Skip to content

Commit

Permalink
Add knowledge graph components (#171)
Browse files Browse the repository at this point in the history 
* enable ragas (#129)

Signed-off-by: XuhuiRen <xuhui.ren@intel.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* Fix RAG performance issues (#132)

* Fix RAG performance issues

Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* add microservice level perf statistics (#135)

* add statistics

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* Add More Contents to the Table of MicroService (#141)

* Add More Contents to the Table MicroService

Signed-off-by: zehao-intel <zehao.huang@intel.com>

* reorder

Signed-off-by: zehao-intel <zehao.huang@intel.com>

* Update README.md

* refine structure

Signed-off-by: zehao-intel <zehao.huang@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix model

Signed-off-by: zehao-intel <zehao.huang@intel.com>

* refine table

Signed-off-by: zehao-intel <zehao.huang@intel.com>

* put llm to the ground

Signed-off-by: zehao-intel <zehao.huang@intel.com>

---------

Signed-off-by: zehao-intel <zehao.huang@intel.com>
Co-authored-by: Sihan Chen <39623753+Spycsh@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* Use common security content for OPEA projects (#151)

* add python coverage

Signed-off-by: chensuyue <suyue.chen@intel.com>

* docs update

Signed-off-by: chensuyue <suyue.chen@intel.com>

* Revert "add python coverage"

This reverts commit 69615b1.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Signed-off-by: chensuyue <suyue.chen@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* Enable vLLM Gaudi support for LLM service based on officially habana vllm release (#137)

Signed-off-by: tianyil1 <tianyi.liu@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* add knowledge graph

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* knowledge graph microservice update

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Support Dataprep Microservice with Llama Index (#154)

* move file to langchain folder

Signed-off-by: letonghan <letong.han@intel.com>

* support dataprep with llama_index

Signed-off-by: letonghan <letong.han@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* add e2e test script

Signed-off-by: letonghan <letong.han@intel.com>

* update test script name

Signed-off-by: letonghan <letong.han@intel.com>

---------

Signed-off-by: letonghan <letong.han@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* Support Embedding Microservice with Llama Index (#150)

* fix stream=false doesn't work issue

Signed-off-by: letonghan <letong.han@intel.com>

* support embedding comp with llama_index

Signed-off-by: letonghan <letong.han@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Add More Contents to the Table of MicroService (#141)

* Add More Contents to the Table MicroService

Signed-off-by: zehao-intel <zehao.huang@intel.com>

* reorder

Signed-off-by: zehao-intel <zehao.huang@intel.com>

* Update README.md

* refine structure

Signed-off-by: zehao-intel <zehao.huang@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix model

Signed-off-by: zehao-intel <zehao.huang@intel.com>

* refine table

Signed-off-by: zehao-intel <zehao.huang@intel.com>

* put llm to the ground

Signed-off-by: zehao-intel <zehao.huang@intel.com>

---------

Signed-off-by: zehao-intel <zehao.huang@intel.com>
Co-authored-by: Sihan Chen <39623753+Spycsh@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* Use common security content for OPEA projects (#151)

* add python coverage

Signed-off-by: chensuyue <suyue.chen@intel.com>

* docs update

Signed-off-by: chensuyue <suyue.chen@intel.com>

* Revert "add python coverage"

This reverts commit 69615b1.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Signed-off-by: chensuyue <suyue.chen@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* Enable vLLM Gaudi support for LLM service based on officially habana vllm release (#137)

Signed-off-by: tianyil1 <tianyi.liu@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* support embedding comp with llama_index

Signed-off-by: letonghan <letong.han@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* add test script for embedding llama_inde

