💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
Python agentsaiai-agentsembeddingsinformation-retrievallanguage-modellarge-language-modelsllmnlppythonragretrieval-augmented-generationsearchsearch-enginesemantic-searchsentence-embeddingstransformerstxtaivector-databasevector-search
Update documentation
davidmezzetti12646f2bc277
diff --git a/README.md b/README.mdindex e43290e9..2e3c02b6 100644--- a/README.md+++ b/README.md@@ -120,6 +120,7 @@ See below to learn more.| Notebook | Description | ||:----------|:-------------|------:|| [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 | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/44_Prompt_templates_and_task_chains.ipynb) |+| [Integrate LLM frameworks](https://github.com/neuml/txtai/blob/master/examples/53_Integrate_LLM_Frameworks.ipynb) | Integrate llama.cpp, LiteLLM and custom generation frameworks | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/53_Integrate_LLM_Frameworks.ipynb) |#### Retrieval augmented generation@@ -132,8 +133,8 @@ A novel feature of txtai is that it can provide both an answer and source citati| Notebook | Description | ||:----------|:-------------|------:|-| [Build RAG pipelines with txtai](https://github.com/neuml/txtai/blob/master/examples/52_Build_RAG_pipelines_with_txtai.ipynb) | Guide on retrieval augmented generation including how to create citations | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/52_Build_RAG_pipelines_with_txtai.ipynb) || [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) | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/42_Prompt_driven_search_with_LLMs.ipynb) |+| [Build RAG pipelines with txtai](https://github.com/neuml/txtai/blob/master/examples/52_Build_RAG_pipelines_with_txtai.ipynb) | Guide on retrieval augmented generation including how to create citations | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/52_Build_RAG_pipelines_with_txtai.ipynb) |### Language Model Workflowsdiff --git a/docs/examples.md b/docs/examples.mdindex 8c0be3c2..52eacf6f 100644--- a/docs/examples.md+++ b/docs/examples.md@@ -29,9 +29,10 @@ LLM chains, retrieval augmented generation (RAG), chat with your data, pipelines| 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) | [](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 | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/44_Prompt_templates_and_task_chains.ipynb) || [Build RAG pipelines with txtai](https://github.com/neuml/txtai/blob/master/examples/52_Build_RAG_pipelines_with_txtai.ipynb) | Guide on retrieval augmented generation including how to create citations | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/52_Build_RAG_pipelines_with_txtai.ipynb) |-| [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) | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/42_Prompt_driven_search_with_LLMs.ipynb) |+| [Integrate LLM frameworks](https://github.com/neuml/txtai/blob/master/examples/53_Integrate_LLM_Frameworks.ipynb) | Integrate llama.cpp, LiteLLM and custom generation frameworks | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/53_Integrate_LLM_Frameworks.ipynb) |## Pipelinesdiff --git a/docs/pipeline/index.md b/docs/pipeline/index.mdindex e42fcf24..20edb787 100644--- a/docs/pipeline/index.md+++ b/docs/pipeline/index.md@@ -24,7 +24,7 @@ The following is a list of the default pipelines available in txtai. All pipelin- [Objects](image/objects)- Text- [Entity](text/entity)- - [Extractive QA](text/extractor)+ - [Extractor](text/extractor)- [Labeling](text/labels)- [LLM](text/llm)- [Similarity](text/similarity)diff --git a/docs/pipeline/text/extractor.md b/docs/pipeline/text/extractor.mdindex b47fb0c9..b213ddd6 100644--- a/docs/pipeline/text/extractor.md+++ b/docs/pipeline/text/extractor.md@@ -53,6 +53,8 @@ See the links below for more detailed examples.|:----------|:-------------|------:|| [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) | [](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 | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/44_Prompt_templates_and_task_chains.ipynb) |+| [Build RAG pipelines with txtai](https://github.com/neuml/txtai/blob/master/examples/52_Build_RAG_pipelines_with_txtai.ipynb) | Guide on retrieval augmented generation including how to create citations | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/52_Build_RAG_pipelines_with_txtai.ipynb) |+| [Integrate LLM frameworks](https://github.com/neuml/txtai/blob/master/examples/53_Integrate_LLM_Frameworks.ipynb) | Integrate llama.cpp, LiteLLM and custom generation frameworks | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/53_Integrate_LLM_Frameworks.