gardel/lightrag
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #514 from ParisNeo/main

Browse Source 
Streamlined API Installation and Documentation Enhancement
This commit is contained in:
zrguo
2024-12-27 15:39:52 +08:00
committed by GitHub
parent 457e683acd 27a52ddf37
commit 9c4853d007
8 changed files with 251 additions and 347 deletions
Download Patch File Download Diff File Expand all files Collapse all files

182
README.md
View File

@@ -598,120 +598,6 @@ if __name__ == "__main__":
| **convert\_response\_to\_json\_func** | `callable` | Not used | `convert_response_to_json` |
| **embedding\_cache\_config** | `dict` | Configuration for question-answer caching. Contains three parameters:<br>- `enabled`: Boolean value to enable/disable cache lookup functionality. When enabled, the system will check cached responses before generating new answers.<br>- `similarity_threshold`: Float value (0-1), similarity threshold. When a new question's similarity with a cached question exceeds this threshold, the cached answer will be returned directly without calling the LLM.<br>- `use_llm_check`: Boolean value to enable/disable LLM similarity verification. When enabled, LLM will be used as a secondary check to verify the similarity between questions before returning cached answers. | Default: `{"enabled": False, "similarity_threshold": 0.95, "use_llm_check": False}` |
## API Server Implementation
LightRAG also provides a FastAPI-based server implementation for RESTful API access to RAG operations. This allows you to run LightRAG as a service and interact with it through HTTP requests.
### Setting up the API Server
<details>
<summary>Click to expand setup instructions</summary>
1. First, ensure you have the required dependencies:
```bash
pip install fastapi uvicorn pydantic
```
2. Set up your environment variables:
```bash
export RAG_DIR="your_index_directory" # Optional: Defaults to "index_default"
export OPENAI_BASE_URL="Your OpenAI API base URL" # Optional: Defaults to "https://api.openai.com/v1"
export OPENAI_API_KEY="Your OpenAI API key" # Required
export LLM_MODEL="Your LLM model" # Optional: Defaults to "gpt-4o-mini"
export EMBEDDING_MODEL="Your embedding model" # Optional: Defaults to "text-embedding-3-large"
```
3. Run the API server:
```bash
python examples/lightrag_api_openai_compatible_demo.py
```
The server will start on `http://0.0.0.0:8020`.
</details>
### API Endpoints
The API server provides the following endpoints:
#### 1. Query Endpoint
<details>
<summary>Click to view Query endpoint details</summary>
- **URL:** `/query`
- **Method:** POST
- **Body:**
```json
{
"query": "Your question here",
"mode": "hybrid", // Can be "naive", "local", "global", or "hybrid"
"only_need_context": true // Optional: Defaults to false, if true, only the referenced context will be returned, otherwise the llm answer will be returned
}
```
- **Example:**
```bash
curl -X POST "http://127.0.0.1:8020/query" \
-H "Content-Type: application/json" \
-d '{"query": "What are the main themes?", "mode": "hybrid"}'
```
</details>
#### 2. Insert Text Endpoint
<details>
<summary>Click to view Insert Text endpoint details</summary>
- **URL:** `/insert`
- **Method:** POST
- **Body:**
```json
{
"text": "Your text content here"
}
```
- **Example:**
```bash
curl -X POST "http://127.0.0.1:8020/insert" \
-H "Content-Type: application/json" \
-d '{"text": "Content to be inserted into RAG"}'
```
</details>
#### 3. Insert File Endpoint
<details>
<summary>Click to view Insert File endpoint details</summary>
- **URL:** `/insert_file`
- **Method:** POST
- **Body:**
```json
{
"file_path": "path/to/your/file.txt"
}
```
- **Example:**
```bash
curl -X POST "http://127.0.0.1:8020/insert_file" \
-H "Content-Type: application/json" \
-d '{"file_path": "./book.txt"}'
```
</details>
#### 4. Health Check Endpoint
<details>
<summary>Click to view Health Check endpoint details</summary>
- **URL:** `/health`
- **Method:** GET
- **Example:**
```bash
curl -X GET "http://127.0.0.1:8020/health"
```
</details>
### Configuration
The API server can be configured using environment variables:
- `RAG_DIR`: Directory for storing the RAG index (default: "index_default")
- API keys and base URLs should be configured in the code for your specific LLM and embedding model providers
### Error Handling
<details>
<summary>Click to view error handling details</summary>
@@ -989,6 +875,12 @@ def extract_queries(file_path):