Signed-off-by: letonghan <letong.han@intel.com>

* remove conflict requirements

Signed-off-by: letonghan <letong.han@intel.com>

* update test script

Signed-off-by: letonghan <letong.han@intel.com>

* udpate

Signed-off-by: letonghan <letong.han@intel.com>

* update

Signed-off-by: letonghan <letong.han@intel.com>

* update

Signed-off-by: letonghan <letong.han@intel.com>

* fix ut issue

Signed-off-by: letonghan <letong.han@intel.com>

---------

Signed-off-by: letonghan <letong.han@intel.com>
Signed-off-by: zehao-intel <zehao.huang@intel.com>
Signed-off-by: chensuyue <suyue.chen@intel.com>
Signed-off-by: tianyil1 <tianyi.liu@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: zehao-intel <zehao.huang@intel.com>
Co-authored-by: Sihan Chen <39623753+Spycsh@users.noreply.github.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>
Co-authored-by: Tianyi Liu <tianyi.liu@intel.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* Support Ollama microservice (#142)

* Add Ollama Support

Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* Fix dataprep microservice path issue (#163)

Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* update CI to support dataprep_redis path level change (#155)

Signed-off-by: chensuyue <suyue.chen@intel.com>
Signed-off-by: letonghan <letong.han@intel.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* Add Gateway for Translation (#169)

* add translation gateway

Signed-off-by: zehao-intel <zehao.huang@intel.com>

* fix import

Signed-off-by: zehao-intel <zehao.huang@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Signed-off-by: zehao-intel <zehao.huang@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* Update LLM readme (#172)

* Update LLM readme

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

* update readme

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

* update tgi readme

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

* rollback requirements.txt

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* add milvus microservice (#158)

* Use common security content for OPEA projects (#151)

* add python coverage

Signed-off-by: chensuyue <suyue.chen@intel.com>

* docs update

Signed-off-by: chensuyue <suyue.chen@intel.com>

* Revert "add python coverage"

This reverts commit 69615b1.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Signed-off-by: chensuyue <suyue.chen@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: jinjunzh <jasper.zhu@intel.com>

* add milvus microservice

Signed-off-by: jinjunzh <jasper.zhu@intel.com>

* fix the typo

Signed-off-by: jinjunzh <jasper.zhu@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Signed-off-by: jinjunzh <jasper.zhu@intel.com>

---------

Signed-off-by: chensuyue <suyue.chen@intel.com>
Signed-off-by: jinjunzh <jasper.zhu@intel.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* enable python coverage (#149)

Signed-off-by: Sun, Xuehao <xuehao.sun@intel.com>
Signed-off-by: chensuyue <suyue.chen@intel.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* Add Ray version for multi file process (#119)

* add ray version document to redis

Signed-off-by: Chendi Xue <chendi.xue@intel.com>

* update test

Signed-off-by: Chendi Xue <chendi.xue@intel.com>

* Add test

Signed-off-by: Chendi Xue <chendi.xue@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Add TIMEOUT in container environment and return status

Signed-off-by: Chendi Xue <chendi.xue@intel.com>

* rebase on new folder layout

Signed-off-by: Chendi Xue <chendi.xue@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* Add codecov (#178)

Signed-off-by: Sun, Xuehao <xuehao.sun@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* Rename lm-eval folder to utils/lm-eval (#179)

Signed-off-by: changwangss <chang1.wang@intel.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* Support rerank and retrieval of RAG OPT (#164)

* supported bce model for rerank.

Signed-off-by: Xinyu Ye <xinyu.ye@intel.com>

* change folder

Signed-off-by: Xinyu Ye <xinyu.ye@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* change path in test file.

Signed-off-by: Xinyu Ye <xinyu.ye@intel.com>

---------

Signed-off-by: Xinyu Ye <xinyu.ye@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* Support vLLM XFT LLM microservice (#174)

* Support vLLM XFT serving

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix access vllm issue

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* add permission for run.sh

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

* add readme

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix proxy issue

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

---------

Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* Update Dataprep Microservice README (#173)

* update dataprep readme

Signed-off-by: letonghan <letong.han@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Signed-off-by: letonghan <letong.han@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* fixed milvus port conflict issues during deployment (#183)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fixed milvus port conflict issues during deployment

* align port for unified retrieval microservice

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* remove

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* remove hard address

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* update readme

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* add example data and ingestion

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* fix typ

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Fix dataprep timeout issue (#203)

Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* Add a new embedding MosecEmbedding (#182)

* Add a new embedding MosecEmbedding.

