add missing branch

Reflect core library parameter update in API server

.gitea/workflows/build.yaml

@@ -0,0 +1,29 @@
+name: Build and Push Docker Image
+
+on:
+  push:
+    branches:
+      - main
+      - build
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Login to Docker Registry
+        uses: docker/login-action@v3
+        with:
+          registry: docker.sunxinao.cn
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+      - name: Build and Push Docker Image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: ./Dockerfile
+          push: true
+          tags: docker.sunxinao.cn/gardel/lightrag:latest

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -1,61 +0,0 @@
-name: Bug Report
-description: File a bug report
-title: "[Bug]:"
-labels: ["bug", "triage"]
-
-body:
-  - type: checkboxes
-    id: existingcheck
-    attributes:
-      label: Do you need to file an issue?
-      description: Please help us manage our time by avoiding duplicates and common bugs with the steps below.
-      options:
-        - label: I have searched the existing issues and this bug is not already filed.
-        - label: I believe this is a legitimate bug, not just a question or feature request.
-  - type: textarea
-    id: description
-    attributes:
-      label: Describe the bug
-      description: A clear and concise description of what the bug is.
-      placeholder: What went wrong?
-  - type: textarea
-    id: reproduce
-    attributes:
-      label: Steps to reproduce
-      description: Steps to reproduce the behavior.
-      placeholder: How can we replicate the issue?
-  - type: textarea
-    id: expected_behavior
-    attributes:
-      label: Expected Behavior
-      description: A clear and concise description of what you expected to happen.
-      placeholder: What should have happened?
-  - type: textarea
-    id: configused
-    attributes:
-      label: LightRAG Config Used
-      description: The LightRAG configuration used for the run.
-      placeholder: The settings content or LightRAG configuration
-      value: |
-        # Paste your config here
-  - type: textarea
-    id: screenshotslogs
-    attributes:
-      label: Logs and screenshots
-      description: If applicable, add screenshots and logs to help explain your problem.
-      placeholder: Add logs and screenshots here
-  - type: textarea
-    id: additional_information
-    attributes:
-      label: Additional Information
-      description: |
-        - LightRAG Version: e.g., v0.1.1
-        - Operating System: e.g., Windows 10, Ubuntu 20.04
-        - Python Version: e.g., 3.8
-        - Related Issues: e.g., #1
-        - Any other relevant information.
-      value: |
-        - LightRAG Version:
-        - Operating System:
-        - Python Version:
-        - Related Issues:

.github/ISSUE_TEMPLATE/config.yml

@@ -1 +0,0 @@
-blank_issues_enabled: false

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -1,26 +0,0 @@
-name: Feature Request
-description: File a feature request
-labels: ["enhancement"]
-title: "[Feature Request]:"
-
-body:
-  - type: checkboxes
-    id: existingcheck
-    attributes:
-      label: Do you need to file a feature request?
-      description: Please help us manage our time by avoiding duplicates and common feature request with the steps below.
-      options:
-        - label: I have searched the existing feature request and this feature request is not already filed.
-        - label: I believe this is a legitimate feature request, not just a question or bug.
-  - type: textarea
-    id: feature_request_description
-    attributes:
-      label: Feature Request Description
-      description: A clear and concise description of the feature request you would like.
-      placeholder: What this feature request add more or improve?
-  - type: textarea
-    id: additional_context
-    attributes:
-      label: Additional Context
-      description: Add any other context or screenshots about the feature request here.
-      placeholder: Any additional information

.github/ISSUE_TEMPLATE/question.yml

@@ -1,26 +0,0 @@
-name: Question
-description: Ask a general question
-labels: ["question"]
-title: "[Question]:"
-
-body:
-  - type: checkboxes
-    id: existingcheck
-    attributes:
-      label: Do you need to ask a question?
-      description: Please help us manage our time by avoiding duplicates and common questions with the steps below.
-      options:
-        - label: I have searched the existing question and discussions and this question is not already answered.
-        - label: I believe this is a legitimate question, not just a bug or feature request.
-  - type: textarea
-    id: question
-    attributes:
-      label: Your Question
-      description: A clear and concise description of your question.
-      placeholder: What is your question?
-  - type: textarea
-    id: context
-    attributes:
-      label: Additional Context
-      description: Provide any additional context or details that might help us understand your question better.
-      placeholder: Add any relevant information here