│ ├── lightrag_siliconcloud_demo.py
│ └── vram_management_demo.py
├── lightrag/
│ ├── api/
│ │ ├── lollms_lightrag_server.py
│ │ ├── ollama_lightrag_server.py
│ │ ├── openai_lightrag_server.py
│ │ ├── azure_openai_lightrag_server.py
│ │ └── requirements.txt
│ ├── kg/
│ │ ├── __init__.py
│ │ ├── oracle_impl.py
@@ -1033,7 +925,7 @@ pip install "lightrag-hku[api]"
```bash
# Clone the repository
git clone https://github.com/ParisNeo/lightrag.git
git clone https://github.com/HKUDS/lightrag.git
# Change to the repository directory
cd lightrag
@@ -1060,6 +952,27 @@ Before running any of the servers, ensure you have the corresponding backend ser
- Requires valid OpenAI API credentials set in environment variables
- OPENAI_API_KEY must be set
#### For Azure OpenAI Server
Azure OpenAI API can be created using the following commands in Azure CLI (you need to install Azure CLI first from [https://docs.microsoft.com/en-us/cli/azure/install-azure-cli](https://docs.microsoft.com/en-us/cli/azure/install-azure-cli)):
```bash
# Change the resource group name, location and OpenAI resource name as needed
RESOURCE_GROUP_NAME=LightRAG
LOCATION=swedencentral
RESOURCE_NAME=LightRAG-OpenAI
az login
az group create --name $RESOURCE_GROUP_NAME --location $LOCATION
az cognitiveservices account create --name $RESOURCE_NAME --resource-group $RESOURCE_GROUP_NAME --kind OpenAI --sku S0 --location swedencentral
az cognitiveservices account deployment create --resource-group $RESOURCE_GROUP_NAME --model-format OpenAI --name $RESOURCE_NAME --deployment-name gpt-4o --model-name gpt-4o --model-version "2024-08-06" --sku-capacity 100 --sku-name "Standard"
az cognitiveservices account deployment create --resource-group $RESOURCE_GROUP_NAME --model-format OpenAI --name $RESOURCE_NAME --deployment-name text-embedding-3-large --model-name text-embedding-3-large --model-version "1" --sku-capacity 80 --sku-name "Standard"
az cognitiveservices account show --name $RESOURCE_NAME --resource-group $RESOURCE_GROUP_NAME --query "properties.endpoint"
az cognitiveservices account keys list --name $RESOURCE_NAME -g $RESOURCE_GROUP_NAME
```
The output of the last command will give you the endpoint and the key for the OpenAI API. You can use these values to set the environment variables in the `.env` file.
### Configuration Options
Each server has its own specific configuration options:
@@ -1112,6 +1025,22 @@ Each server has its own specific configuration options:
| --input-dir | ./inputs | Input directory for documents |
| --log-level | INFO | Logging level |
#### OpenAI AZURE Server Options
| Parameter | Default | Description |
|-----------|---------|-------------|
| --host | 0.0.0.0 | Server host |
| --port | 9621 | Server port |
| --model | gpt-4 | OpenAI model name |
| --embedding-model | text-embedding-3-large | OpenAI embedding model |
| --working-dir | ./rag_storage | Working directory for RAG |
| --max-tokens | 32768 | Maximum token size |
| --max-embed-tokens | 8192 | Maximum embedding token size |
| --input-dir | ./inputs | Input directory for documents |
| --enable-cache | True | Enable response cache |
| --log-level | INFO | Logging level |
### Example Usage
#### LoLLMs RAG Server
@@ -1140,17 +1069,25 @@ ollama-lightrag-server --model mistral-nemo:latest --embedding-model bge-m3 --em
# Using GPT-4 with text-embedding-3-large
openai-lightrag-server --port 9624 --model gpt-4 --embedding-model text-embedding-3-large
```
#### Azure OpenAI RAG Server
```bash
# Using GPT-4 with text-embedding-3-large
azure-openai-lightrag-server --model gpt-4o --port 8080 --working-dir ./custom_rag --embedding-model text-embedding-3-large
```
**Important Notes:**
- For LoLLMs: Make sure the specified models are installed in your LoLLMs instance
- For Ollama: Make sure the specified models are installed in your Ollama instance
- For OpenAI: Ensure you have set up your OPENAI_API_KEY environment variable
- For Azure OpenAI: Build and configure your server as stated in the Prequisites section
For help on any server, use the --help flag:
```bash
lollms-lightrag-server --help
ollama-lightrag-server --help
openai-lightrag-server --help
azure-openai-lightrag-server --help
```
Note: If you don't need the API functionality, you can install the base package without API support using:
@@ -1160,7 +1097,7 @@ pip install lightrag-hku
## API Endpoints
All servers (LoLLMs, Ollama, and OpenAI) provide the same REST API endpoints for RAG functionality.