Signed-off-by: Jincheng Miao <jincheng.miao@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Signed-off-by: Jincheng Miao <jincheng.miao@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* expand timeout for microservice test (#208)

Signed-off-by: chensuyue <suyue.chen@intel.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* fix typo

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* fix requirement

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Signed-off-by: XuhuiRen <xuhui.ren@intel.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Signed-off-by: zehao-intel <zehao.huang@intel.com>
Signed-off-by: chensuyue <suyue.chen@intel.com>
Signed-off-by: tianyil1 <tianyi.liu@intel.com>
Signed-off-by: letonghan <letong.han@intel.com>
Signed-off-by: jinjunzh <jasper.zhu@intel.com>
Signed-off-by: Sun, Xuehao <xuehao.sun@intel.com>
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: changwangss <chang1.wang@intel.com>
Signed-off-by: Xinyu Ye <xinyu.ye@intel.com>
Signed-off-by: Jincheng Miao <jincheng.miao@intel.com>
Co-authored-by: XuhuiRen <44249229+XuhuiRen@users.noreply.github.com>
Co-authored-by: lvliang-intel <liang1.lv@intel.com>
Co-authored-by: Sihan Chen <39623753+Spycsh@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: zehao-intel <zehao.huang@intel.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>
Co-authored-by: Tianyi Liu <tianyi.liu@intel.com>
Co-authored-by: Letong Han <106566639+letonghan@users.noreply.github.com>
Co-authored-by: jasperzhu <jasper.zhu@intel.com>
Co-authored-by: Chendi.Xue <chendi.xue@intel.com>
Co-authored-by: Sun, Xuehao <xuehao.sun@intel.com>
Co-authored-by: Wang, Chang <491521017@qq.com>
Co-authored-by: XinyuYe-Intel <xinyu.ye@intel.com>
Co-authored-by: Jincheng Miao <jincheng.miao@intel.com>
  • Loading branch information
@XinyaoWa @XuhuiRen
@lvliang-intel @Spycsh @pre-commit-ci @zehao-intel @chensuyue @tianyil1 @letonghan @jinjunzh @xuechendi @XuehaoSun @changwangss @XinyuYe-Intel @miaojinc
15 people authored Jun 20, 2024
1 parent 23e6ed0 commit 4c0afd0
Show file tree
Hide file tree
Showing 19 changed files with 452 additions and 0 deletions.
1 change: 1 addition & 0 deletions comps/__init__.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@
TextDoc,
RAGASParams,
RAGASScores,
GraphDoc,
LVMDoc,
)

Expand Down
3 changes: 3 additions & 0 deletions comps/cores/mega/constants.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@ class ServiceType(Enum):
UNDEFINED = 10
RAGAS = 11
LVM = 12
KNOWLEDGE_GRAPH = 13


class MegaServiceEndpoint(Enum):
Expand All @@ -50,6 +51,8 @@ class MegaServiceEndpoint(Enum):
RERANKING = "/v1/reranking"
GUARDRAILS = "/v1/guardrails"
RAGAS = "/v1/ragas"
GRAPHS = "/v1/graphs"

# COMMON
LIST_SERVICE = "/v1/list_service"
LIST_PARAMETERS = "/v1/list_parameters"
Expand Down
13 changes: 13 additions & 0 deletions comps/cores/proto/docarray.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -104,6 +104,19 @@ class RAGASScores(BaseDoc):
context_precision: float


class GraphDoc(BaseDoc):
text: str
strtype: Optional[str] = Field(
description="type of input query, can be 'query', 'cypher', 'rag'",
default="query",
)
max_new_tokens: Optional[int] = Field(default=1024)
rag_index_name: Optional[str] = Field(default="rag")
rag_node_label: Optional[str] = Field(default="Task")
rag_text_node_properties: Optional[list] = Field(default=["name", "description", "status"])
rag_embedding_node_property: Optional[str] = Field(default="embedding")


class LVMDoc(BaseDoc):
image: str
prompt: str
Expand Down
146 changes: 146 additions & 0 deletions comps/knowledgegraphs/README.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,146 @@
# Knowledge Graph Microservice

