Platform For AI:Manage knowledge bases

How it works

LangStudio knowledge bases transform OSS files into a format retrievable by LLMs through three steps:

1. Data reading and chunking: Reads source files from OSS and splits them into processable units.

   • Unstructured documents are parsed and split into smaller, semantically complete text blocks (chunks).

   • Structured data is chunked by row.

   • Images are processed as a whole without being chunked.

2. Vectorization: Calls an embedding model to convert each chunk or image into a numerical vector representing its semantic meaning.

3. Storage and indexing: Stores vector data in a vector database and creates an index for retrieval.

Get started

This section describes how to create a Document-type knowledge base and use it in an application flow.

1. Create a knowledge base. Navigate to LangStudio and select a workspace. On the Knowledge Base tab, click Create Knowledge Base. Configure these parameters and click OK.

   Parameter		Description
   Basic Configuration	Name	Enter a custom name for the knowledge base, such as test_kg.
   	Data Source OSS Path	Location where source files are stored. For example: oss://examplebucket.oss-cn-hangzhou-internal.aliyuncs.com/test/original/.
   	Output OSS Path	Stores intermediate results and index information from document parsing. Final output depends on the selected vector database type. For example: oss://examplebucket.oss-cn-hangzhou-internal.aliyuncs.com/test/output/. Important If the Instance RAM Role for the runtime is the PAI default role, set this parameter to a directory within the current workspace default storage path's OSS Bucket.
   	Type	Select Document.
   Embedding Model and Database	Embedding Type	Select Alibaba Cloud Model Studio Service (create a connection first, see Connection Configuration), then select the connection and model.
   	Vector Database Type	Select FAISS for quick testing.

2. Upload files.

   1. On the Knowledge Base tab, click the knowledge base. On the Overview page, switch to the Documents tab. This tab displays documents from the configured OSS data source.

   2. Add or update files using the Upload button, or upload files directly to the OSS data source. For example, upload rag_test_doc.txt through the page. For supported file formats, see Knowledge Base Types.

      

3. Update the index. After uploading files, click Update Index in the upper-right corner. In the dialog box, configure computing resources and network. When the task succeeds, file status changes to Indexed. Click a file to preview its chunks. For image knowledge bases, the system returns image lists.

   Note

   For document chunks stored in Milvus, set their status to Enabled or Disabled individually. Disabled chunks are not retrieved during searches.

   

4. Run a retrieval test. After updating the index, switch to the Recall Test tab. Enter a query and tune retrieval parameters to test performance.

   

5. Use the knowledge base in an application flow. After testing, retrieve information from the knowledge base in an application flow. In the knowledge base node, enable query rewriting and result reranking features and view the rewritten query in the execution trace.

   

   The result is a List[Dict]. Each Dict has content and score keys, representing the retrieved chunk and its similarity score with the query.

