Change neo4j Bolt default PORT from 7687 to $NEO4J_PORT2 (opea-projec…

…t#1292) * Change neo4j Bolt default PORT from 7687 to -configured the port in neo4j compose.yaml to use variable value -made all corresponding changes in neo4j dataprep and retriever components and test scripts to use env variable instead of default port value. Signed-off-by: rbrugaro <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * missing positional arg in milvus dataprep Signed-off-by: rbrugaro <[email protected]> * remove redundance in stop_docker Signed-off-by: rbrugaro <[email protected]> * resolve retriever to neo4j connectivity issue bad URL Signed-off-by: rbrugaro <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * set neo4j ports to neo4j defaults and fix environment variables in READMEs Signed-off-by: rbrugaro <[email protected]> --------- Signed-off-by: rbrugaro <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Liang Lv <[email protected]>
arangoml · Feb 20, 2025 · 135ef91 · 135ef91
1 parent a4f6af1
commit 135ef91
Show file tree

Hide file tree

Showing 8 changed files with 49 additions and 22 deletions.
diff --git a/comps/dataprep/src/README_neo4j_llamaindex.md b/comps/dataprep/src/README_neo4j_llamaindex.md
@@ -19,22 +19,30 @@ export host_ip=${your_hostname IP}  # local IP
 export no_proxy=$no_proxy,${host_ip}  # important to add {host_ip} for containers communication
 export http_proxy=${your_http_proxy}
 export https_proxy=${your_http_proxy}
-export NEO4J_URI=${your_neo4j_url}
 export NEO4J_USERNAME=${your_neo4j_username}
 export NEO4J_PASSWORD=${your_neo4j_password}  # should match what was used in NEO4J_AUTH when running the neo4j-apoc
 export PYTHONPATH=${path_to_comps}
 export OPENAI_KEY=${your_openai_api_key}  # optional, when not provided will use open models TGI/TEI
 export HUGGINGFACEHUB_API_TOKEN=${your_hf_token}
+export DATA_PATH=${host_path_to_volume_mnt}
 