This microservice, designed for efficiently handling and retrieving informantion from knowledge graph. The microservice integrates text retriever, knowledge graph quick search and LLM agent, which can be combined to enhance question answering.

The service contains three modes:

- "cypher": Query knowledge graph directly with cypher
- "rag": Apply similarity search on embeddings of knowledge graph
- "query": An LLM agent will automatically choose tools (RAG or CypherChain) to enhance the question answering

Here is the overall workflow:

![Workflow](doc/workflow.png)

A prerequisite for using this microservice is that users must have a knowledge gragh database already running, and currently we have support [Neo4J](https://neo4j.com/) for quick deployment. Users need to set the graph service's endpoint into an environment variable and microservie utilizes it for data injestion and retrieve. If user want to use "rag" and "query" mode, still need a LLM text generation service (etc., TGI, vLLM and Ray) already running.

Overall, this microservice provides efficient support for applications related with graph dataset, especially for answering multi-part questions, or any other conditions including comples relationship between entities.

# 🚀1. Start Microservice with Docker

## 1.1 Setup Environment Variables

```bash
export NEO4J_ENDPOINT="neo4j://${your_ip}:7687"
export NEO4J_USERNAME="neo4j"
export NEO4J_PASSWORD=${define_a_password}
export HUGGINGFACEHUB_API_TOKEN=${your_huggingface_api_token}
export LLM_ENDPOINT="http://${your_ip}:8080"
export LLM_MODEL="meta-llama/Llama-2-7b-hf"
export AGENT_LLM="HuggingFaceH4/zephyr-7b-beta"
```

## 1.2 Start Neo4j Service

```bash
docker pull neo4j

docker run --rm \
--publish=7474:7474 --publish=7687:7687 \
--env NEO4J_AUTH=$NEO4J_USER/$NEO4J_PASSWORD \
--volume=$PWD/neo4j_data:"/data" \
--env='NEO4JLABS_PLUGINS=["apoc"]' \
neo4j
```

## 1.3 Start LLM Service for "rag"/"query" mode

You can start any LLM microserve, here we take TGI as an example.

```bash
docker run -p 8080:80 \
-v $PWD/llm_data:/data --runtime=habana \
-e HABANA_VISIBLE_DEVICES=all \
-e OMPI_MCA_btl_vader_single_copy_mechanism=none \
-e HUGGING_FACE_HUB_TOKEN=$HUGGINGFACEHUB_API_TOKEN \
--cap-add=sys_nice \
--ipc=host \
ghcr.io/huggingface/tgi-gaudi:2.0.0 \
--model-id $LLM_MODEL \
--max-input-tokens 1024 \
--max-total-tokens 2048
```

Verify LLM service.

```bash
curl $LLM_ENDPOINT/generate \
-X POST \
-d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":32}}' \
-H 'Content-Type: application/json'
```

## 1.4 Start Microservice

```bash
cd ../..
docker build -t opea/knowledge_graphs:latest \
--build-arg https_proxy=$https_proxy \
--build-arg http_proxy=$http_proxy \
-f comps/knowledgegraphs/langchain/docker/Dockerfile .

docker run --rm \
--name="knowledge-graph-server" \
-p 8060:8060 \
--ipc=host \
-e http_proxy=$http_proxy \
-e https_proxy=$https_proxy \
-e NEO4J_ENDPOINT=$NEO4J_ENDPOINT \
-e NEO4J_USERNAME=$NEO4J_USERNAME \
-e NEO4J_PASSWORD=$NEO4J_PASSWORD \
-e HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN \
-e LLM_ENDPOINT=$LLM_ENDPOINT \
opea/knowledge_graphs:latest
```

