Merge branch 'master' into model_gallery

.vscode/launch.json

@@ -1,6 +1,19 @@
 {
     "version": "0.2.0",
     "configurations": [
+        {
+            "name": "Python: Current File",
+            "type": "python",
+            "request": "launch",
+            "program": "${file}",
+            "console": "integratedTerminal",
+            "justMyCode": false,
+            "cwd": "${workspaceFolder}/examples/langchain-chroma",
+            "env": {
+                "OPENAI_API_BASE": "http://localhost:8080/v1",
+                "OPENAI_API_KEY": "abc"
+            }
+        },
         {
             "name": "Launch Go",
             "type": "go",

examples/langchain-chroma/.env.example

@@ -0,0 +1,5 @@
+THREADS=4
+CONTEXT_SIZE=512
+MODELS_PATH=/models
+DEBUG=true
+# BUILD_TYPE=generic

examples/langchain-chroma/.gitignore

@@ -0,0 +1,4 @@
+db/
+state_of_the_union.txt
+models/bert
+models/ggml-gpt4all-j

examples/langchain-chroma/README.md

@@ -10,13 +10,20 @@ Download the models and start the API:
 # Clone LocalAI
 git clone https://github.com/go-skynet/LocalAI
 
-cd LocalAI/examples/query_data
+cd LocalAI/examples/langchain-chroma
 
 wget https://huggingface.co/skeskinen/ggml/resolve/main/all-MiniLM-L6-v2/ggml-model-q4_0.bin -O models/bert
 wget https://gpt4all.io/models/ggml-gpt4all-j.bin -O models/ggml-gpt4all-j
 
+# configure your .env
+# NOTE: ensure that THREADS does not exceed your machine's CPU cores
+mv .env.example .env
+
 # start with docker-compose
 docker-compose up -d --build
+
+# tail the logs & wait until the build completes
+docker logs -f langchain-chroma-api-1
 ```
 
 ### Python requirements
@@ -37,7 +44,7 @@ wget https://raw.githubusercontent.com/hwchase17/chat-your-data/master/state_of_
 python store.py
 ```
 
-After it finishes, a directory "storage" will be created with the vector index database.
+After it finishes, a directory "db" will be created with the vector index database.
 
 ## Query
 

examples/langchain-chroma/docker-compose.yml

@@ -0,0 +1,15 @@
+version: '3.6'
+
+services:
+  api:
+    image: quay.io/go-skynet/local-ai:latest
+    build:
+      context: ../../
+      dockerfile: Dockerfile
+    ports:
+      - 8080:8080
+    env_file:
+      - ../../.env
+    volumes:
+      - ./models:/models:cached
+    command: ["/usr/bin/local-ai"]

examples/langchain-chroma/models/embeddings.yaml

@@ -1,5 +1,6 @@
 name: text-embedding-ada-002
 parameters:
   model: bert
+threads: 4
 backend: bert-embeddings
 embeddings: true

examples/langchain-chroma/query.py

@@ -2,8 +2,9 @@
 import os
 from langchain.vectorstores import Chroma
 from langchain.embeddings import OpenAIEmbeddings
-from langchain.llms import OpenAI
+from langchain.chat_models import ChatOpenAI
-from langchain.chains import VectorDBQA
+from langchain.chains import RetrievalQA
+from langchain.vectorstores.base import VectorStoreRetriever
 
 base_path = os.environ.get('OPENAI_API_BASE', 'http://localhost:8080/v1')
 
@@ -12,8 +13,10 @@ embedding = OpenAIEmbeddings()
 persist_directory = 'db'
 