All servers (LoLLMs, Ollama, OpenAI and Azure OpenAI) provide the same REST API endpoints for RAG functionality.
### Query Endpoints
@@ -1245,7 +1182,10 @@ For OpenAI:
```bash
uvicorn openai_lightrag_server:app --reload --port 9621
```
For Azure OpenAI:
```bash
uvicorn azure_openai_lightrag_server:app --reload --port 9621
```
### API Documentation
When any server is running, visit:
@@ -1301,6 +1241,14 @@ ollama-lightrag-server --input-dir ./my_documents --port 8080
openai-lightrag-server --input-dir ./my_documents --port 9624
```
#### Azure OpenAI RAG Server
```bash
# Start server with automatic document vectorization
# Existing documents are retrieved from cache, only new ones are processed
azure-openai-lightrag-server --input-dir ./my_documents --port 9624
```
**Important Notes:**
- The `--input-dir` parameter enables automatic document processing at startup
- Documents already in the database are not re-vectorized

114
examples/openai_README.md Normal file
View File

@@ -0,0 +1,114 @@
## API Server Implementation
LightRAG also provides a FastAPI-based server implementation for RESTful API access to RAG operations. This allows you to run LightRAG as a service and interact with it through HTTP requests.
### Setting up the API Server
<details>
<summary>Click to expand setup instructions</summary>
1. First, ensure you have the required dependencies:
```bash
pip install fastapi uvicorn pydantic
```
2. Set up your environment variables:
```bash
export RAG_DIR="your_index_directory" # Optional: Defaults to "index_default"
export OPENAI_BASE_URL="Your OpenAI API base URL" # Optional: Defaults to "https://api.openai.com/v1"
export OPENAI_API_KEY="Your OpenAI API key" # Required
export LLM_MODEL="Your LLM model" # Optional: Defaults to "gpt-4o-mini"
export EMBEDDING_MODEL="Your embedding model" # Optional: Defaults to "text-embedding-3-large"
```
3. Run the API server:
```bash
python examples/lightrag_api_openai_compatible_demo.py
```
The server will start on `http://0.0.0.0:8020`.
</details>
### API Endpoints
The API server provides the following endpoints:
#### 1. Query Endpoint
<details>
<summary>Click to view Query endpoint details</summary>
- **URL:** `/query`
- **Method:** POST
- **Body:**
```json
{
"query": "Your question here",
"mode": "hybrid", // Can be "naive", "local", "global", or "hybrid"
"only_need_context": true // Optional: Defaults to false, if true, only the referenced context will be returned, otherwise the llm answer will be returned
}
```
- **Example:**
```bash
curl -X POST "http://127.0.0.1:8020/query" \
-H "Content-Type: application/json" \
-d '{"query": "What are the main themes?", "mode": "hybrid"}'
```
</details>
#### 2. Insert Text Endpoint
<details>
<summary>Click to view Insert Text endpoint details</summary>
- **URL:** `/insert`
- **Method:** POST
- **Body:**
```json
{
"text": "Your text content here"
}
```
- **Example:**
```bash
curl -X POST "http://127.0.0.1:8020/insert" \
-H "Content-Type: application/json" \
-d '{"text": "Content to be inserted into RAG"}'
```
</details>
#### 3. Insert File Endpoint
<details>
<summary>Click to view Insert File endpoint details</summary>
- **URL:** `/insert_file`
- **Method:** POST
- **Body:**
```json
{
"file_path": "path/to/your/file.txt"
}
```
- **Example:**
```bash
curl -X POST "http://127.0.0.1:8020/insert_file" \
-H "Content-Type: application/json" \
-d '{"file_path": "./book.txt"}'
```
</details>
#### 4. Health Check Endpoint
<details>
<summary>Click to view Health Check endpoint details</summary>
- **URL:** `/health`
- **Method:** GET
- **Example:**
```bash
curl -X GET "http://127.0.0.1:8020/health"
```
</details>
### Configuration
The API server can be configured using environment variables:
- `RAG_DIR`: Directory for storing the RAG index (default: "index_default")
- API keys and base URLs should be configured in the code for your specific LLM and embedding model providers

202
lightrag/api/README_AZURE_OPENAI.md
View File

@@ -1,202 +0,0 @@
# LightRAG API Server
A powerful FastAPI-based server for managing and querying documents using LightRAG (Light Retrieval-Augmented Generation). This server provides a REST API interface for document management and intelligent querying using OpenAI's language models.
