diff --git a/comps/cores/mega/README.md b/comps/cores/mega/README.md
deleted file mode 100644
index e69de29bb2..0000000000
diff --git a/comps/knowledgegraphs/langchain/README.md b/comps/knowledgegraphs/langchain/README.md
deleted file mode 100755
index e69de29bb2..0000000000
diff --git a/comps/llms/summarization/tgi/README.md b/comps/llms/summarization/tgi/README.md
index e69de29bb2..9e5858b4b7 100644
--- a/comps/llms/summarization/tgi/README.md
+++ b/comps/llms/summarization/tgi/README.md
@@ -0,0 +1,96 @@
+# Document Summary TGI Microservice
+
+In this microservice, we utilize LangChain to implement summarization strategies and facilitate LLM inference using Text Generation Inference on Intel Xeon and Gaudi2 processors.
+[Text Generation Inference](https://github.com/huggingface/text-generation-inference) (TGI) is a toolkit for deploying and serving Large Language Models (LLMs). TGI enables high-performance text generation for the most popular open-source LLMs, including Llama, Falcon, StarCoder, BLOOM, GPT-NeoX, and more.
+
+# 🚀1. Start Microservice with Python (Option 1)
+
+To start the LLM microservice, you need to install python packages first.
+
+## 1.1 Install Requirements
+
+```bash
+pip install -r requirements.txt
+```
+
+## 1.2 Start LLM Service
+
+```bash
+export HF_TOKEN=${your_hf_api_token}
+docker run -p 8008:80 -v ./data:/data --name llm-docsum-tgi --shm-size 1g ghcr.io/huggingface/text-generation-inference:2.1.0 --model-id ${your_hf_llm_model}
+```
+
+## 1.3 Verify the TGI Service
+
+```bash
+curl http://${your_ip}:8008/generate \
+  -X POST \
+  -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' \
+  -H 'Content-Type: application/json'
+```
+
+## 1.4 Start LLM Service with Python Script
+
+```bash
+export TGI_LLM_ENDPOINT="http://${your_ip}:8008"
+python llm.py
+```
+
+# 🚀2. Start Microservice with Docker (Option 2)
+
+If you start an LLM microservice with docker, the `docker_compose_llm.yaml` file will automatically start a TGI/vLLM service with docker.
+
+## 2.1 Setup Environment Variables
+
+In order to start TGI and LLM services, you need to setup the following environment variables first.
+
+```bash
+export HF_TOKEN=${your_hf_api_token}
+export TGI_LLM_ENDPOINT="http://${your_ip}:8008"
+export LLM_MODEL_ID=${your_hf_llm_model}
+```
+
+## 2.2 Build Docker Image
+
+```bash
+cd ../../
+docker build -t opea/llm-docsum-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/summarization/tgi/Dockerfile .
+```
+
+To start a docker container, you have two options:
+
+- A. Run Docker with CLI
+- B. Run Docker with Docker Compose
+
+You can choose one as needed.
+
+## 2.3 Run Docker with CLI (Option A)
+
+```bash
+docker run -d --name="llm-docsum-tgi-server" -p 9000:9000 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e TGI_LLM_ENDPOINT=$TGI_LLM_ENDPOINT -e HF_TOKEN=$HF_TOKEN opea/llm-docsum-tgi:latest
+```
+
+## 2.4 Run Docker with Docker Compose (Option B)
+
+```bash
+docker compose -f docker_compose_llm.yaml up -d
+```
+
+# 🚀3. Consume LLM Service
+
+## 3.1 Check Service Status
+
+```bash
+curl http://${your_ip}:9000/v1/health_check\
+  -X GET \
+  -H 'Content-Type: application/json'
+```
+
+## 3.2 Consume LLM Service
+
+```bash
+curl http://${your_ip}:9000/v1/chat/docsum \
+  -X POST \
+  -d '{"query":"Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."}' \
+  -H 'Content-Type: application/json'
+```
diff --git a/comps/llms/summarization/tgi/docker_compose_llm.yaml b/comps/llms/summarization/tgi/docker_compose_llm.yaml
index 41ae5d0768..2b517333e1 100644
--- a/comps/llms/summarization/tgi/docker_compose_llm.yaml
+++ b/comps/llms/summarization/tgi/docker_compose_llm.yaml
@@ -5,7 +5,7 @@ version: "3.8"
 
 services:
   tgi_service:
-    image: ghcr.io/huggingface/text-generation-inference:1.4
+    image: ghcr.io/huggingface/text-generation-inference:2.1.0
     container_name: tgi-service
     ports:
       - "8008:80"
@@ -16,8 +16,8 @@ services:
     shm_size: 1g
     command: --model-id ${LLM_MODEL_ID}
   llm:
-    image: opea/gen-ai-comps:llm-tgi-server
-    container_name: llm-tgi-server
+    image: opea/llm-docsum-tgi:latest
+    container_name: llm-docsum-tgi-server
     ports:
       - "9000:9000"
     ipc: host
@@ -27,7 +27,6 @@ services:
       https_proxy: ${https_proxy}
       TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
       HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
-      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
     restart: unless-stopped
 
 networks:
diff --git a/comps/vectorstores/langchain/chroma/README.md b/comps/vectorstores/langchain/chroma/README.md
index e69de29bb2..d7399b8fb7 100644
--- a/comps/vectorstores/langchain/chroma/README.md
+++ b/comps/vectorstores/langchain/chroma/README.md
@@ -0,0 +1,36 @@
+# Introduction
+
+Chroma is a AI-native open-source vector database focused on developer productivity and happiness. Chroma is licensed under Apache 2.0. Chroma runs in various modes, we can deploy it as a server running your local machine or in the cloud.
+
+# Getting Started
+
+## Start Chroma Server
+
+To start the Chroma server on your local machine, follow these steps:
+
+```bash
+git clone https://github.com/chroma-core/chroma.git
+cd chroma
+docker compose up -d
+```
+
+## Start Log Output
+
+Upon starting the server, you should see log outputs similar to the following:
+
+```log
+server-1  | Starting 'uvicorn chromadb.app:app' with args: --workers 1 --host 0.0.0.0 --port 8000 --proxy-headers --log-config chromadb/log_config.yml --timeout-keep-alive 30
+server-1  | INFO:     [02-08-2024 07:03:19] Set chroma_server_nofile to 65536
+server-1  | INFO:     [02-08-2024 07:03:19] Anonymized telemetry enabled. See                     https://docs.trychroma.com/telemetry for more information.
+server-1  | DEBUG:    [02-08-2024 07:03:19] Starting component System
+server-1  | DEBUG:    [02-08-2024 07:03:19] Starting component OpenTelemetryClient
+server-1  | DEBUG:    [02-08-2024 07:03:19] Starting component SqliteDB
+server-1  | DEBUG:    [02-08-2024 07:03:19] Starting component QuotaEnforcer
+server-1  | DEBUG:    [02-08-2024 07:03:19] Starting component Posthog
+server-1  | DEBUG:    [02-08-2024 07:03:19] Starting component LocalSegmentManager
+server-1  | DEBUG:    [02-08-2024 07:03:19] Starting component SegmentAPI
+server-1  | INFO:     [02-08-2024 07:03:19] Started server process [1]
+server-1  | INFO:     [02-08-2024 07:03:19] Waiting for application startup.
+server-1  | INFO:     [02-08-2024 07:03:19] Application startup complete.
+server-1  | INFO:     [02-08-2024 07:03:19] Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
+```