 # Now we can load the persisted database from disk, and use it as normal. 
+llm = ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo", openai_api_base=base_path)
 vectordb = Chroma(persist_directory=persist_directory, embedding_function=embedding)
-qa = VectorDBQA.from_chain_type(llm=OpenAI(temperature=0, model_name="gpt-3.5-turbo", openai_api_base=base_path), chain_type="stuff", vectorstore=vectordb)
+retriever = VectorStoreRetriever(vectorstore=vectordb)
+qa = RetrievalQA.from_llm(llm=llm, retriever=retriever)
 
 query = "What the president said about taxes ?"
 print(qa.run(query))

examples/langchain-chroma/store.py

@@ -2,9 +2,7 @@
 import os
 from langchain.vectorstores import Chroma
 from langchain.embeddings import OpenAIEmbeddings
-from langchain.text_splitter import RecursiveCharacterTextSplitter,TokenTextSplitter,CharacterTextSplitter
+from langchain.text_splitter import 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')
@@ -14,7 +12,6 @@ loader = TextLoader('state_of_the_union.txt')
 documents = loader.load()
 
 text_splitter = CharacterTextSplitter(chunk_size=300, chunk_overlap=70)
-#text_splitter = TokenTextSplitter()
 texts = text_splitter.split_documents(documents)
 
 # Embed and store the texts

examples/query_data/docker-compose.yml

@@ -4,7 +4,7 @@ services:
   api:
     image: quay.io/go-skynet/local-ai:latest
     build:
-      context: .
+      context: ../../
       dockerfile: Dockerfile
     ports:
       - 8080:8080

examples/rwkv/.gitignore

@@ -0,0 +1,2 @@
+models/rwkv
+models/rwkv.tokenizer.json

examples/rwkv/Dockerfile.build

@@ -1,5 +1,7 @@
 FROM python
 
+RUN apt-get update && apt-get -y install cmake
+
 # convert the model (one-off)
 RUN pip3 install torch numpy
 

go.mod

@@ -10,14 +10,14 @@ require (
 	github.com/go-skynet/go-bert.cpp v0.0.0-20230516063724-cea1ed76a7f4
 	github.com/go-skynet/go-gpt2.cpp v0.0.0-20230512145559-7bff56f02245
 	github.com/go-skynet/go-gpt4all-j.cpp v0.0.0-20230422090028-1f7bff57f66c
-	github.com/go-skynet/go-llama.cpp v0.0.0-20230516230554-b7bbefbe0b84
+	github.com/go-skynet/go-llama.cpp v0.0.0-20230518171914-33f8c2db53bf
 	github.com/gofiber/fiber/v2 v2.45.0
 	github.com/google/uuid v1.3.0
 	github.com/hashicorp/go-multierror v1.1.1
 	github.com/mudler/go-stable-diffusion v0.0.0-20230516152536-c0748eca3642
-	github.com/nomic-ai/gpt4all/gpt4all-bindings/golang v0.0.0-20230518171731-546600fb6878
+	github.com/nomic-ai/gpt4all/gpt4all-bindings/golang v0.0.0-20230518183047-94f401889042
 	github.com/onsi/ginkgo/v2 v2.9.5
-	github.com/onsi/gomega v1.27.6
+	github.com/onsi/gomega v1.27.7
 	github.com/otiai10/copy v1.11.0
 	github.com/otiai10/openaigo v1.1.0
 	github.com/rs/zerolog v1.29.1