## Features
- 🔍 Multiple search modes (naive, local, global, hybrid)
- 📡 Streaming and non-streaming responses
- 📝 Document management (insert, batch upload, clear)
- ⚙️ Highly configurable model parameters
- 📚 Support for text and file uploads
- 🔧 RESTful API with automatic documentation
- 🚀 Built with FastAPI for high performance
## Prerequisites
- Python 3.8+
- Azure OpenAI API key
- Azure OpenAI Deployments (gpt-4o, text-embedding-3-large)
- Required Python packages:
- fastapi
- uvicorn
- lightrag
- pydantic
- openai
- nest-asyncio
## Installation
If you are using Windows, you will need to download and install visual c++ build tools from [https://visualstudio.microsoft.com/visual-cpp-build-tools/](https://visualstudio.microsoft.com/visual-cpp-build-tools/)
Make sure you install the VS 2022 C++ x64/x86 Build tools from individual components tab.
1. Clone the repository:
```bash
git clone https://github.com/ParisNeo/LightRAG.git
cd api
```
2. Install dependencies:
```bash
python -m venv venv
source venv/bin/activate
#venv\Scripts\activate for Windows
pip install -r requirements.txt
```
3. Set up environment variables:
use the `.env` file to set the environment variables (you can copy the `.env.aoi.example` file and rename it to `.env`),
or set them manually:
```bash
export AZURE_OPENAI_API_VERSION='2024-08-01-preview'
export AZURE_OPENAI_DEPLOYMENT='gpt-4o'
export AZURE_OPENAI_API_KEY='myapikey'
export AZURE_OPENAI_ENDPOINT='https://myendpoint.openai.azure.com'
export AZURE_EMBEDDING_DEPLOYMENT='text-embedding-3-large'
export AZURE_EMBEDDING_API_VERSION='2023-05-15'
```
## Configuration
The server can be configured using command-line arguments:
```bash
python azure_openai_lightrag_server.py --help
```
Available options:
| Parameter | Default | Description |
|-----------|---------|-------------|
| --host | 0.0.0.0 | Server host |
| --port | 9621 | Server port |
| --model | gpt-4 | OpenAI model name |
| --embedding-model | text-embedding-3-large | OpenAI embedding model |
| --working-dir | ./rag_storage | Working directory for RAG |
| --max-tokens | 32768 | Maximum token size |
| --max-embed-tokens | 8192 | Maximum embedding token size |
| --input-dir | ./inputs | Input directory for documents |
| --enable-cache | True | Enable response cache |
| --log-level | INFO | Logging level |
## Quick Start
1. Basic usage with default settings:
```bash
python azure_openai_lightrag_server.py
```
2. Custom configuration:
```bash
python azure_openai_lightrag_server.py --model gpt-4o --port 8080 --working-dir ./custom_rag
```
## API Endpoints
### Query Endpoints
#### POST /query
Query the RAG system with options for different search modes.
```bash
curl -X POST "http://localhost:9621/query" \
-H "Content-Type: application/json" \
-d '{"query": "Your question here", "mode": "hybrid"}'
```
#### POST /query/stream
Stream responses from the RAG system.
