Files
ragflow/example/http/chunk_example.sh
Calixto Ong 11ff848b04 feat: Add SDK and cURL examples for chunk management, chat assistant, and retrieval (#4310) (#14208)
Closes #4310

### What problem does this PR solve?

Issue #4310 requests practical examples for the RAGFlow SDK and HTTP API
to help developers get started faster. The existing `example/sdk/`
folder only contains `dataset_example.py`. This PR fills the remaining
gaps by adding examples for three key API areas not yet covered in
`main` or by other open PRs (#13904, #13284):

- **Chunk management** — add, list, update, delete, and retrieve chunks
within a dataset
- **Chat assistant** — create a chat assistant, open a session, send
messages (streaming and non-streaming), and clean up
- **Retrieval** — perform semantic retrieval across one or multiple
datasets

### Type of change

- [x] Documentation Update
- [x] New Feature (non-breaking change which adds functionality)
2026-05-22 12:13:00 +08:00

90 lines
3.3 KiB
Bash

#!/bin/bash
#
# Copyright 2025 The InfiniFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# Variables
HOST_ADDRESS="${RAGFLOW_HOST_ADDRESS:-http://localhost:9380}"
API_KEY="${RAGFLOW_API_KEY:-ragflow-IzZmY1MGVhYTBhMjExZWZiYTdjMDI0Mm}"
# Check for jq
if ! command -v jq &> /dev/null; then
echo "jq could not be found, please install it to run this example."
exit 1
fi
# 0. Setup: Create a dataset and upload a document to get IDs
echo -e "\n-- Creating a dataset"
DATASET_ID=$(curl -s --request POST \
--url "${HOST_ADDRESS}/api/v1/datasets" \
--header 'Content-Type: application/json' \
--header "Authorization: Bearer ${API_KEY}" \
--data '{"name": "chunk_shell_example"}' | jq -r '.data.id')
echo "Dataset ID: ${DATASET_ID}"
echo -e "\n-- Uploading a document"
DOC_ID=$(curl -s --request POST \
--url "${HOST_ADDRESS}/api/v1/datasets/${DATASET_ID}/documents" \
--header "Authorization: Bearer ${API_KEY}" \
--form 'file=@sample.txt;type=text/plain' \
--form 'display_name=sample.txt' | jq -r '.data[0].id')
echo "Document ID: ${DOC_ID}"
# 1. Add a chunk to a document
echo -e "\n-- Add a chunk to a document"
CHUNK_ID=$(curl -s --request POST \
--url "${HOST_ADDRESS}/api/v1/datasets/${DATASET_ID}/documents/${DOC_ID}/chunks" \
--header 'Content-Type: application/json' \
--header "Authorization: Bearer ${API_KEY}" \
--data '{
"content": "RAGFlow is an open-source RAG engine.",
"important_keywords": ["RAGFlow", "open-source"]
}' | jq -r '.data.chunk.id')
echo "Chunk ID: ${CHUNK_ID}"
# 2. List chunks of a document
echo -e "\n-- List chunks of a document"
curl -s --request GET \
--url "${HOST_ADDRESS}/api/v1/datasets/${DATASET_ID}/documents/${DOC_ID}/chunks?page=1&page_size=10" \
--header "Authorization: Bearer ${API_KEY}" | jq .
# 3. Update a chunk
echo -e "\n-- Update a chunk"
curl -s --request PUT \
--url "${HOST_ADDRESS}/api/v1/datasets/${DATASET_ID}/documents/${DOC_ID}/chunks/${CHUNK_ID}" \
--header 'Content-Type: application/json' \
--header "Authorization: Bearer ${API_KEY}" \
--data '{
"content": "RAGFlow is a powerful open-source RAG engine."
}' | jq .
# 4. Delete chunks
echo -e "\n-- Delete chunks"
curl -s --request DELETE \
--url "${HOST_ADDRESS}/api/v1/datasets/${DATASET_ID}/documents/${DOC_ID}/chunks" \
--header 'Content-Type: application/json' \
--header "Authorization: Bearer ${API_KEY}" \
--data "{
\"chunk_ids\": [\"${CHUNK_ID}\"]
}" | jq .
# Cleanup
echo -e "\n-- Cleaning up dataset"
curl -s --request DELETE \
--url "${HOST_ADDRESS}/api/v1/datasets" \
--header 'Content-Type: application/json' \
--header "Authorization: Bearer ${API_KEY}" \
--data "{\"ids\": [\"${DATASET_ID}\"]}" | jq .