Skip to content

Commit 7d6b6e2

Browse files
authored
Merge branch 'main' into suyue/cd
2 parents e8c1f7a + c50dfb2 commit 7d6b6e2

File tree

123 files changed

+5888
-1440
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

123 files changed

+5888
-1440
lines changed

.github/workflows/_helm-e2e.yml

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -134,7 +134,7 @@ jobs:
134134
CHART_NAME="${example,,}" # CodeGen
135135
echo "CHART_NAME=$CHART_NAME" >> $GITHUB_ENV
136136
echo "RELEASE_NAME=${CHART_NAME}$(date +%Y%m%d%H%M%S)" >> $GITHUB_ENV
137-
echo "NAMESPACE=${CHART_NAME}-$(date +%Y%m%d%H%M%S)" >> $GITHUB_ENV
137+
echo "NAMESPACE=${CHART_NAME}-$(head -c 4 /dev/urandom | xxd -p)" >> $GITHUB_ENV
138138
echo "ROLLOUT_TIMEOUT_SECONDS=600s" >> $GITHUB_ENV
139139
echo "TEST_TIMEOUT_SECONDS=600s" >> $GITHUB_ENV
140140
echo "KUBECTL_TIMEOUT_SECONDS=60s" >> $GITHUB_ENV
@@ -173,7 +173,7 @@ jobs:
173173
$RELEASE_NAME \
174174
oci://ghcr.io/opea-project/charts/${CHART_NAME} \
175175
--set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} \
176-
--set global.modelUseHostPath=/home/sdp/.cache/huggingface/hub \
176+
--set global.modelUseHostPath=/data2/hf_model \
177177
--set GOOGLE_API_KEY=${{ env.GOOGLE_API_KEY}} \
178178
--set GOOGLE_CSE_ID=${{ env.GOOGLE_CSE_ID}} \
179179
--set web-retriever.GOOGLE_API_KEY=${{ env.GOOGLE_API_KEY}} \

.github/workflows/dockerhub-description.yml

Lines changed: 984 additions & 0 deletions
Large diffs are not rendered by default.

.github/workflows/pr-link-path-scan.yml

Lines changed: 1 addition & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -76,13 +76,7 @@ jobs:
7676
cd ${{github.workspace}}
7777
fail="FALSE"
7878
repo_name=${{ github.event.pull_request.head.repo.full_name }}
79-
if [ "$(echo "$repo_name"|cut -d'/' -f1)" != "opea-project" ]; then
80-
owner=$(echo "${{ github.event.pull_request.head.repo.full_name }}" |cut -d'/' -f1)
81-
branch="https://github.com/$owner/GenAIExamples/tree/${{ github.event.pull_request.head.ref }}"
82-
else
83-
branch="https://github.com/opea-project/GenAIExamples/blob/${{ github.event.pull_request.head.ref }}"
84-
fi
85-
link_head="https://github.com/opea-project/GenAIExamples/blob/main"
79+
branch="https://github.com/$repo_name/blob/${{ github.event.pull_request.head.ref }}"
8680
8781
merged_commit=$(git log -1 --format='%H')
8882
changed_files="$(git diff --name-status --diff-filter=ARM ${{ github.event.pull_request.base.sha }} ${merged_commit} | awk '/\.md$/ {print $NF}')"

AgentQnA/README.md

Lines changed: 19 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,13 @@
11
# Agents for Question Answering
22

3+
## Table of contents
4+
5+
1. [Overview](#overview)
6+
2. [Deploy with Docker](#deploy-with-docker)
7+
3. [Launch the UI](#launch-the-ui)
8+
4. [Validate Services](#validate-services)
9+
5. [Register Tools](#how-to-register-other-tools-with-the-ai-agent)
10+
311
## Overview
412

513
This example showcases a hierarchical multi-agent system for question-answering applications. The architecture diagram below shows a supervisor agent that interfaces with the user and dispatches tasks to two worker agents to gather information and come up with answers. The worker RAG agent uses the retrieval tool to retrieve relevant documents from a knowledge base - a vector database. The worker SQL agent retrieves relevant data from a SQL database. Although not included in this example by default, other tools such as a web search tool or a knowledge graph query tool can be used by the supervisor agent to gather information from additional sources.
@@ -134,7 +142,7 @@ source $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi/set_env.sh
134142
source $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/cpu/xeon/set_env.sh
135143
```
136144

137-
### 3. Launch the multi-agent system. </br>
145+
### 2. Launch the multi-agent system. </br>
138146

139147
Two options are provided for the `llm_engine` of the agents: 1. open-source LLMs on Gaudi, 2. OpenAI models via API calls.
140148

@@ -151,11 +159,19 @@ cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi/
151159
docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose.yaml up -d
152160
```
153161

162+
To enable Open Telemetry Tracing, compose.telemetry.yaml file need to be merged along with default compose.yaml file.
163+
Gaudi example with Open Telemetry feature:
164+
165+
```bash
166+
cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi/
167+
docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose.yaml -f compose.telemetry.yaml up -d
168+
```
169+
154170
##### [Optional] Web Search Tool Support
155171

156172
<details>
157173
<summary> Instructions </summary>
158-
A web search tool is supported in this example and can be enabled by running docker compose with the `compose.webtool.yaml` file.
174+
A web search tool is supported in this example and can be enabled by running docker compose with the `compose.webtool.yaml` file.
159175
The Google Search API is used. Follow the [instructions](https://python.langchain.com/docs/integrations/tools/google_search) to create an API key and enable the Custom Search API on a Google account. The environment variables `GOOGLE_CSE_ID` and `GOOGLE_API_KEY` need to be set.
160176

161177
```bash
@@ -179,7 +195,7 @@ cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/cpu/xeon
179195
docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose_openai.yaml up -d
180196
```
181197

182-
### 4. Ingest Data into the vector database
198+
### 3. Ingest Data into the vector database
183199

184200
The `run_ingest_data.sh` script will use an example jsonl file to ingest example documents into a vector database. Other ways to ingest data and other types of documents supported can be found in the OPEA dataprep microservice located in the opea-project/GenAIComps repo.
185201

0 commit comments

Comments
 (0)