fix(rwkv): load tokenizer file from model path (#255)

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>

Makefile

@@ -3,14 +3,14 @@ GOTEST=$(GOCMD) test
 GOVET=$(GOCMD) vet
 BINARY_NAME=local-ai
 
-GOLLAMA_VERSION?=70593fccbe4b01dedaab805b0f25cb58192c7b38
+GOLLAMA_VERSION?=eb99b5438787cbd687682da445e879e02bfeaa07
 GPT4ALL_REPO?=https://github.com/go-skynet/gpt4all
 GPT4ALL_VERSION?=a330bfe26e9e35ca402e16df18973a3b162fb4db
 GOGPT2_VERSION?=92421a8cf61ed6e03babd9067af292b094cb1307
 RWKV_REPO?=https://github.com/donomii/go-rwkv.cpp
 RWKV_VERSION?=07166da10cb2a9e8854395a4f210464dcea76e47
-WHISPER_CPP_VERSION?=bf2449dfae35a46b2cd92ab22661ce81a48d4993
-BERT_VERSION?=ac22f8f74aec5e31bc46242c17e7d511f127856b
+WHISPER_CPP_VERSION?=1d17cd5bb37a3212679d6055ad69ba5a8d58eb71
+BERT_VERSION?=33118e0da50318101408986b86a331daeb4a6658
 BLOOMZ_VERSION?=e9366e82abdfe70565644fbfae9651976714efd1
 
 

README.md

@@ -9,7 +9,7 @@
 
 [![](https://dcbadge.vercel.app/api/server/uJAeKSAGDy?style=flat-square&theme=default-inverted)](https://discord.gg/uJAeKSAGDy) 
 
-**LocalAI** is a drop-in replacement REST API compatible with OpenAI for local CPU inferencing. It allows to run models locally or on-prem with consumer grade hardware, supporting multiple models families. Supports also GPT4ALL-J which is licensed under Apache 2.0.
+**LocalAI** is a drop-in replacement REST API compatible with OpenAI for local inferencing. It allows to run models locally or on-prem with consumer grade hardware, supporting multiple models families. For a list of the supported model families, see [the model compatibility table below](https://github.com/go-skynet/LocalAI#model-compatibility-table).
 
 - OpenAI compatible API
 - Supports multiple models
@@ -25,6 +25,7 @@ See [examples on how to integrate LocalAI](https://github.com/go-skynet/LocalAI/
 
 ## News
 
+- 13-05-2023: __v1.11.0__ released! 🔥 Updated `llama.cpp` bindings: This update includes a breaking change in the model files ( https://github.com/ggerganov/llama.cpp/pull/1405 ) - old models should still work with the `gpt4all-llama` backend.
 - 12-05-2023: __v1.10.0__ released! 🔥🔥 Updated `gpt4all` bindings. Added support for GPTNeox (experimental), RedPajama (experimental), Starcoder (experimental), Replit (experimental), MosaicML MPT. Also now `embeddings` endpoint supports tokens arrays. See the [langchain-chroma](https://github.com/go-skynet/LocalAI/tree/master/examples/langchain-chroma) example! Note - this update does NOT include https://github.com/ggerganov/llama.cpp/pull/1405 which makes models incompatible.
 - 11-05-2023: __v1.9.0__ released! 🔥 Important whisper updates ( https://github.com/go-skynet/LocalAI/pull/233 https://github.com/go-skynet/LocalAI/pull/229 ) and extended gpt4all model families support ( https://github.com/go-skynet/LocalAI/pull/232 ). Redpajama/dolly experimental ( https://github.com/go-skynet/LocalAI/pull/214 )
 - 10-05-2023: __v1.8.0__ released! 🔥 Added support for fast and accurate embeddings with `bert.cpp` ( https://github.com/go-skynet/LocalAI/pull/222 )
@@ -683,6 +684,9 @@ Feel free to open up a PR to get your project listed!
 - [x] Multi-model support
 - [x] Have a webUI!
 - [x] Allow configuration of defaults for models.
+- [x] Support for embeddings
+- [x] Support for audio transcription with https://github.com/ggerganov/whisper.cpp
+- [ ] GPU/CUDA support ( https://github.com/go-skynet/LocalAI/issues/69 )
 - [ ] Enable automatic downloading of models from a curated gallery, with only free-licensed models, directly from the webui.
 
 ## Star history

examples/langchain-chroma/query.py

@@ -2,25 +2,14 @@
 import os
 from langchain.vectorstores import Chroma
 from langchain.embeddings import OpenAIEmbeddings
-from langchain.text_splitter import RecursiveCharacterTextSplitter,CharacterTextSplitter
 from langchain.llms import OpenAI
 from langchain.chains import VectorDBQA
-from langchain.document_loaders import TextLoader
 
 base_path = os.environ.get('OPENAI_API_BASE', 'http://localhost:8080/v1')
 
 # Load and process the text
-loader = TextLoader('state_of_the_union.txt')
-documents = loader.load()
-
-text_splitter = CharacterTextSplitter(chunk_size=300, chunk_overlap=70)
-texts = text_splitter.split_documents(documents)
-
-# Embed and store the texts
-# Supplying a persist_directory will store the embeddings on disk
-persist_directory = 'db'
-
 embedding = OpenAIEmbeddings()
+persist_directory = 'db'
 
 # Now we can load the persisted database from disk, and use it as normal. 
 vectordb = Chroma(persist_directory=persist_directory, embedding_function=embedding)

pkg/model/initializers.go

@@ -2,6 +2,7 @@ package model
 
 import (
 	"fmt"
+	"path/filepath"
 	"strings"
 
 	rwkv "github.com/donomii/go-rwkv.cpp"
@@ -143,7 +144,7 @@ func (ml *ModelLoader) BackendLoader(backendString string, modelFile string, lla
 	case BertEmbeddingsBackend:
 		return ml.LoadModel(modelFile, bertEmbeddings)
 	case RwkvBackend:
-		return ml.LoadModel(modelFile, rwkvLM(modelFile+tokenizerSuffix, threads))
+		return ml.LoadModel(modelFile, rwkvLM(filepath.Join(ml.ModelPath, modelFile+tokenizerSuffix), threads))
 	case WhisperBackend:
 		return ml.LoadModel(modelFile, whisperModel)
 	default: