diff --git a/.github/workflows/docker/compose/retrievers-compose.yaml b/.github/workflows/docker/compose/retrievers-compose.yaml
index 7b89ce9bf..bfc8a29a5 100644
--- a/.github/workflows/docker/compose/retrievers-compose.yaml
+++ b/.github/workflows/docker/compose/retrievers-compose.yaml
@@ -47,3 +47,7 @@ services:
     build:
       dockerfile: comps/retrievers/neo4j/llama_index/Dockerfile
     image: ${REGISTRY:-opea}/retriever-neo4j-llamaindex:${TAG:-latest}
+  retriever-arango:
+    build:
+      dockerfile: comps/retrievers/arango/langchain/Dockerfile
+    image: ${REGISTRY:-opea}/retriever-arango:${TAG:-latest}
\ No newline at end of file
diff --git a/comps/retrievers/arango/langchain/Dockerfile b/comps/retrievers/arango/langchain/Dockerfile
new file mode 100644
index 000000000..043bf7460
--- /dev/null
+++ b/comps/retrievers/arango/langchain/Dockerfile
@@ -0,0 +1,33 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+FROM python:3.11-slim
+
+ENV LANG=C.UTF-8
+
+ENV HUGGINGFACEHUB_API_TOKEN=dummy
+
+ARG ARCH="cpu"
+
+RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
+    build-essential \
+    libgl1-mesa-glx \
+    libjemalloc-dev
+
+RUN useradd -m -s /bin/bash user && \
+    mkdir -p /home/user && \
+    chown -R user /home/user/
+
+USER user
+
+COPY comps /home/user/comps
+
+RUN pip install --no-cache-dir --upgrade pip setuptools && \
+    if [ ${ARCH} = "cpu" ]; then pip install --no-cache-dir torch --index-url https://download.pytorch.org/whl/cpu; fi && \
+    pip install --no-cache-dir -r /home/user/comps/retrievers/arangodb/langchain/requirements.txt
+
+ENV PYTHONPATH=$PYTHONPATH:/home/user
+
+WORKDIR /home/user/comps/retrievers/arangodb/langchain
+
+ENTRYPOINT ["python", "retriever_arangodb.py"]
diff --git a/comps/retrievers/arango/langchain/README.md b/comps/retrievers/arango/langchain/README.md
new file mode 100644
index 000000000..6e0c7a907
--- /dev/null
+++ b/comps/retrievers/arango/langchain/README.md
@@ -0,0 +1,111 @@
+# Retriever Microservice with ArangoDB (work-in-progress)
+
+## 🚀Start Microservice with Python
+
+### Install Requirements
+
+```bash
+pip install -r requirements.txt
+```
+
+### Start ArangoDB Server
+
+To launch ArangoDB locally, first ensure you have docker installed. Then, you can launch the database with the following docker command.
+
+**TODO: Switch to official image when ready**
+
+```bash
+docker run \
+  -p 8529:8529
+  -e ARANGO_ROOT_PASSWORD=test
+  jbajic/arangodb-arm:vector-index-preview
+```
+
+### Setup Environment Variables
+
+```bash
+export no_proxy=${your_no_proxy}
+export http_proxy=${your_http_proxy}
+export https_proxy=${your_http_proxy}
+export ARANGODB_URI=${your_arangodb_uri}
+export ARANGODB_USERNAME=${your_arangodb_username}
+export ARANGODB_PASSWORD=${your_arangodb_password}
+export ARANGODB_DATABASE=${your_arangodb_database}
+```
+
+### Start Retriever Service
+
+```bash
+python retriever_arangodb.py
+```
+
+## 🚀Start Microservice with Docker
+
+### Build Docker Image
+
+```bash
+cd ../../
+docker build -t opea/retriever-arangodb:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/retrievers/arangodb/langchain/Dockerfile .
+```
+
+### Run Docker with CLI
+
+```bash
+docker run -d --name="retriever-arangodb-server" -p 7000:7000 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e ARANGODB_URI=${your_arangodb_host_ip}  opea/retriever-arangodb:latest
+```
+
+## 🚀3. Consume Retriever Service
+
+### 3.1 Check Service Status
+
+```bash
+curl http://${your_ip}:7000/v1/health_check \
+  -X GET \
+  -H 'Content-Type: application/json'
+```
+
+### 3.2 Consume Embedding Service
+
+To consume the Retriever Microservice, you can generate a mock embedding vector of length 768 with Python.