.github/dependabot.yml

@@ -1,11 +0,0 @@
-# To get started with Dependabot version updates, you'll need to specify which
-# package ecosystems to update and where the package manifests are located.
-# Please see the documentation for all configuration options:
-# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
-
-version: 2
-updates:
-  - package-ecosystem: "pip" # See documentation for possible values
-    directory: "/" # Location of package manifests
-    schedule:
-      interval: "weekly"

.github/pull_request_template.md

@@ -1,32 +0,0 @@
-<!--
-Thanks for contributing to LightRAG!
-
-Please ensure your pull request is ready for review before submitting.
-
-About this template
-
-This template helps contributors provide a clear and concise description of their changes. Feel free to adjust it as needed.
--->
-
-## Description
-
-[Briefly describe the changes made in this pull request.]
-
-## Related Issues
-
-[Reference any related issues or tasks addressed by this pull request.]
-
-## Changes Made
-
-[List the specific changes made in this pull request.]
-
-## Checklist
-
-- [ ] Changes tested locally
-- [ ] Code reviewed
-- [ ] Documentation updated (if necessary)
-- [ ] Unit tests added (if applicable)
-
-## Additional Notes
-
-[Add any additional notes or context for the reviewer(s).]

.github/workflows/docker-publish.yml

@@ -1,47 +0,0 @@
-name: Build and Push Docker Image
-
-on:
-  release:
-    types: [published]
-  workflow_dispatch:
-
-permissions:
-  contents: read
-  packages: write
-
-jobs:
-  build-and-push:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Login to GitHub Container Registry
-        uses: docker/login-action@v3
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Extract metadata for Docker
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ghcr.io/${{ github.repository }}
-          tags: |
-            type=semver,pattern={{version}}
-            type=raw,value=latest,enable={{is_default_branch}}
-
-      - name: Build and push Docker image
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          platforms: linux/amd64,linux/arm64
-          push: true
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max

.github/workflows/linting.yaml

@@ -1,30 +0,0 @@
-name: Linting and Formatting
-
-on:
-    push:
-        branches:
-            - main
-    pull_request:
-        branches:
-            - main
-
-jobs:
-    lint-and-format:
-        runs-on: ubuntu-latest
-
-        steps:
-            - name: Checkout code
-              uses: actions/checkout@v2
-
-            - name: Set up Python
-              uses: actions/setup-python@v2
-              with:
-                python-version: '3.x'
-
-            - name: Install dependencies
-              run: |
-                python -m pip install --upgrade pip
-                pip install pre-commit
-
-            - name: Run pre-commit
-              run: pre-commit run --all-files --show-diff-on-failure

.github/workflows/pypi-publish.yml

@@ -1,52 +0,0 @@
-name: Upload LightRAG-hku Package
-
-on:
-  release:
-    types: [published]
-
-permissions:
-  contents: read
-
-jobs:
-  release-build:
-    runs-on: ubuntu-latest
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: actions/setup-python@v5
-        with:
-          python-version: "3.x"
-
-      - name: Build release distributions
-        run: |
-          python -m pip install build
-          python -m build
-
-      - name: Upload distributions
-        uses: actions/upload-artifact@v4
-        with:
-          name: release-dists
-          path: dist/
-
-  pypi-publish:
-    runs-on: ubuntu-latest
-    needs:
-      - release-build
-    permissions:
-      id-token: write
-
-    environment:
-      name: pypi
-
-    steps:
-      - name: Retrieve release distributions
-        uses: actions/download-artifact@v4
-        with:
-          name: release-dists
-          path: dist/
-
-      - name: Publish release distributions to PyPI
-        uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          packages-dir: dist/