```bash
curl -X POST "http://localhost:9621/query/stream" \
-H "Content-Type: application/json" \
-d '{"query": "Your question here", "mode": "hybrid"}'
```
### Document Management Endpoints
#### POST /documents/text
Insert text directly into the RAG system.
```bash
curl -X POST "http://localhost:9621/documents/text" \
-H "Content-Type: application/json" \
-d '{"text": "Your text content here", "description": "Optional description"}'
```
#### POST /documents/file
Upload a single file to the RAG system.
```bash
curl -X POST "http://localhost:9621/documents/file" \
-F "file=@/path/to/your/document.txt" \
-F "description=Optional description"
```
#### POST /documents/batch
Upload multiple files at once.
```bash
curl -X POST "http://localhost:9621/documents/batch" \
-F "files=@/path/to/doc1.txt" \
-F "files=@/path/to/doc2.txt"
```
#### DELETE /documents
Clear all documents from the RAG system.
```bash
curl -X DELETE "http://localhost:9621/documents"
```
### Utility Endpoints
#### GET /health
Check server health and configuration.
```bash
curl "http://localhost:9621/health"
```
## Development
### Running in Development Mode
```bash
uvicorn azure_openai_lightrag_server:app --reload --port 9621
```
### API Documentation
When the server is running, visit:
- Swagger UI: http://localhost:9621/docs
- ReDoc: http://localhost:9621/redoc
## Deployment
Azure OpenAI API can be created using the following commands in Azure CLI (you need to install Azure CLI first from [https://docs.microsoft.com/en-us/cli/azure/install-azure-cli](https://docs.microsoft.com/en-us/cli/azure/install-azure-cli)):
```bash
# Change the resource group name, location and OpenAI resource name as needed
RESOURCE_GROUP_NAME=LightRAG
LOCATION=swedencentral
RESOURCE_NAME=LightRAG-OpenAI
az login
az group create --name $RESOURCE_GROUP_NAME --location $LOCATION
az cognitiveservices account create --name $RESOURCE_NAME --resource-group $RESOURCE_GROUP_NAME --kind OpenAI --sku S0 --location swedencentral
az cognitiveservices account deployment create --resource-group $RESOURCE_GROUP_NAME --model-format OpenAI --name $RESOURCE_NAME --deployment-name gpt-4o --model-name gpt-4o --model-version "2024-08-06" --sku-capacity 100 --sku-name "Standard"
az cognitiveservices account deployment create --resource-group $RESOURCE_GROUP_NAME --model-format OpenAI --name $RESOURCE_NAME --deployment-name text-embedding-3-large --model-name text-embedding-3-large --model-version "1" --sku-capacity 80 --sku-name "Standard"
az cognitiveservices account show --name $RESOURCE_NAME --resource-group $RESOURCE_GROUP_NAME --query "properties.endpoint"
az cognitiveservices account keys list --name $RESOURCE_NAME -g $RESOURCE_GROUP_NAME
```
The output of the last command will give you the endpoint and the key for the OpenAI API. You can use these values to set the environment variables in the `.env` file.
## License
This project is licensed under the MIT License - see the LICENSE file for details.
