/ docs / pipeline / index.md
index.md
 1  # Pipeline
 2  
 3  ![pipeline](../images/pipeline.png#only-light)
 4  ![pipeline](../images/pipeline-dark.png#only-dark)
 5  
 6  txtai provides a generic pipeline processing framework with the only interface requirement being a `__call__` method. Pipelines are flexible and process various types of data. Pipelines can wrap machine learning models as well as other processes.
 7  
 8  Pipelines are run with Python or configuration. Pipelines can be instantiated in [configuration](../api/configuration/#pipeline) using the lower case name of the pipeline. Configuration-driven pipelines are run with [workflows](../workflow/#configuration-driven-example) or the [API](../api#local-instance).
 9  
10  ## List of pipelines
11  
12  The following is a list of the current pipelines available in txtai. All pipelines use default models when otherwise not specified. See the [model guide](../models) for the current model recommendations. All pipelines are designed to work with local models via the [Transformers library](https://github.com/huggingface/transformers).
13  
14  The `LLM` and `RAG` pipelines also have integrations for [llama.cpp](https://github.com/abetlen/llama-cpp-python) and [hosted API models via LiteLLM](https://github.com/BerriAI/litellm). The `LLM` pipeline can be prompted to accomplish many of the same tasks (i.e. summarization, translation, classification).
15  
16  - Audio
17      - [AudioMixer](audio/audiomixer)
18      - [AudioStream](audio/audiostream)
19      - [Microphone](audio/microphone)
20      - [TextToAudio](audio/texttoaudio)
21      - [TextToSpeech](audio/texttospeech)
22      - [Transcription](audio/transcription)
23  - Data Processing
24      - [FileToHTML](data/filetohtml)
25      - [HTMLToMarkdown](data/htmltomd)
26      - [Segmentation](data/segmentation)
27      - [Tabular](data/tabular)
28      - [Text extraction](data/textractor)
29      - [Tokenizer](data/tokenizer)
30  - Image
31      - [Caption](image/caption)
32      - [Image Hash](image/imagehash)
33      - [Objects](image/objects)
34  - Text
35      - [Entity](text/entity)
36      - [Labeling](text/labels)
37      - [LLM](text/llm)
38      - [RAG](text/rag)
39      - [Reranker](text/reranker)
40      - [Similarity](text/similarity)
41      - [Summary](text/summary)
42      - [Translation](text/translation)
43  - Training
44      - [HF ONNX](train/hfonnx)
45      - [ML ONNX](train/mlonnx)
46      - [Trainer](train/trainer)