# 🚀2. Consume Knowledge Graph Service

## 2.1 Cypher mode

```bash
curl http://${your_ip}:8060/v1/graphs \
-X POST \
-d "{\"text\":\"MATCH (t:Task {status:'open'}) RETURN count(*)\",\"strtype\":\"cypher\"}" \
-H 'Content-Type: application/json'
```

Example output:
![Cypher Output](doc/output_cypher.png)

## 2.2 Rag mode

```bash
curl http://${your_ip}:8060/v1/graphs \
-X POST \
-d "{\"text\":\"How many open tickets there are?\",\"strtype\":\"rag\", \"max_new_tokens\":128}" \
-H 'Content-Type: application/json'
```

Example output:
![Cypher Output](doc/output_rag.png)

## 2.3 Query mode

First example:

```bash
curl http://${your_ip}:8060/v1/graphs \
-X POST \
-d "{\"text\":\"Which tasks have optimization in their description?\",\"strtype\":\"query\"}" \
-H 'Content-Type: application/json'
```

Example output:
![Cypher Output](doc/output_query1.png)

Second example:

```bash
curl http://${your_ip}:8060/v1/graphs \
-X POST \
-d "{\"text\":\"Which team is assigned to maintain PaymentService?\",\"strtype\":\"query\"}" \
-H 'Content-Type: application/json'
```

Example output:
![Cypher Output](doc/output_query2.png)
2 changes: 2 additions & 0 deletions comps/knowledgegraphs/__init__.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
7 changes: 7 additions & 0 deletions comps/knowledgegraphs/build_docker.sh
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