 # set additional environment settings
 export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+export EMBED_MODEL=${EMBEDDING_MODEL_ID}
 export OPENAI_EMBEDDING_MODEL="text-embedding-3-small"
-export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
+export LLM_MODEL_ID="meta-llama/Meta-Llama-3.1-8B-Instruct"
+export MAX_INPUT_TOKENS=4096
+export MAX_TOTAL_TOKENS=8192
 export OPENAI_LLM_MODEL="gpt-4o"
-export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"
-export TGI_LLM_ENDPOINT="http://${host_ip}:6005"
-export NEO4J_URL="bolt://${host_ip}:7687"
-export NEO4J_USERNAME=neo4j
+export TEI_EMBEDDER_PORT=11633
+export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:${TEI_EMBEDDER_PORT}"
+export LLM_ENDPOINT_PORT=11634
+export TGI_LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
+export NEO4J_AUTH="${NEO4J_USERNAME}/${NEO4J_PASSWORD}"
+export NEO4J_PORT1=7474   # 11631
+export NEO4J_PORT2=7687   # 11632
+export NEO4J_URI="bolt://${host_ip}:${NEO4J_PORT2}"
+export NEO4J_URL="bolt://${host_ip}:${NEO4J_PORT2}"
 export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6004/v1/dataprep"
 export LOGFLAG=True
 ```

diff --git a/comps/dataprep/src/integrations/neo4j_llamaindex.py b/comps/dataprep/src/integrations/neo4j_llamaindex.py
@@ -60,8 +60,9 @@
 from llama_index.core.schema import BaseNode, TransformComponent
 
 host_ip = os.getenv("host_ip")
+NEO4J_PORT2 = os.getenv("NEO4J_PORT2")
 # Neo4J configuration
-NEO4J_URL = os.getenv("NEO4J_URL", f"bolt://{host_ip}:7687")
+NEO4J_URL = os.getenv("NEO4J_URL", f"bolt://{host_ip}:{NEO4J_PORT2}")
 NEO4J_USERNAME = os.getenv("NEO4J_USERNAME", "neo4j")
 NEO4J_PASSWORD = os.getenv("NEO4J_PASSWORD", "neo4jtest")
 

diff --git a/comps/retrievers/deployment/docker_compose/compose.yaml b/comps/retrievers/deployment/docker_compose/compose.yaml
@@ -67,6 +67,7 @@ services:
       EMBEDDING_MODEL_ID: ${EMBEDDING_MODEL_ID}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       NEO4J_URI: ${NEO4J_URI}
+      NEO4J_URL: ${NEO4J_URI}
       NEO4J_USERNAME: ${NEO4J_USERNAME}
       NEO4J_PASSWORD: ${NEO4J_PASSWORD}
       VDMS_USE_CLIP: 0

diff --git a/comps/retrievers/src/README_neo4j.md b/comps/retrievers/src/README_neo4j.md
@@ -44,22 +44,32 @@ export host_ip=${your_hostname IP}  # local IP
 export no_proxy=$no_proxy,${host_ip}  # important to add {host_ip} for containers communication
 export http_proxy=${your_http_proxy}
 export https_proxy=${your_http_proxy}
-export NEO4J_URI=${your_neo4j_url}
 export NEO4J_USERNAME=${your_neo4j_username}
 export NEO4J_PASSWORD=${your_neo4j_password}
 export PYTHONPATH=${path_to_comps}
 export OPENAI_KEY=${your_openai_api_key}  # optional, when not provided will use smaller models TGI/TEI
 export HUGGINGFACEHUB_API_TOKEN=${your_hf_token}
+export DATA_PATH=${host_path_to_volume_mnt}
+
 # set additional environment settings
 export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
 export OPENAI_EMBEDDING_MODEL="text-embedding-3-small"
-export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
+export LLM_MODEL_ID="meta-llama/Meta-Llama-3.1-8B-Instruct"
+export MAX_INPUT_TOKENS=4096
+export MAX_TOTAL_TOKENS=8192
 export OPENAI_LLM_MODEL="gpt-4o"
+export TEI_EMBEDDER_PORT=11633
+export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:${TEI_EMBEDDER_PORT}"
+export LLM_ENDPOINT_PORT=11634
+export TGI_LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
 export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"
 export TGI_LLM_ENDPOINT="http://${host_ip}:6005"
-export NEO4J_URL="bolt://${host_ip}:7687"
-export NEO4J_USERNAME=neo4j
+export NEO4J_PORT1=7474   # 11631
+export NEO4J_PORT2=7687   # 11632
+export NEO4J_URI="bolt://${host_ip}:${NEO4J_PORT2}"
+export NEO4J_URL="bolt://${host_ip}:${NEO4J_PORT2}"
 export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6004/v1/dataprep"
+export RETRIEVER_PORT=11635
 export LOGFLAG=True
 ```
 

diff --git a/comps/retrievers/src/integrations/config.py b/comps/retrievers/src/integrations/config.py
@@ -63,7 +63,8 @@ def get_boolean_env_var(var_name, default_value=False):
 #######################################################
 #                    Neo4j                            #
 #######################################################
-NEO4J_URL = os.getenv("NEO4J_URI", "bolt://localhost:7687")
+NEO4J_PORT2 = os.getenv("NEO4J_PORT2", "11632")
+NEO4J_URL = os.getenv("NEO4J_URI", f"bolt://localhost:{NEO4J_PORT2}")
 NEO4J_USERNAME = os.getenv("NEO4J_USERNAME", "neo4j")
 NEO4J_PASSWORD = os.getenv("NEO4J_PASSWORD", "test")
 host_ip = os.getenv("host_ip")

diff --git a/comps/third_parties/neo4j/deployment/docker_compose/compose.yaml b/comps/third_parties/neo4j/deployment/docker_compose/compose.yaml
@@ -9,10 +9,10 @@ services:
       - "${NEO4J_PORT1:-7474}:7474"
       - "${NEO4J_PORT2:-7687}:7687"
     volumes:
-        - /$HOME/neo4j/logs:/logs
-        - /$HOME/neo4j/config:/config
-        - /$HOME/neo4j/data:/data
-        - /$HOME/neo4j/plugins:/plugins
+        - ./data/neo4j/logs:/logs
+        - ./data/neo4j/config:/config
+        - ./data/neo4j/data:/data
+        - ./data/neo4j/plugins:/plugins
     ipc: host
     environment:
       - no_proxy=${no_proxy}
@@ -24,6 +24,7 @@ services:
       - NEO4J_apoc_import_file_enabled=true
       - NEO4J_apoc_import_file_use__neo4j__config=true
       - NEO4J_dbms_security_procedures_unrestricted=apoc.\*
+      - NEO4J_server_bolt_advertised__address=localhost:${NEO4J_PORT2}
     restart: always
     healthcheck:
       test: wget http://localhost:7474 || exit 1