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 | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/05_Extractive_QA_with_txtai.ipynb) || [Extractive QA with Elasticsearch](https://github.com/neuml/txtai/blob/master/examples/06_Extractive_QA_with_Elasticsearch.ipynb) | Run extractive question-answering queries with Elasticsearch | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/06_Extractive_QA_with_Elasticsearch.ipynb) || [Extractive QA to build structured data](https://github.com/neuml/txtai/blob/master/examples/20_Extractive_QA_to_build_structured_data.ipynb) | Build structured datasets using extractive question-answering | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/20_Extractive_QA_to_build_structured_data.ipynb) |diff --git a/docs/pipeline/text/llm.md b/docs/pipeline/text/llm.mdindex 8d6dd31a..cc6d4090 100644--- a/docs/pipeline/text/llm.md+++ b/docs/pipeline/text/llm.md@@ -3,7 +3,7 @@-The LLM pipeline runs prompts through a large language model (LLM). This pipeline autodetects if the model path is a text generation or sequence to sequence model.+The LLM pipeline runs prompts through a large language model (LLM). This pipeline autodetects the LLM framework based on the model path.## Example@@ -28,22 +28,17 @@ llm()```-The LLM pipeline automatically detects the underlying model type (`text-generation` or `sequence-sequence`). This can also be manually set.+The LLM pipeline automatically detects the underlying LLM framework. This can also be manually set.```python-from txtai.pipeline import LLM, Generator, Sequences--# Set model type via task parameter-llm = LLM("google/flan-t5-xl", task="sequence-sequence")--# Create sequences pipeline (same as previous statement)-sequences = Sequences("google/flan-t5-xl")+from txtai.pipeline import LLM-# Set model type via task parameter-llm = LLM("openlm-research/open_llama_3b", task="language-generation")+# Set method as litellm+llm = LLM("vllm/Open-Orca/Mistral-7B-OpenOrca", method="litellm")-# Create generator pipeline (same as previous statement)-generator = Generator("openlm-research/open_llama_3b")+# Set method as llama.cpp+llm = LLM("TheBloke/Mistral-7B-OpenOrca-GGUF/mistral-7b-openorca.Q4_K_M.gguf",+ method="llama.cpp")```Models can be externally loaded and passed to pipelines. This is useful for models that are not yet supported by Transformers and/or need special initialization.@@ -71,6 +66,8 @@ See the links below for more detailed examples.|:----------|:-------------|------:|| [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) | [](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 | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/44_Prompt_templates_and_task_chains.ipynb) |+| [Build RAG pipelines with txtai](https://github.com/neuml/txtai/blob/master/examples/52_Build_RAG_pipelines_with_txtai.ipynb) | Guide on retrieval augmented generation including how to create citations | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/52_Build_RAG_pipelines_with_txtai.ipynb) |+| [Integrate LLM frameworks](https://github.com/neuml/txtai/blob/master/examples/53_Integrate_LLM_Frameworks.ipynb) | Integrate llama.cpp, LiteLLM and custom generation frameworks | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/53_Integrate_LLM_Frameworks.ipynb) |## Configuration-driven examplediff --git a/docs/usecases.md b/docs/usecases.mdindex 76890885..bebee9f7 100644--- a/docs/usecases.md+++ b/docs/usecases.md@@ -37,6 +37,7 @@ See below to learn more.| Notebook | Description | ||:----------|:-------------|------:|| [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 | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/44_Prompt_templates_and_task_chains.ipynb) |+| [Integrate LLM frameworks](https://github.com/neuml/txtai/blob/master/examples/53_Integrate_LLM_Frameworks.ipynb) | Integrate llama.cpp, LiteLLM and custom generation frameworks | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/53_Integrate_LLM_Frameworks.ipynb) |### Retrieval augmented generation@@ -49,8 +50,8 @@ A novel feature of txtai is that it can provide both an answer and source citati| Notebook | Description | ||:----------|:-------------|------:|-| [Build RAG pipelines with txtai](https://github.com/neuml/txtai/blob/master/examples/52_Build_RAG_pipelines_with_txtai.ipynb) | Guide on retrieval augmented generation including how to create citations | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/52_Build_RAG_pipelines_with_txtai.ipynb) || [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) | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/42_Prompt_driven_search_with_LLMs.ipynb) |+| [Build RAG pipelines with txtai](https://github.com/neuml/txtai/blob/master/examples/52_Build_RAG_pipelines_with_txtai.ipynb) | Guide on retrieval augmented generation including how to create citations | [](https://colab.research.google.com/github/neuml/txtai/blob/master/examples/52_Build_RAG_pipelines_with_txtai.ipynb) |## Language Model Workflows