_Cloud.ipynb) | Load and use an embeddings index from the Hugging Face Hub | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/43_Embeddings_in_the_Cloud.ipynb) |
| [Customize your own embeddings database](https://github.com/neuml/txtai/blob/master/examples/45_Customize_your_own_embeddings_database.ipynb) | Ways to combine vector indexes with relational databases | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/45_Customize_your_own_embeddings_database.ipynb) |
## LLM Orchestration
Prompt-driven search, retrieval augmented generation (RAG), pipelines and workflows that interface with large language models (LLMs).
![llm](images/llm.png)
Integrate conversational search, LLM chains and self-critique.
| Notebook | Description | |
|:----------|:-------------|------:|
| [Prompt-driven search with LLMs](https://github.com/neuml/txtai/blob/master/examples/42_Prompt_driven_search_with_LLMs.ipynb) | Embeddings-guided and Prompt-driven search with Large Language Models (LLMs) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/42_Prompt_driven_search_with_LLMs.ipynb) |
| [Prompt templates and task chains](https://github.com/neuml/txtai/blob/master/examples/44_Prompt_templates_and_task_chains.ipynb) | Build model prompts and connect tasks together with workflows | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/44_Prompt_templates_and_task_chains.ipynb) |
## Language Model Workflows
Language model workflows, also known as semantic workflows, connect language models together to build intelligent applications.
![flows](images/flows.png#gh-light-mode-only)
![flows](images/flows-dark.png#gh-dark-mode-only)
While LLMs are powerful, there are plenty of smaller, more specialized models that work better and faster for specific tasks. This includes models for extractive question-answering, automatic summarization, text-to-speech, transcription and translation.
| Notebook | Description | |
|:----------|:-------------|------:|
| [Run pipeline workflows](https://github.com/neuml/txtai/blob/master/examples/14_Run_pipeline_workflows.ipynb) [▶️](https://www.youtube.com/watch?v=UBMPDCn1gEU) | Simple yet powerful constructs to efficiently process data | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/14_Run_pipeline_workflows.ipynb) |
| [Extractive QA with txtai](https://github.com/neuml/txtai/blob/master/examples/05_Extractive_QA_with_txtai.ipynb) | Introduction to extractive question-answering with txtai | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/05_Extractive_QA_with_txtai.ipynb) |
| [Building abstractive text summaries](https://github.com/neuml/txtai/blob/master/examples/09_Building_abstractive_text_summaries.ipynb) | Run abstractive text summarization | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/09_Building_abstractive_text_summaries.ipynb) |
| [Text to speech generation](https://github.com/neuml/txtai/blob/master/examples/40_Text_to_Speech_Generation.ipynb) | Generate speech from text | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/40_Text_to_Speech_Generation.ipynb) |
| [Transcribe audio to text](https://github.com/neuml/txtai/blob/master/examples/11_Transcribe_audio_to_text.ipynb) | Convert audio files to text | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/11_Transcribe_audio_to_text.ipynb) |
| [Translate text between languages](https://github.com/neuml/txtai/blob/master/examples/12_Translate_text_between_languages.ipynb) | Streamline machine translation and language detection | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/12_Translate_text_between_languages.ipynb) |
docs/why.md
+2 -2
View File
@@ -8,9 +8,9 @@ New vector databases, LLM frameworks and everything in between are sprouting up
- Up and running in minutes with [pip](../install/) or [Docker](../cloud/)
```python
# Get started in a couple lines
from txtai.embeddings import Embeddings
import txtai
embeddings = Embeddings()
embeddings = txtai.Embeddings()
embeddings.index(["Correct", "Not what we hoped"])
embeddings.search("positive", 1)
#[(0, 0.29862046241760254)]
logo.png
BIN
View File
Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 29 KiB

After

Width:  |  Height:  |  Size: 13 KiB

mkdocs.yml
+3 -1
View File
@@ -52,8 +52,8 @@ markdown_extensions:
nav:
- Home: index.md
- Why txtai?: why.md
- Use Cases: usecases.md
- Installation: install.md
- Examples: examples.md
- Model Guide: models.md
- Embeddings:
- embeddings/index.md
@@ -114,5 +114,7 @@ nav:
- Configuration: api/configuration.md
- Methods: api/methods.md
- Cloud: cloud.md
- Examples: examples.md
- FAQ: faq.md
- Powered by txtai: poweredby.md
- Further Reading: further.md