   [
     {
       "score": 0.8057173490524292,
       "content": "Due to the uncertainty caused by the pandemic, XX Bank proactively increased provisions for impairment losses on loans, advances, and non-credit assets based on economic trends and forecasts for China or the Chinese mainland. The bank also increased the write-off and disposal of non-performing assets to improve the provision coverage ratio. In 2020, the net profit reached 28.928 billion CNY, a year-on-year increase of 2.6%, and profitability gradually improved.\n(CNY in millions) 2020 2019 Change (%)\nOperating Results and Profitability\nOperating Income 153,542 137,958 11.3\nOperating Profit Before Impairment Losses 107,327 95,816 12.0\nNet Profit 28,928 28,195 2.6\nCost-to-Income Ratio(1)(%) 29.11 29.61 down 0.50 percentage points\nAverage Return on Total Assets (%) 0.69 0.77 down 0.08 percentage points\nWeighted Average Return on Equity (%) 9.58 11.30 down 1.72 percentage points\nNet Interest Margin(2)(%) 2.53 2.62 down 0.09 percentage points\nNote: (1) Cost-to-Income Ratio = Business and management fees / Operating income.",
       "id": "49f04c4cb1d48cbad130647bd0d75f***1cf07c4aeb7a5d9a1f3bda950a6b86e",
       "metadata": {
         "page_label": "40",
         "file_name": "2021-02-04_XX_Insurance_Group_Co_Ltd_XX_China_XX_2020_Annual_Report.pdf",
         "file_path": "oss://my-bucket-name/datasets/chatglm-fintech/2021-02-04__XX_Insurance_Group_Co_Ltd__601318__China_XX__2020_Annual_Report.pdf",
         "file_type": "application/pdf",
         "file_size": 7982999,
         "creation_date": "2024-10-10",
         "last_modified_date": "2024-10-10"
       }
     },
     {
       "score": 0.7708036303520203,
       "content": "7.2 billion CNY, a year-on-year increase of 5.2%.\n2020\n(CNY in millions) Life and Health Insurance Business, Property and Casualty Insurance Business, Banking Business, Trust Business, Securities Business, Other Asset Management Business, Technology Business, Other Business and Consolidation Elimination, Group Consolidated\nNet profit attributable to shareholders of the parent company 95,018 16,083 16,766 2,476 2,959 5,737 7,936 (3,876) 143,099\nMinority interest 1,054 76 12,162 3 143 974 1,567 281 16,260\nNet profit (A) 96,072 16,159 28,928 2,479 3,102 6,711 9,503 (3,595) 159,359\nItems excluded:\n Short-term investment fluctuation(1)(B) 10,308 – – – – – – – 10,308\n Impact of discount rate change (C) (7,902) – – – – – – – (7,902)\n One-time significant items and others excluded by management as not part of daily operating income and expenditure (D) – – – – – – 1,282 – 1,282\nOperating profit (E=A-B-C-D) 93,666 16,159 28,928 2,479 3,102 6,711 8,221 (3,595) 155,670\nOperating profit attributable to shareholders of the parent company 92,672 16,",
       "id": "8066c16048bd722d030a85ee8b1***36d5f31624b28f1c0c15943855c5ae5c9f",
       "metadata": {
         "page_label": "19",
         "file_name": "2021-02-04_XX_Insurance_Group_Co_Ltd_XXX_China_XX_2020_Annual_Report.pdf",
         "file_path": "oss://my-bucket-name/datasets/chatglm-fintech/2021-02-04__XX_Insurance_Group_Co_Ltd__601318__China_XX__2020_Annual_Report.pdf",
         "file_type": "application/pdf",
         "file_size": 7982999,
         "creation_date": "2024-10-10",
         "last_modified_date": "2024-10-10"
       }
     }
   ]

Detailed features

Configure retrieval parameters

• Top K: Maximum number of relevant text chunks to retrieve from the knowledge base. Value range: 1 to 100.

• Score threshold: Similarity score threshold (0 to 1). Only chunks with scores above this threshold are returned. Higher values require higher similarity between text and query.

• Retrieval Pattern: Default is Dense (vector) retrieval. To use Hybrid retrieval (vector + keyword), the vector database must be Milvus 2.4.x or later, or Elasticsearch. For guidance on choosing a retrieval mode, see Select a retrieval mode.

• Metadata filter condition: Filters the search scope using metadata to improve accuracy. For more information, see Use metadata.

• Query rewrite: Uses an LLM to optimize a user's vague, colloquial, or context-dependent query, making it clearer, more complete, and more intentional to improve retrieval accuracy. For usage scenarios, see Query rewrite.

• Result Reranking: Uses a reranking model to reorder initial retrieval results, placing the most relevant results at the top. For usage scenarios, see Result Reranking.

  Note

  Result reranking requires a reranking model. Supported model service connection types: Model Studio, AI Search Open Platform Model Service, and General Reranker Model Service.

Optimize retrieval performance

FAQ