docs: fix langchain-chroma example (#298)

Signed-off-by: Tyler Gillson <tyler.gillson@gmail.com>

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.chains import VectorDBQA
+from langchain.chat_models import ChatOpenAI
+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.llms import OpenAI
-from langchain.chains import VectorDBQA
+from langchain.text_splitter import CharacterTextSplitter
 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