docker build -t opea/knowledge_graphs:latest \
--build-arg https_proxy=$https_proxy \
--build-arg http_proxy=$http_proxy \
-f comps/knowledgegraphs/langchain/docker/Dockerfile .
Binary file added comps/knowledgegraphs/doc/output_cypher.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added comps/knowledgegraphs/doc/output_query1.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added comps/knowledgegraphs/doc/output_query2.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added comps/knowledgegraphs/doc/output_rag.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added comps/knowledgegraphs/doc/workflow.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Empty file added comps/knowledgegraphs/langchain/README.md
View file
Empty file.
2 changes: 2 additions & 0 deletions comps/knowledgegraphs/langchain/__init__.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
3 changes: 3 additions & 0 deletions comps/knowledgegraphs/langchain/data/microservices.json
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
{
"query": "MERGE (catalog:Microservice {name: 'CatalogService', technology: 'Java'}) MERGE (order:Microservice {name: 'OrderService', technology: 'Python'}) MERGE (user:Microservice {name: 'UserService', technology: 'Go'}) MERGE (payment:Microservice {name: 'PaymentService', technology: 'Node.js'}) MERGE (inventory:Microservice {name: 'InventoryService', technology: 'Java'}) MERGE (shipping:Microservice {name: 'ShippingService', technology: 'Python'}) MERGE (review:Microservice {name: 'ReviewService', technology: 'Go'}) MERGE (recommendation:Microservice {name: 'RecommendationService', technology: 'Node.js'}) MERGE (auth:Microservice {name: 'AuthService', technology: 'Node.js'}) MERGE (db:Microservice {name: 'Database', technology: 'SQL'}) MERGE (cache:Microservice {name: 'Cache', technology: 'In-memory'}) MERGE (mq:Microservice {name: 'MessageQueue', technology: 'Pub-Sub'}) MERGE (api:Microservice {name: 'ExternalAPI', technology: 'REST'}) MERGE (bugFixCatalog:Task {name: 'BugFix', description: 'Address and resolve a critical bug impacting the CatalogService, affecting the user interface and experience, and hampering the overall performance and responsiveness of the service.', status: 'open'}) MERGE (featureAddOrder:Task {name: 'FeatureAdd', description: 'Implement a new feature in OrderService to facilitate bulk orders, ensuring the features seamless integration with existing functionalities and maintaining the overall stability and performance of the service.', status: 'in progress'}) MERGE (refactorUser:Task {name: 'Refactor', description: 'Refactor the UserService codebase to enhance its readability, maintainability, and scalability, focusing primarily on modularization and optimization of existing functionalities.', status: 'completed'}) MERGE (optimizePayment:Task {name: 'Optimize', description: 'Optimize PaymentService by refining the transaction processing logic, reducing the service’s latency, and improving its reliability and efficiency in handling transactions.', status: 'open'}) MERGE (updateInventory:Task {name: 'Update', description: 'Update InventoryService to include real-time stock updates, ensuring accurate reflection of the inventory levels and aiding in the efficient management of stock.', status: 'in progress'}) MERGE (enhanceShipping:Task {name: 'Enhance', description: 'Enhance the ShippingService by integrating a new shipping partner API, thereby expanding the shipping options available to the customers and improving the overall delivery experience.', status: 'completed'}) MERGE (reviewFix:Task {name: 'ReviewFix', description: 'Rectify a recurring issue in ReviewService affecting the retrieval of user reviews, by refining the service’s logic and improving its efficiency in handling and displaying user reviews.', status: 'open'}) MERGE (recommendationFeature:Task {name: 'RecommendationFeature', description: 'Add a new feature to RecommendationService to provide more personalized and accurate product recommendations to the users, leveraging user behavior and preference data.', status: 'in progress'}) MERGE (optimizeAuth:Task {name: 'Optimize', description: 'Enhance AuthService’s performance and security by optimizing the authentication mechanisms and implementing additional security measures to safeguard user information.', status: 'open'}) MERGE (newTask:Task {name: 'ImproveSecurity', description: 'Enhance the security of microservices by implementing advanced encryption and securing endpoints.', status: 'open'}) MERGE (teamA:Team {name: 'TeamA'}) MERGE (teamB:Team {name: 'TeamB'}) MERGE (teamC:Team {name: 'TeamC'}) MERGE (teamD:Team {name: 'TeamD'}) MERGE (alice:Person {name: 'Alice'}) MERGE (bob:Person {name: 'Bob'}) MERGE (charlie:Person {name: 'Charlie'}) MERGE (diana:Person {name: 'Diana'}) MERGE (eva:Person {name: 'Eva'}) MERGE (frank:Person {name: 'Frank'}) MERGE (catalog)-[:DEPENDS_ON]->(db) MERGE (order)-[:DEPENDS_ON]->(db) MERGE (user)-[:DEPENDS_ON]->(db) MERGE (payment)-[:DEPENDS_ON]->(db) MERGE (inventory)-[:DEPENDS_ON]->(db) MERGE (shipping)-[:DEPENDS_ON]->(mq) MERGE (review)-[:DEPENDS_ON]->(cache) MERGE (recommendation)-[:DEPENDS_ON]->(api) MERGE (auth)-[:DEPENDS_ON]->(db) MERGE (order)-[:DEPENDS_ON]->(inventory) MERGE (order)-[:DEPENDS_ON]->(shipping) MERGE (order)-[:DEPENDS_ON]->(payment) MERGE (catalog)-[:DEPENDS_ON]->(review) MERGE (catalog)-[:DEPENDS_ON]->(recommendation) MERGE (user)-[:DEPENDS_ON]->(auth) MERGE (payment)-[:DEPENDS_ON]->(auth) MERGE (shipping)-[:DEPENDS_ON]->(auth) MERGE (catalog)-[:MAINTAINED_BY]->(teamA) MERGE (order)-[:MAINTAINED_BY]->(teamB) MERGE (user)-[:MAINTAINED_BY]->(teamC) MERGE (payment)-[:MAINTAINED_BY]->(teamD) MERGE (inventory)-[:MAINTAINED_BY]->(teamA) MERGE (shipping)-[:MAINTAINED_BY]->(teamB) MERGE (review)-[:MAINTAINED_BY]->(teamC) MERGE (recommendation)-[:MAINTAINED_BY]->(teamD) MERGE (auth)-[:MAINTAINED_BY]->(teamA) MERGE (bugFixCatalog)-[:ASSIGNED_TO]->(teamA) MERGE (featureAddOrder)-[:ASSIGNED_TO]->(teamB) MERGE (refactorUser)-[:ASSIGNED_TO]->(teamC) MERGE (optimizePayment)-[:ASSIGNED_TO]->(teamD) MERGE (updateInventory)-[:ASSIGNED_TO]->(teamA) MERGE (enhanceShipping)-[:ASSIGNED_TO]->(teamB) MERGE (reviewFix)-[:ASSIGNED_TO]->(teamC) MERGE (recommendationFeature)-[:ASSIGNED_TO]->(teamD) MERGE (optimizeAuth)-[:ASSIGNED_TO]->(teamA) MERGE (bugFixCatalog)-[:LINKED_TO]->(catalog) MERGE (featureAddOrder)-[:LINKED_TO]->(order) MERGE (refactorUser)-[:LINKED_TO]->(user) MERGE (optimizePayment)-[:LINKED_TO]->(payment) MERGE (updateInventory)-[:LINKED_TO]->(inventory) MERGE (enhanceShipping)-[:LINKED_TO]->(shipping) MERGE (reviewFix)-[:LINKED_TO]->(review) MERGE (recommendationFeature)-[:LINKED_TO]->(recommendation) MERGE (optimizeAuth)-[:LINKED_TO]->(auth) MERGE (alice)-[:PART_OF]->(teamA) MERGE (bob)-[:PART_OF]->(teamB) MERGE (charlie)-[:PART_OF]->(teamC) MERGE (diana)-[:PART_OF]->(teamD) MERGE (eva)-[:PART_OF]->(teamA) MERGE (frank)-[:PART_OF]->(teamB) MERGE (newTask)-[:LINKED_TO]->(auth) MERGE (newTask)-[:ASSIGNED_TO]->(teamA)"
}
27 changes: 27 additions & 0 deletions comps/knowledgegraphs/langchain/docker/Dockerfile
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