+
+```bash
+export your_embedding=$(python -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
+curl http://${your_ip}:7000/v1/retrieval \
+  -X POST \
+  -d "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${your_embedding}}" \
+  -H 'Content-Type: application/json'
+```
+
+You can set the parameters for the retriever.
+
+```bash
+export your_embedding=$(python -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
+curl http://localhost:7000/v1/retrieval \
+  -X POST \
+  -d "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${your_embedding},\"search_type\":\"similarity\", \"k\":4}" \
+  -H 'Content-Type: application/json'
+```
+
+```bash
+export your_embedding=$(python -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
+curl http://localhost:7000/v1/retrieval \
+  -X POST \
+  -d "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${your_embedding},\"search_type\":\"similarity_distance_threshold\", \"k\":4, \"distance_threshold\":1.0}" \
+  -H 'Content-Type: application/json'
+```
+
+```bash
+export your_embedding=$(python -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
+curl http://localhost:7000/v1/retrieval \
+  -X POST \
+  -d "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${your_embedding},\"search_type\":\"similarity_score_threshold\", \"k\":4, \"score_threshold\":0.2}" \
+  -H 'Content-Type: application/json'
+```
+
+```bash
+export your_embedding=$(python -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
+curl http://localhost:7000/v1/retrieval \
+  -X POST \
+  -d "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${your_embedding},\"search_type\":\"mmr\", \"k\":4, \"fetch_k\":20, \"lambda_mult\":0.5}" \
+  -H 'Content-Type: application/json'
+```
diff --git a/comps/retrievers/arango/langchain/__init__.py b/comps/retrievers/arango/langchain/__init__.py
new file mode 100644
index 000000000..916f3a44b
--- /dev/null
+++ b/comps/retrievers/arango/langchain/__init__.py
@@ -0,0 +1,2 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
diff --git a/comps/retrievers/arango/langchain/config.py b/comps/retrievers/arango/langchain/config.py
new file mode 100644
index 000000000..8d8e089fe
--- /dev/null
+++ b/comps/retrievers/arango/langchain/config.py
@@ -0,0 +1,26 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+import os
+
+# ArangoDB configuration
+ARANGO_URL = os.getenv("ARANGO_URL", "http://localhost:8529")
+ARANGO_USERNAME = os.getenv("ARANGO_USERNAME", "root")
+ARANGO_PASSWORD = os.getenv("ARANGO_PASSWORD", "test")
+ARANGO_DB_NAME = os.getenv("ARANGO_DB_NAME", "_system")
+ARANGO_COLLECTION_NAME = os.getenv("ARANGO_COLLECTION_NAME", "SOURCE")
+ARANGO_DISTANCE_STRATEGY = os.getenv("ARANGO_DISTANCE_STRATEGY", "COSINE")
+ARANGO_TEXT_FIELD = os.getenv("ARANGO_TEXT_FIELD", "text")
+ARANGO_EMBBEDDING_FIELD = os.getenv("ARANGO_EMBEDDING_FIELD", "metadata.embedding")
+ARANGO_EMBED_DIMENSION = os.getenv("ARANGO_EMBED_DIMENSION")
+ARANGO_NUM_CENTROIDS = os.getenv("ARANGO_NUM_CENTROIDS", 1)
+ARANGO_GRAPH_NAME = os.getenv("ARANGO_GRAPH_NAME")
+
+# Embedding configuration
+EMBED_MODEL = os.getenv("EMBED_MODEL", "BAAI/bge-base-en-v1.5")
+EMBED_ENDPOINT = os.getenv("TEI_EMBEDDING_ENDPOINT", "")
+HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
+
+# OpenAI configuration (alternative to TEI & local model)
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
+OPENAI_EMBED_MODEL = os.getenv("OPENAI_EMBED_MODEL", "text-embedding-3-small")
diff --git a/comps/retrievers/arango/langchain/requirements.txt b/comps/retrievers/arango/langchain/requirements.txt
new file mode 100644
index 000000000..f1d40dbbe
--- /dev/null
+++ b/comps/retrievers/arango/langchain/requirements.txt
@@ -0,0 +1,22 @@
+docarray[full]
+fastapi
+frontend
+huggingface_hub
+langchain
+git+https://github.com/arangoml/langchain.git@arangodb#subdirectory=libs/community
+langchain_openai
+python-arango
+numpy
+opentelemetry-api
+opentelemetry-exporter-otlp
+opentelemetry-sdk
+pandas
+Pillow
+prometheus-fastapi-instrumentator
+pydantic
+pymupdf
+python-docx
+sentence_transformers
+shortuuid
+tiktoken
+uvicorn
diff --git a/comps/retrievers/arango/langchain/retriever_arangodb.py b/comps/retrievers/arango/langchain/retriever_arangodb.py
new file mode 100644
index 000000000..17df9e6d7
--- /dev/null
+++ b/comps/retrievers/arango/langchain/retriever_arangodb.py
@@ -0,0 +1,178 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+import os
+import time
+from typing import Union
+
+from arango import ArangoClient
+from config import (
+    ARANGO_COLLECTION_NAME,
+    ARANGO_DB_NAME,
+    ARANGO_DISTANCE_STRATEGY,
+    ARANGO_EMBBEDDING_FIELD,
+    ARANGO_NUM_CENTROIDS,
+    ARANGO_PASSWORD,
+    ARANGO_GRAPH_NAME,
+    ARANGO_TEXT_FIELD,
+    ARANGO_URL,
+    ARANGO_USERNAME,
+    ARANGO_EMBED_DIMENSION,
+    EMBED_ENDPOINT,
+    EMBED_MODEL,
+    HUGGINGFACEHUB_API_TOKEN,
+    OPENAI_API_KEY,
+    OPENAI_EMBED_MODEL,
+)
+from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceHubEmbeddings
+from langchain_community.vectorstores.arangodb_vector import ArangoVector
+from langchain_openai import OpenAIEmbeddings
+
+from comps import (
+    CustomLogger,
+    EmbedDoc,
+    SearchedDoc,
+    ServiceType,
+    TextDoc,
+    opea_microservices,
+    register_microservice,
+    register_statistics,
+    statistics_dict,
+)
+from comps.cores.proto.api_protocol import (
+    ChatCompletionRequest,
+    RetrievalRequest,
+    RetrievalResponse,
+    RetrievalResponseData,
+)
+
+logger = CustomLogger("retriever_arangodb")
+logflag = os.getenv("LOGFLAG", False)
+
+
+@register_microservice(
+    name="opea_service@retriever_arangodb",
+    service_type=ServiceType.RETRIEVER,
+    endpoint="/v1/retrieval",
+    host="0.0.0.0",
+    port=7000,
+)
+@register_statistics(names=["opea_service@retriever_arangodb"])
+async def retrieve(
+    input: Union[EmbedDoc, RetrievalRequest, ChatCompletionRequest]
+) -> Union[SearchedDoc, RetrievalResponse, ChatCompletionRequest]:
+    if logflag:
+        logger.info(input)
+    start = time.time()
+
+    index = vector_db.retrieve_vector_index()
+    if index is None and db.collection(vector_db.collection_name).count() > 0:
+        vector_db.create_vector_index()
+
+    query = input.text if isinstance(input, EmbedDoc) else input.input
+    embedding = input.embedding if isinstance(input.embedding, list) else None
+    k = input.k
+
+    if input.search_type == "similarity":
+        if not input.embedding:
+            raise ValueError("Embedding must be provided for similarity retriever")
+
+        search_res = await vector_db.asimilarity_search_by_vector(query=query, embedding=embedding, k=k)
+    elif input.search_type == "similarity_distance_threshold":
+        if input.distance_threshold is None:
+            raise ValueError("distance_threshold must be provided for similarity_distance_threshold retriever")
+        if not embedding:
+            raise ValueError("Embedding must not be None for similarity_distance_threshold retriever")
+
+        search_res = await vector_db.asimilarity_search_by_vector(
+            query=query,
+            embedding=embedding,
+            k=k,
+            distance_threshold=input.distance_threshold,
+        )
+    elif input.search_type == "similarity_score_threshold":
+        docs_and_similarities = await vector_db.asimilarity_search_with_relevance_scores(
+            query=query, embedding=embedding, k=k, score_threshold=input.score_threshold
+        )
+        search_res = [doc for doc, _ in docs_and_similarities]
+    elif input.search_type == "mmr":
+        search_res = await vector_db.amax_marginal_relevance_search(