examples/unofficial-sample/lightrag_llamaindex_litellm_demo.py

@@ -53,7 +53,6 @@ async def llm_model_func(prompt, system_prompt=None, history_messages=[], **kwar
             prompt,
             system_prompt=system_prompt,
             history_messages=history_messages,
-            **kwargs,
         )
         return response
     except Exception as e:

examples/unofficial-sample/lightrag_llamaindex_litellm_opik_demo.py

@@ -0,0 +1,155 @@
+import os
+from lightrag import LightRAG, QueryParam
+from lightrag.llm.llama_index_impl import (
+    llama_index_complete_if_cache,
+    llama_index_embed,
+)
+from lightrag.utils import EmbeddingFunc
+from llama_index.llms.litellm import LiteLLM
+from llama_index.embeddings.litellm import LiteLLMEmbedding
+import asyncio
+import nest_asyncio
+
+nest_asyncio.apply()
+
+from lightrag.kg.shared_storage import initialize_pipeline_status
+
+# Configure working directory
+WORKING_DIR = "./index_default"
+print(f"WORKING_DIR: {WORKING_DIR}")
+
+# Model configuration
+LLM_MODEL = os.environ.get("LLM_MODEL", "gemma-3-4b")
+print(f"LLM_MODEL: {LLM_MODEL}")
+EMBEDDING_MODEL = os.environ.get("EMBEDDING_MODEL", "arctic-embed")
+print(f"EMBEDDING_MODEL: {EMBEDDING_MODEL}")
+EMBEDDING_MAX_TOKEN_SIZE = int(os.environ.get("EMBEDDING_MAX_TOKEN_SIZE", 8192))
+print(f"EMBEDDING_MAX_TOKEN_SIZE: {EMBEDDING_MAX_TOKEN_SIZE}")
+
+# LiteLLM configuration
+LITELLM_URL = os.environ.get("LITELLM_URL", "http://localhost:4000")
+print(f"LITELLM_URL: {LITELLM_URL}")
+LITELLM_KEY = os.environ.get("LITELLM_KEY", "sk-4JdvGFKqSA3S0k_5p0xufw")
+
+if not os.path.exists(WORKING_DIR):
+    os.mkdir(WORKING_DIR)
+
+
+# Initialize LLM function
+async def llm_model_func(prompt, system_prompt=None, history_messages=[], **kwargs):
+    try:
+        # Initialize LiteLLM if not in kwargs
+        if "llm_instance" not in kwargs:
+            llm_instance = LiteLLM(
+                model=f"openai/{LLM_MODEL}",  # Format: "provider/model_name"
+                api_base=LITELLM_URL,
+                api_key=LITELLM_KEY,
+                temperature=0.7,
+            )
+            kwargs["llm_instance"] = llm_instance
+
+        chat_kwargs = {}
+        chat_kwargs["litellm_params"] = {
+            "metadata": {
+                "opik": {
+                    "project_name": "lightrag_llamaindex_litellm_opik_demo",
+                    "tags": ["lightrag", "litellm"],
+                }
+            }
+        }
+
+        response = await llama_index_complete_if_cache(
+            kwargs["llm_instance"],
+            prompt,
+            system_prompt=system_prompt,
+            history_messages=history_messages,
+            chat_kwargs=chat_kwargs,
+        )
+        return response
+    except Exception as e:
+        print(f"LLM request failed: {str(e)}")
+        raise
+
+
+# Initialize embedding function
+async def embedding_func(texts):
+    try:
+        embed_model = LiteLLMEmbedding(
+            model_name=f"openai/{EMBEDDING_MODEL}",
+            api_base=LITELLM_URL,
+            api_key=LITELLM_KEY,
+        )
+        return await llama_index_embed(texts, embed_model=embed_model)
+    except Exception as e:
+        print(f"Embedding failed: {str(e)}")
+        raise
+
+
+# Get embedding dimension
+async def get_embedding_dim():
+    test_text = ["This is a test sentence."]
+    embedding = await embedding_func(test_text)
+    embedding_dim = embedding.shape[1]
+    print(f"embedding_dim={embedding_dim}")
+    return embedding_dim
+
+
+async def initialize_rag():
+    embedding_dimension = await get_embedding_dim()
+
+    rag = LightRAG(
+        working_dir=WORKING_DIR,
+        llm_model_func=llm_model_func,
+        embedding_func=EmbeddingFunc(
+            embedding_dim=embedding_dimension,
+            max_token_size=EMBEDDING_MAX_TOKEN_SIZE,
+            func=embedding_func,
+        ),
+    )
+
+    await rag.initialize_storages()
+    await initialize_pipeline_status()
+
+    return rag
+
+
+def main():
+    # Initialize RAG instance
+    rag = asyncio.run(initialize_rag())
+
+    # Insert example text
+    with open("./book.txt", "r", encoding="utf-8") as f:
+        rag.insert(f.read())
+
+    # Test different query modes
+    print("\nNaive Search:")
+    print(
+        rag.query(
+            "What are the top themes in this story?", param=QueryParam(mode="naive")
+        )
+    )
+
+    print("\nLocal Search:")
+    print(
+        rag.query(
+            "What are the top themes in this story?", param=QueryParam(mode="local")
+        )
+    )
+
+    print("\nGlobal Search:")
+    print(
+        rag.query(
+            "What are the top themes in this story?", param=QueryParam(mode="global")
+        )
+    )
+
+    print("\nHybrid Search:")
+    print(
+        rag.query(
+            "What are the top themes in this story?", param=QueryParam(mode="hybrid")
+        )
+    )
+
+
+if __name__ == "__main__":
+    main()