go.sum

@@ -66,6 +66,8 @@ github.com/go-skynet/go-llama.cpp v0.0.0-20230510072905-70593fccbe4b h1:qqxrjY8f
 github.com/go-skynet/go-llama.cpp v0.0.0-20230510072905-70593fccbe4b/go.mod h1:DLfsPD7tYYnpksERH83HSf7qVNW3FIwmz7/zfYO0/6I=
 github.com/go-skynet/go-llama.cpp v0.0.0-20230516230554-b7bbefbe0b84 h1:f5iYF75bAr73Tl8AdtFD5Urs/2bsHKPh52K++jLbsfk=
 github.com/go-skynet/go-llama.cpp v0.0.0-20230516230554-b7bbefbe0b84/go.mod h1:jxyQ26t1aKC5Gn782w9WWh5n1133PxCOfkuc01xM4RQ=
+github.com/go-skynet/go-llama.cpp v0.0.0-20230518171914-33f8c2db53bf h1:D9CLQwr1eqSnV0DM7YGOKhSfNajj2qOA7XAD6+p1/HI=
+github.com/go-skynet/go-llama.cpp v0.0.0-20230518171914-33f8c2db53bf/go.mod h1:oA0r4BW8ndyjTMGi1tulsNd7sdg3Ql8MaVFuT1zF6ws=
 github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572 h1:tfuBGBXKqDEevZMzYi5KSi8KkcZtzBcTgAUUtapy0OI=
 github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572/go.mod h1:9Pwr4B2jHnOSGXyyzV8ROjYa2ojvAY6HCGYYfMoC3Ls=
 github.com/godbus/dbus/v5 v5.0.4/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
@@ -115,12 +117,16 @@ github.com/nomic-ai/gpt4all/gpt4all-bindings/golang v0.0.0-20230516143155-79d624
 github.com/nomic-ai/gpt4all/gpt4all-bindings/golang v0.0.0-20230516143155-79d6243fe1bc/go.mod h1:4T3CHXyrt+7FQHXaxULZfPjHbD8/99WuDDJa0YVZARI=
 github.com/nomic-ai/gpt4all/gpt4all-bindings/golang v0.0.0-20230518171731-546600fb6878 h1:3MFUW2a1Aqm2nMF5f+PNGq55cbxIzkRHQX/o7JVysAo=
 github.com/nomic-ai/gpt4all/gpt4all-bindings/golang v0.0.0-20230518171731-546600fb6878/go.mod h1:4T3CHXyrt+7FQHXaxULZfPjHbD8/99WuDDJa0YVZARI=
+github.com/nomic-ai/gpt4all/gpt4all-bindings/golang v0.0.0-20230518183047-94f401889042 h1:bMU75tTgyw6mYDa5NbOHlZ1KYqQgz7heQFfTwuvCGww=
+github.com/nomic-ai/gpt4all/gpt4all-bindings/golang v0.0.0-20230518183047-94f401889042/go.mod h1:4T3CHXyrt+7FQHXaxULZfPjHbD8/99WuDDJa0YVZARI=
 github.com/onsi/ginkgo/v2 v2.9.4 h1:xR7vG4IXt5RWx6FfIjyAtsoMAtnc3C/rFXBBd2AjZwE=
 github.com/onsi/ginkgo/v2 v2.9.4/go.mod h1:gCQYp2Q+kSoIj7ykSVb9nskRSsR6PUj4AiLywzIhbKM=
 github.com/onsi/ginkgo/v2 v2.9.5 h1:+6Hr4uxzP4XIUyAkg61dWBw8lb/gc4/X5luuxN/EC+Q=
 github.com/onsi/ginkgo/v2 v2.9.5/go.mod h1:tvAoo1QUJwNEU2ITftXTpR7R1RbCzoZUOs3RonqW57k=
 github.com/onsi/gomega v1.27.6 h1:ENqfyGeS5AX/rlXDd/ETokDz93u0YufY1Pgxuy/PvWE=
 github.com/onsi/gomega v1.27.6/go.mod h1:PIQNjfQwkP3aQAH7lf7j87O/5FiNr+ZR8+ipb+qQlhg=
+github.com/onsi/gomega v1.27.7 h1:fVih9JD6ogIiHUN6ePK7HJidyEDpWGVB5mzM7cWNXoU=
+github.com/onsi/gomega v1.27.7/go.mod h1:1p8OOlwo2iUUDsHnOrjE5UKYJ+e3W8eQ3qSlRahPmr4=
 github.com/otiai10/copy v1.11.0 h1:OKBD80J/mLBrwnzXqGtFCzprFSGioo30JcmR4APsNwc=
 github.com/otiai10/copy v1.11.0/go.mod h1:rSaLseMUsZFFbsFGc7wCJnnkTAvdc5L6VWxPE4308Ww=
 github.com/otiai10/mint v1.5.1 h1:XaPLeE+9vGbuyEHem1JNk3bYc7KKqyI/na0/mLd/Kks=