## Acknowledgments
- Built with [FastAPI](https://fastapi.tiangolo.com/)
- Uses [LightRAG](https://github.com/HKUDS/LightRAG) for document processing
- Powered by [OpenAI](https://openai.com/) for language model inference

27
lightrag/api/azure_openai_lightrag_server.py
View File

@@ -136,6 +136,7 @@ class SearchMode(str, Enum):
class QueryRequest(BaseModel):
query: str
mode: SearchMode = SearchMode.hybrid
only_need_context: bool = False
# stream: bool = False
@@ -308,7 +309,11 @@ def create_app(args):
try:
response = await rag.aquery(
request.query,
param=QueryParam(mode=request.mode, stream=False),
param=QueryParam(
mode=request.mode,
stream=False,
only_need_context=request.only_need_context,
),
)
return QueryResponse(response=response)
except Exception as e:
@@ -319,7 +324,11 @@ def create_app(args):
try:
response = await rag.aquery(
request.query,
param=QueryParam(mode=request.mode, stream=True),
param=QueryParam(
mode=request.mode,
stream=True,
only_need_context=request.only_need_context,
),
)
if inspect.isasyncgen(response):
@@ -339,11 +348,11 @@ def create_app(args):
@app.post("/documents/text", response_model=InsertResponse)
async def insert_text(request: InsertTextRequest):
try:
rag.insert(request.text)
await rag.ainsert(request.text)
return InsertResponse(
status="success",
message="Text successfully inserted",
document_count=len(rag),
document_count=1,
)
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@@ -365,7 +374,7 @@ def create_app(args):
return InsertResponse(
status="success",
message=f"File '{file.filename}' successfully inserted",
document_count=len(rag),
document_count=1,
)
except UnicodeDecodeError:
raise HTTPException(status_code=400, detail="File encoding not supported")
@@ -397,7 +406,7 @@ def create_app(args):
return InsertResponse(
status="success" if inserted_count > 0 else "partial_success",
message=status_message,
document_count=len(rag),
document_count=len(files),
)
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@@ -435,9 +444,13 @@ def create_app(args):
return app
if __name__ == "__main__":
def main():
args = parse_args()
import uvicorn
app = create_app(args)
uvicorn.run(app, host=args.host, port=args.port)
if __name__ == "__main__":
main()

26
lightrag/api/lollms_lightrag_server.py
View File

@@ -130,6 +130,7 @@ class QueryRequest(BaseModel):
query: str
mode: SearchMode = SearchMode.hybrid
stream: bool = False
only_need_context: bool = False
class QueryResponse(BaseModel):
@@ -219,7 +220,7 @@ def create_app(args):
try:
with open(file_path, "r", encoding="utf-8") as f:
content = f.read()
rag.insert(content)
await rag.ainsert(content)
doc_manager.mark_as_indexed(file_path)
indexed_count += 1
except Exception as e:
@@ -250,7 +251,7 @@ def create_app(args):
# Immediately index the uploaded file
with open(file_path, "r", encoding="utf-8") as f:
content = f.read()
rag.insert(content)
await rag.ainsert(content)
doc_manager.mark_as_indexed(file_path)
return {
@@ -266,7 +267,11 @@ def create_app(args):
try:
response = await rag.aquery(
request.query,
param=QueryParam(mode=request.mode, stream=request.stream),
param=QueryParam(
mode=request.mode,
stream=request.stream,
only_need_context=request.only_need_context,
),
)
if request.stream:
@@ -283,7 +288,12 @@ def create_app(args):
async def query_text_stream(request: QueryRequest):
try:
response = rag.query(
request.query, param=QueryParam(mode=request.mode, stream=True)
request.query,
param=QueryParam(
mode=request.mode,
stream=True,
only_need_context=request.only_need_context,
),
)
async def stream_generator():
@@ -313,7 +323,7 @@ def create_app(args):
if file.filename.endswith((".txt", ".md")):
text = content.decode("utf-8")
rag.insert(text)
await rag.ainsert(text)
else:
raise HTTPException(
status_code=400,
@@ -323,7 +333,7 @@ def create_app(args):
return InsertResponse(
status="success",
message=f"File '{file.filename}' successfully inserted",
document_count=len(rag),
document_count=1,
)
except UnicodeDecodeError:
raise HTTPException(status_code=400, detail="File encoding not supported")
@@ -341,7 +351,7 @@ def create_app(args):
content = await file.read()
if file.filename.endswith((".txt", ".md")):
text = content.decode("utf-8")
rag.insert(text)
await rag.ainsert(text)
inserted_count += 1
else:
failed_files.append(f"{file.filename} (unsupported type)")
@@ -355,7 +365,7 @@ def create_app(args):
return InsertResponse(
status="success" if inserted_count > 0 else "partial_success",
message=status_message,
document_count=len(rag),