+            query=query, embedding=embedding, k=k, fetch_k=input.fetch_k, lambda_mult=input.lambda_mult
+        )
+    else:
+        raise ValueError(f"Search Type '{input.search_type}' not valid")
+
+    # return different response format
+    retrieved_docs = []
+    if isinstance(input, EmbedDoc):
+        for r in search_res:
+            retrieved_docs.append(TextDoc(text=r.page_content, id=r.id))
+        result = SearchedDoc(retrieved_docs=retrieved_docs, initial_query=input.text)
+    else:
+        for r in search_res:
+            retrieved_docs.append(RetrievalResponseData(text=r.page_content, id=r.id, metadata=r.metadata))
+        if isinstance(input, RetrievalRequest):
+            result = RetrievalResponse(retrieved_docs=retrieved_docs)
+        elif isinstance(input, ChatCompletionRequest):
+            input.retrieved_docs = retrieved_docs
+            input.documents = [doc.text for doc in retrieved_docs]
+            result = input
+
+    # if ARANGO_GRAPH_NAME:
+    #     # TODO: Sample neighborhood from the graph?
+    #     retrieved_docs_keys = [doc.id for doc in retrieved_docs]
+
+    #     query = """
+    #         FOR doc IN @@collection
+    #             FILTER doc._key IN @keys
+
+    #             FOR v, e IN 1..1 ANY doc GRAPH @graph
+    #                 RETURN ?
+    #     """
+
+    #     pass
+
+    statistics_dict["opea_service@retriever_arangodb"].append_latency(time.time() - start, None)
+
+    if logflag:
+        logger.info(result)
+
+    return result
+
+
+if __name__ == "__main__":
+
+    if not ARANGO_EMBED_DIMENSION:
+        raise ValueError("EMBED_DIMENSION must specified in advance.")
+
+    if OPENAI_API_KEY and OPENAI_EMBED_MODEL:
+        # Use OpenAI embeddings
+        embeddings = OpenAIEmbeddings(model=OPENAI_EMBED_MODEL, dimensions=ARANGO_EMBED_DIMENSION)
+
+    elif EMBED_ENDPOINT and HUGGINGFACEHUB_API_TOKEN:
+        # create embeddings using TEI endpoint service
+        embeddings = HuggingFaceHubEmbeddings(model=EMBED_ENDPOINT, huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN)
+    else:
+        # create embeddings using local embedding model
+        embeddings = HuggingFaceBgeEmbeddings(model_name=EMBED_MODEL)
+
+    client = ArangoClient(hosts=ARANGO_URL)
+    sys_db = client.db(name="_system", username=ARANGO_USERNAME, password=ARANGO_PASSWORD, verify=True)
+
+    if not sys_db.has_database(ARANGO_DB_NAME):
+        sys_db.create_database(ARANGO_DB_NAME)
+
+    db = client.db(name=ARANGO_DB_NAME, username=ARANGO_USERNAME, password=ARANGO_PASSWORD, verify=True)
+
+    vector_db = ArangoVector(
+        embedding=embeddings,
+        embedding_dimension=ARANGO_EMBED_DIMENSION,
+        database=db,
+        collection_name=ARANGO_COLLECTION_NAME,
+        embedding_field=ARANGO_EMBBEDDING_FIELD,
+        text_field=ARANGO_TEXT_FIELD,
+        distance_strategy=ARANGO_DISTANCE_STRATEGY,
+        num_centroids=ARANGO_NUM_CENTROIDS,
+    )
+
+    opea_microservices["opea_service@retriever_arangodb"].start()
diff --git a/tests/retrievers/test_retrievers_arango_langchain.sh b/tests/retrievers/test_retrievers_arango_langchain.sh
new file mode 100644
index 000000000..e6a90786a
--- /dev/null
+++ b/tests/retrievers/test_retrievers_arango_langchain.sh
@@ -0,0 +1,99 @@
+#!/bin/bash
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+set -x
+
+WORKPATH=$(dirname "$PWD")
+LOG_PATH="$WORKPATH/tests"
+ip_address=$(hostname -I | awk '{print $1}')
+
+function build_docker_images() {
+    cd $WORKPATH
+    docker run -d -p 7474:7474 -p 7687:7687 -v ./data:/data -v ./plugins:/plugins --name test-comps-arango-apoc1 -e ARANGO_AUTH=arango/password -e ARANGO_PLUGINS=\[\"apoc\"\] arango:latest
+    sleep 30s
+
+    docker build --no-cache -t opea/retriever-arango:comps --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/retrievers/arango/langchain/Dockerfile .