diff --git a/tests/dataprep/test_dataprep_neo4j_on_intel_hpu.sh b/tests/dataprep/test_dataprep_neo4j_on_intel_hpu.sh
@@ -28,8 +28,10 @@ function build_docker_images() {
 function start_service() {
     service_name="neo4j-apoc tei-embedding-serving tgi-gaudi-server dataprep-neo4j-llamaindex"
     export host_ip=${ip_address}
+    export NEO4J_PORT1=7474   # 11631
+    export NEO4J_PORT2=7687   # 11632
     export NEO4J_AUTH="neo4j/neo4jtest"
-    export NEO4J_URL="bolt://${ip_address}:7687"
+    export NEO4J_URL="bolt://${ip_address}:${NEO4J_PORT2}"
     export NEO4J_USERNAME="neo4j"
     export NEO4J_PASSWORD="neo4jtest"
     export NEO4J_apoc_export_file_enabled=true
@@ -95,7 +97,7 @@ function validate_service() {
 function validate_microservice() {
     # validate neo4j-apoc
     validate_service \
-        "${ip_address}:7474" \
+        "${ip_address}:${NEO4J_PORT1}" \
         "200 OK" \
         "neo4j-apoc" \
         "neo4j-apoc" \

diff --git a/tests/retrievers/test_retrievers_neo4j_on_intel_hpu.sh b/tests/retrievers/test_retrievers_neo4j_on_intel_hpu.sh
@@ -50,7 +50,10 @@ function start_service() {
     export LLM_MODEL_ID="meta-llama/Meta-Llama-3.1-8B-Instruct"
     export TGI_LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
     export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6004"
-    export NEO4J_URI="bolt://${host_ip}:7687"
+    export NEO4J_PORT1=7474   # 11631
+    export NEO4J_PORT2=7687   # 11632
+    export NEO4J_URI="bolt://${host_ip}:${NEO4J_PORT2}"
+    export NEO4J_URL="bolt://${host_ip}:${NEO4J_PORT2}"
     export NEO4J_USERNAME="neo4j"
     export NEO4J_PASSWORD="neo4jtest"
     export no_proxy="localhost,127.0.0.1,"${host_ip}
@@ -64,8 +67,8 @@ function start_service() {
     # Not testing openai code path since not able to provide key for cicd
     docker run -d --name="test-comps-retrievers-neo4j-llama-index-dataprep" -p 6004:5000 -v ./data:/data --ipc=host -e TGI_LLM_ENDPOINT=$TGI_LLM_ENDPOINT \
         -e TEI_EMBEDDING_ENDPOINT=$TEI_EMBEDDING_ENDPOINT -e EMBEDDING_MODEL_ID=$EMBEDDING_MODEL_ID -e LLM_MODEL_ID=$LLM_MODEL_ID -e host_ip=$host_ip -e no_proxy=$no_proxy \
-        -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e NEO4J_URL="bolt://${host_ip}:7687" -e NEO4J_USERNAME="neo4j" \
-        -e NEO4J_PASSWORD="neo4jtest" -e HF_TOKEN=$HF_TOKEN -e MAX_INPUT_TOKENS=$MAX_INPUT_TOKENS -e LOGFLAG=True \
+        -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e NEO4J_URL="bolt://${host_ip}:${NEO4J_PORT2}" -e NEO4J_USERNAME="neo4j" \
+        -e NEO4J_PASSWORD="neo4jtest" -e NEO4J_PORT1=$NEO4J_PORT1 -e NEO4J_PORT2=$NEO4J_PORT2 -e HF_TOKEN=$HF_TOKEN -e MAX_INPUT_TOKENS=$MAX_INPUT_TOKENS -e LOGFLAG=True \
         -e DATAPREP_COMPONENT_NAME="OPEA_DATAPREP_NEO4J_LLAMAINDEX" opea/dataprep-neo4j-llamaindex:comps
 
     sleep 1m
@@ -117,7 +120,7 @@ function validate_service() {
 function validate_microservice() {
     # validate neo4j-apoc
     validate_service \
-        "${host_ip}:7474" \
+        "${host_ip}:${NEO4J_PORT1}" \
         "200 OK" \
         "neo4j-apoc" \
         "neo4j-apoc" \