FROM langchain/langchain:latest

RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
libgl1-mesa-glx \
libjemalloc-dev \
vim

RUN useradd -m -s /bin/bash user && \
mkdir -p /home/user && \
chown -R user /home/user/

COPY comps /home/user/comps

USER user

RUN pip install --no-cache-dir --upgrade pip && \
pip install --no-cache-dir -r /home/user/comps/knowledgegraphs/requirements.txt

ENV PYTHONPATH=$PYTHONPATH:/home/user

WORKDIR /home/user/comps/knowledgegraphs/langchain

ENTRYPOINT ["python", "knowledge_graph.py"]
21 changes: 21 additions & 0 deletions comps/knowledgegraphs/langchain/ingest.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

import json
import os

from langchain_community.graphs import Neo4jGraph

neo4j_endpoint = os.getenv("NEO4J_ENDPOINT", "neo4j://localhost:7687")
neo4j_username = os.getenv("NEO4J_USERNAME", "neo4j")
neo4j_password = os.getenv("NEO4J_PASSWORD", "neo4j")
graph = Neo4jGraph(url=neo4j_endpoint, username=neo4j_username, password=neo4j_password)

# remove all nodes
graph.query("MATCH (n) DETACH DELETE n")

# ingest
import_query = json.load(open("data/microservices.json", "r"))["query"]
graph.query(import_query)
print("Total nodes: ", graph.query("MATCH (n) RETURN count(n)"))
print("Total edges: ", graph.query("MATCH ()-->() RETURN count(*)"))
Loading

0 comments on commit 4c0afd0

Please sign in to comment.