diff --git a/examples/langchain-chroma/.env b/examples/langchain-chroma/.env
new file mode 100644
index 00000000..37cda598
--- /dev/null
+++ b/examples/langchain-chroma/.env
@@ -0,0 +1,5 @@
+THREADS=4
+CONTEXT_SIZE=512
+MODELS_PATH=/models
+DEBUG=true
+# BUILD_TYPE=generic
\ No newline at end of file
diff --git a/examples/langchain-chroma/.gitignore b/examples/langchain-chroma/.gitignore
new file mode 100644
index 00000000..3dc19014
--- /dev/null
+++ b/examples/langchain-chroma/.gitignore
@@ -0,0 +1,4 @@
+db/
+state_of_the_union.txt
+models/bert
+models/ggml-gpt4all-j
\ No newline at end of file
diff --git a/examples/langchain-chroma/README.md b/examples/langchain-chroma/README.md
index 70e3f42b..abc4d1ac 100644
--- a/examples/langchain-chroma/README.md
+++ b/examples/langchain-chroma/README.md
@@ -10,13 +10,16 @@ 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
 
 # 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 +40,7 @@ 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
 
diff --git a/examples/langchain-chroma/docker-compose.yml b/examples/langchain-chroma/docker-compose.yml
new file mode 100644
index 00000000..96ef540e
--- /dev/null
+++ b/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"]
diff --git a/examples/langchain-chroma/models/embeddings.yaml b/examples/langchain-chroma/models/embeddings.yaml
index 46a08502..536c8de1 100644
--- a/examples/langchain-chroma/models/embeddings.yaml
+++ b/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