lightrag/api/routers/document_routes.py

@@ -84,22 +84,30 @@ class InsertTextRequest(BaseModel):
 
     Attributes:
         text: The text content to be inserted into the RAG system
+        file_source: Source of the text (optional)
     """
 
     text: str = Field(
         min_length=1,
         description="The text to insert",
     )
+    file_source: str = Field(default=None, min_length=0, description="File Source")
 
     @field_validator("text", mode="after")
     @classmethod
-    def strip_after(cls, text: str) -> str:
+    def strip_text_after(cls, text: str) -> str:
         return text.strip()
 
+    @field_validator("file_source", mode="after")
+    @classmethod
+    def strip_source_after(cls, file_source: str) -> str:
+        return file_source.strip()
+
     class Config:
         json_schema_extra = {
             "example": {
-                "text": "This is a sample text to be inserted into the RAG system."
+                "text": "This is a sample text to be inserted into the RAG system.",
+                "file_source": "Source of the text (optional)",
             }
         }
 
@@ -109,25 +117,37 @@ class InsertTextsRequest(BaseModel):
 
     Attributes:
         texts: List of text contents to be inserted into the RAG system
+        file_sources: Sources of the texts (optional)
     """
 
     texts: list[str] = Field(
         min_length=1,
         description="The texts to insert",
     )
+    file_sources: list[str] = Field(
+        default=None, min_length=0, description="Sources of the texts"
+    )
 
     @field_validator("texts", mode="after")
     @classmethod
-    def strip_after(cls, texts: list[str]) -> list[str]:
+    def strip_texts_after(cls, texts: list[str]) -> list[str]:
         return [text.strip() for text in texts]
 
+    @field_validator("file_sources", mode="after")
+    @classmethod
+    def strip_sources_after(cls, file_sources: list[str]) -> list[str]:
+        return [file_source.strip() for file_source in file_sources]
+
     class Config:
         json_schema_extra = {
             "example": {
                 "texts": [
                     "This is the first text to be inserted.",
                     "This is the second text to be inserted.",
-                ]
+                ],
+                "file_sources": [
+                    "First file source (optional)",
+                ],
             }
         }
 
@@ -656,16 +676,25 @@ async def pipeline_index_files(rag: LightRAG, file_paths: List[Path]):
         logger.error(traceback.format_exc())
 