+    if [ $? -ne 0 ]; then
+        echo "opea/retriever-arango built fail"
+        exit 1
+    else
+        echo "opea/retriever-arango built successful"
+    fi
+}
+
+function start_service() {
+    # tei endpoint
+    tei_endpoint=5434
+    model="BAAI/bge-base-en-v1.5"
+    docker run -d --name="test-comps-retriever-arango-tei-endpoint" -p $tei_endpoint:80 -v ./data:/data --pull always ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 --model-id $model
+    sleep 30s
+    export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:${tei_endpoint}"
+
+    # Arango retriever
+    export ARANGO_URL="http://${ip_address}:8529"
+    export ARANGO_USERNAME="root"
+    export ARANGO_PASSWORD="test"
+    retriever_port=5435
+    # unset http_proxy
+    export no_proxy="localhost,127.0.0.1,"${ip_address}
+    docker run -d --name="test-comps-retriever-arango-server" -p ${retriever_port}:7000 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e ARANGO_URL="http://${ip_address}:8529" -e ARANGO_USERNAME="root" -e ARANGO_PASSWORD="test" opea/retriever-arango:comps
+
+    sleep 1m
+}
+
+function validate_microservice() {
+    retriever_port=5435
+    export PATH="${HOME}/miniforge3/bin:$PATH"
+    source activate
+    URL="http://${ip_address}:$retriever_port/v1/retrieval"
+
+    test_embedding=$(python -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
+
+    HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" -X POST -d "{\"text\":\"test\",\"embedding\":${test_embedding}}" -H 'Content-Type: application/json' "$URL")
+    if [ "$HTTP_STATUS" -eq 200 ]; then
+        echo "[ retriever ] HTTP status is 200. Checking content..."
+        local CONTENT=$(curl -s -X POST -d "{\"text\":\"test\",\"embedding\":${test_embedding}}" -H 'Content-Type: application/json' "$URL" | tee ${LOG_PATH}/retriever.log)
+
+        if echo "$CONTENT" | grep -q "retrieved_docs"; then
+            echo "[ retriever ] Content is as expected."
+        else
+            echo "[ retriever ] Content does not match the expected result: $CONTENT"
+            docker logs test-comps-retriever-arango-server >> ${LOG_PATH}/retriever.log
+            docker logs test-comps-retriever-arango-tei-endpoint >> ${LOG_PATH}/tei.log
+            exit 1
+        fi
+    else
+        echo "[ retriever ] HTTP status is not 200. Received status was $HTTP_STATUS"
+        docker logs test-comps-retriever-arango-server >> ${LOG_PATH}/retriever.log
+        docker logs test-comps-retriever-arango-tei-endpoint >> ${LOG_PATH}/tei.log
+        exit 1
+    fi
+}
+
+function stop_docker() {
+    cid_retrievers=$(docker ps -aq --filter "name=test-comps-retriever-arango*")
+    if [[ ! -z "$cid_retrievers" ]]; then
+        docker stop $cid_retrievers && docker rm $cid_retrievers && sleep 1s
+    fi
+    cid_db=$(docker ps -aq --filter "name=test-comps-arango-apoc1")
+    if [[ ! -z "$cid_retrievers" ]]; then
+        docker stop $cid_retrievers && docker rm $cid_retrievers && sleep 1s
+    fi
+}
+
+function main() {
+
+    stop_docker
+
+    build_docker_images
+    start_service
+
+    validate_microservice
+
+    stop_docker
+    echo y | docker system prune
+
+}
+
+main