Update documentation

neuml · May 28, 2024 · 88adf4d · 88adf4d
1 parent 3422e0f
commit 88adf4d
Show file tree

Hide file tree

Showing 3 changed files with 13 additions and 3 deletions.
diff --git a/docs/embeddings/configuration/vectors.md b/docs/embeddings/configuration/vectors.md
@@ -12,12 +12,12 @@ Sets the path for a vectors model. When using a transformers/sentence-transforme
 
 ## method
 ```yaml
-method: transformers|sentence-transformers|words|external
+method: transformers|sentence-transformers|llama.cpp|litellm|external|words
 ```
 
 Embeddings method to use. If the method is not provided, it is inferred using the `path`.
 
-`sentence-transformers` and `words` require the [vectors](../../../install/#vectors) extras package to be installed.
+`sentence-transformers`, `llama.cpp`, `litellm` and `words` require the [vectors](../../../install/#vectors) extras package to be installed.
 
 ### transformers
 
@@ -31,6 +31,14 @@ from `transformers` to `meanpooling` or `clspooling` respectively.
 
 Same as transformers but loads models with the [sentence-transformers](https://github.com/UKPLab/sentence-transformers) library.
 
+### llama.cpp
+
+Builds embeddings using a llama.cpp model. Supports both local and remote GGUF paths on the HF Hub.
+
+### litellm
+
+Builds embeddings using a LiteLLM model. See the [LiteLLM documentation](https://litellm.vercel.app/docs/providers) for the options available with LiteLLM models.
+
 ### words
 
 Builds embeddings using a word embeddings model. Transformers models are the preferred vector backend in most cases. Word embeddings models may be deprecated in the future.

diff --git a/docs/install.md b/docs/install.md
@@ -102,7 +102,7 @@ pip install txtai[scoring]
 
 ### Vectors
 
-Support for sentence-transformers models not on the HF Hub and word vectors.
+Additional vector methods.
 
 ```
 pip install txtai[vectors]

diff --git a/docs/pipeline/text/llm.md b/docs/pipeline/text/llm.md
@@ -30,6 +30,8 @@ llm(
 
 The LLM pipeline automatically detects the underlying LLM framework. This can also be manually set.
 
+See the [LiteLLM documentation](https://litellm.vercel.app/docs/providers) for the options available with LiteLLM models. Models with llama.cpp support both local and remote GGUF paths on the HF Hub.
+
 ```python
 from txtai.pipeline import LLM