 
-async def pipeline_index_texts(rag: LightRAG, texts: List[str]):
+async def pipeline_index_texts(
+    rag: LightRAG, texts: List[str], file_sources: List[str] = None
+):
     """Index a list of texts
 
     Args:
         rag: LightRAG instance
         texts: The texts to index
+        file_sources: Sources of the texts
     """
     if not texts:
         return
-    await rag.apipeline_enqueue_documents(texts)
+    if file_sources is not None:
+        if len(file_sources) != 0 and len(file_sources) != len(texts):
+            [
+                file_sources.append("unknown_source")
+                for _ in range(len(file_sources), len(texts))
+            ]
+    await rag.apipeline_enqueue_documents(input=texts, file_paths=file_sources)
     await rag.apipeline_process_enqueue_documents()
 
 
@@ -816,7 +845,12 @@ def create_document_routes(
             HTTPException: If an error occurs during text processing (500).
         """
         try:
-            background_tasks.add_task(pipeline_index_texts, rag, [request.text])
+            background_tasks.add_task(
+                pipeline_index_texts,
+                rag,
+                [request.text],
+                file_sources=[request.file_source],
+            )
             return InsertResponse(
                 status="success",
                 message="Text successfully received. Processing will continue in background.",
@@ -851,7 +885,12 @@ def create_document_routes(
             HTTPException: If an error occurs during text processing (500).
         """
         try:
-            background_tasks.add_task(pipeline_index_texts, rag, request.texts)
+            background_tasks.add_task(
+                pipeline_index_texts,
+                rag,
+                request.texts,
+                file_sources=request.file_sources,
+            )
             return InsertResponse(
                 status="success",
                 message="Text successfully received. Processing will continue in background.",

lightrag/api/routers/query_routes.py

@@ -78,6 +78,10 @@ class QueryRequest(BaseModel):
         description="Number of complete conversation turns (user-assistant pairs) to consider in the response context.",
     )
 
+    ids: list[str] | None = Field(
+        default=None, description="List of ids to filter the results."
+    )
+
     user_prompt: Optional[str] = Field(
         default=None,
         description="User-provided prompt for the query. If provided, this will be used instead of the default value from prompt template.",

lightrag/kg/mongo_impl.py

@@ -311,6 +311,17 @@ class MongoDocStatusStorage(DocStatusStorage):
             logger.error(f"Error dropping doc status {self._collection_name}: {e}")
             return {"status": "error", "message": str(e)}
 
+    async def delete(self, ids: list[str]) -> None:
+        try:
+            result = await self._data.delete_many({"_id": {"$in": ids}})
+            deleted_count = result.deleted_count
+
+            logger.info(
+                f"Dropped {deleted_count} documents from doc status {self._collection_name}"
+            )
+        except PyMongoError as e:
+            logger.error(f"Error deleting doc status {self._collection_name}: {e}")
+
 
 @final
 @dataclass

lightrag/llm/llama_index_impl.py

@@ -95,7 +95,7 @@ async def llama_index_complete_if_cache(
     prompt: str,
     system_prompt: Optional[str] = None,
     history_messages: List[dict] = [],
-    **kwargs,
+    chat_kwargs={},
 ) -> str:
     """Complete the prompt using LlamaIndex."""
     try:
@@ -122,13 +122,9 @@ async def llama_index_complete_if_cache(
         # Add current prompt
         formatted_messages.append(ChatMessage(role=MessageRole.USER, content=prompt))
 
-        # Get LLM instance from kwargs
+        response: ChatResponse = await model.achat(
-        if "llm_instance" not in kwargs:
+            messages=formatted_messages, **chat_kwargs
-            raise ValueError("llm_instance must be provided in kwargs")
+        )
-        llm = kwargs["llm_instance"]
-
-        # Get response
-        response: ChatResponse = await llm.achat(messages=formatted_messages)
 
         # In newer versions, the response is in message.content
         content = response.message.content