document_count=len(files),
)
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))

28
lightrag/api/ollama_lightrag_server.py
View File

@@ -130,6 +130,7 @@ class QueryRequest(BaseModel):
query: str
mode: SearchMode = SearchMode.hybrid
stream: bool = False
only_need_context: bool = False
class QueryResponse(BaseModel):
@@ -219,7 +220,7 @@ def create_app(args):
try:
with open(file_path, "r", encoding="utf-8") as f:
content = f.read()
rag.insert(content)
await rag.ainsert(content)
doc_manager.mark_as_indexed(file_path)
indexed_count += 1
except Exception as e:
@@ -250,7 +251,7 @@ def create_app(args):
# Immediately index the uploaded file
with open(file_path, "r", encoding="utf-8") as f:
content = f.read()
rag.insert(content)
await rag.ainsert(content)
doc_manager.mark_as_indexed(file_path)
return {
@@ -266,7 +267,11 @@ def create_app(args):
try:
response = await rag.aquery(
request.query,
param=QueryParam(mode=request.mode, stream=request.stream),
param=QueryParam(
mode=request.mode,
stream=request.stream,
only_need_context=request.only_need_context,
),
)
if request.stream:
@@ -283,7 +288,12 @@ def create_app(args):
async def query_text_stream(request: QueryRequest):
try:
response = rag.query(
request.query, param=QueryParam(mode=request.mode, stream=True)
request.query,
param=QueryParam(
mode=request.mode,
stream=True,
only_need_context=request.only_need_context,
),
)
async def stream_generator():
@@ -297,7 +307,7 @@ def create_app(args):
@app.post("/documents/text", response_model=InsertResponse)
async def insert_text(request: InsertTextRequest):
try:
rag.insert(request.text)
await rag.ainsert(request.text)
return InsertResponse(
status="success",
message="Text successfully inserted",
@@ -313,7 +323,7 @@ def create_app(args):
if file.filename.endswith((".txt", ".md")):
text = content.decode("utf-8")
rag.insert(text)
await rag.ainsert(text)
else:
raise HTTPException(
status_code=400,
@@ -323,7 +333,7 @@ def create_app(args):
return InsertResponse(
status="success",
message=f"File '{file.filename}' successfully inserted",
document_count=len(rag),
document_count=1,
)
except UnicodeDecodeError:
raise HTTPException(status_code=400, detail="File encoding not supported")
@@ -341,7 +351,7 @@ def create_app(args):
content = await file.read()
if file.filename.endswith((".txt", ".md")):
text = content.decode("utf-8")
rag.insert(text)
await rag.ainsert(text)
inserted_count += 1
else:
failed_files.append(f"{file.filename} (unsupported type)")
@@ -355,7 +365,7 @@ def create_app(args):
return InsertResponse(
status="success" if inserted_count > 0 else "partial_success",
message=status_message,
document_count=len(rag),
document_count=len(files),
)
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))

18
lightrag/api/openai_lightrag_server.py
View File

@@ -119,6 +119,7 @@ class QueryRequest(BaseModel):
query: str
mode: SearchMode = SearchMode.hybrid
stream: bool = False
only_need_context: bool = False
class QueryResponse(BaseModel):
@@ -270,7 +271,11 @@ def create_app(args):
try:
response = await rag.aquery(
request.query,
param=QueryParam(mode=request.mode, stream=request.stream),
param=QueryParam(
mode=request.mode,
stream=request.stream,
only_need_context=request.only_need_context,
),
)
if request.stream:
@@ -287,7 +292,12 @@ def create_app(args):
async def query_text_stream(request: QueryRequest):
try:
response = rag.query(
request.query, param=QueryParam(mode=request.mode, stream=True)
request.query,
param=QueryParam(
mode=request.mode,
stream=True,
only_need_context=request.only_need_context,
),
)
async def stream_generator():
@@ -327,7 +337,7 @@ def create_app(args):
return InsertResponse(
status="success",
message=f"File '{file.filename}' successfully inserted",
document_count=len(rag),
document_count=1,
)
except UnicodeDecodeError:
raise HTTPException(status_code=400, detail="File encoding not supported")
@@ -359,7 +369,7 @@ def create_app(args):
return InsertResponse(
status="success" if inserted_count > 0 else "partial_success",
message=status_message,
document_count=len(rag),
document_count=len(files),
)
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))

1
setup.py
View File

@@ -103,6 +103,7 @@ setuptools.setup(
"lollms-lightrag-server=lightrag.api.lollms_lightrag_server:main [api]",
"ollama-lightrag-server=lightrag.api.ollama_lightrag_server:main [api]",
"openai-lightrag-server=lightrag.api.openai_lightrag_server:main [api]",
"azure-openai-lightrag-server=lightrag.api.azure_openai_lightrag_server:main [api]",
],
},
)