v0,5
版本发布时间: 2024-10-30 14:24:30
neo4j-labs/llm-graph-builder最新发布版本:v0,5(2024-10-30 14:24:30)
What's Changed
New Features
- Graph communities- - In a Neo4j Aura DS instance, graph communities (also called clusters, modules, or subgraphs) can be created. These are groups of interconnected nodes with denser internal connections than external connections. These communities are created to improve chatbot performance by organizing users into relevant groups. Users have the option to enable community creation across entities as part of the post processing job in the graph enhancement tab on UI. #721 , #728
- Global search full text - This new chat mode includes communities, full-text indexing, and global search. Full-text indexing speeds up searches by creating a searchable index of words and their locations within documents, eliminating the need to scan entire documents. This improves search speed, storage efficiency, and allows searching across multiple database columns. Global search leverages broader contextual understanding across the entire system for less specific queries, benefiting from connections between different data points. - #699
- Ragas Evaluation Metrics - RAGAs (Retrieval-Augmented Generation Assessment) is a framework that automatically evaluates RAG pipelines. Instead of relying on human-labeled data, it uses LLMs to assess component performance, providing scores for faithfulness (accuracy to source information) and answer relevancy (how well the answer addresses the question). RAGAs evaluation metrics are now provided as chatbot retrieval information. These scores help improve chatbot accuracy and helpfulness. #787, #806
- Read only user support - The application provides access to the read-only Neo4j database users. Users have the option to view graph data, access chat bot and chat history.#766
- Get neighborhood nodes -To dive deeper into the structure of a graph, get Neighbors retrieves nodes directly connected to a specified element. This can be particularly useful for exploring connections around a given node, allowing for focused data inspection within the larger graph. By providing the element ID, users can pinpoint a node and extract its neighboring nodes and relationships. Implemented text link (View Graph) for Retrieval information modal that holds information for Chunk and entities and in Graph enhancement model for Disconnected nodes and De duplication of nodes we are adding links to ID column. #796
- Download chat conversation - Export the current chat history in JSON format. This includes all messages, timestamps, and ideally, identifying information for each user (e.g., neo4j usernames or IDs). #800
- Updated Lang chain versions in https://github.com/neo4j-labs/llm-graph-builder/pull/565
Enhancements
- Retry Processing - Users can reprocess canceled, failed, or processed files. Options include starting from the beginning, deleting existing entities and starting over, or resuming from the last successful point (not available for completed files). Clicking "Generate graph" after selecting "Reprocess" begins processing. #698
- Post processing call after file completion - https://github.com/neo4j-labs/llm-graph-builder/pull/716/files#diff-b31aa7db705259a32218d462af23ecdc6369dbc7b67ff46e67204f696925c884 Changes to post processing call that will take place only if there are no files in the table with status processing or waiting or if all files are completed
- Multiple chat mode selection - The chat interface offers users a choice of several powerful search modes, allowing for highly customizable retrieval of information. Users can select one or more of the following modes: - Vector Search: A search based on semantic similarity, finding results conceptually similar to the query. - Full Text Search: A traditional keyword-based search, returning results containing the exact words or phrases in the query. - Graph + Vector + Full Text Search: A combined approach leveraging graph connections, semantic similarity (vector), and keyword matching (full text) for comprehensive results. - Entity Search + Vector Search: Focuses on identifying and retrieving specific entities (people, places, things) combined with semantic similarity. - Global Search + Vector + Full Text Search: A broad search encompassing all available data, utilizing communities, semantic similarity and keyword matching. The results from each selected mode are displayed separately and can be viewed by navigating between them using the arrow keys.#780
- Open AI/Gemini LLM configuration - Local application users can configure the large language model (LLM) by specifying the model name and API key. For Open AI models, this includes the model name (e.g., gpt-3.5-turbo-0125) and API key. For Gemini models, only the model name (e.g., gemini-1.5-flash-002) is needed. Configuration is done via environment variables, such as LLM_MODEL_CONFIG_openai_gpt_3.5 and LLM_MODEL_CONFIG_gemini_1.5_flash. #794
- Graph enhancements - Users have the option to search node and relationship labels when visualizing graphs. . When users click on either node or relationship in the graph, they can access detailed information about that node/relationship, such as its type, ID, and other relevant attributes.#795 , #699
- connection creation in extract and Cancelled Error handling for server side events in https://github.com/neo4j-labs/llm-graph-builder/pull/584
User Interface Improvements
- ref added for key down: Key down events to allow the user to submit any details if not interested to use mouse clicks. #717
- Improved database information presentation with UI icons. This indicates whether they are using GDS [Graph data science] instance or GD [Graph Database] instance . The GDS allows users to create communities.. #722.
- A comprehensively described chat mode menu to facilitate user comprehension. Added descriptions to chat modes that help users to understand what modes do what. #743
- Post processing alerts - Once all files have been processed, a message will inform the user that post-processing is underway and will be available shortly. A second message will appear when the Q&A functionalities are ready. #758
New Contributors
- @jeromechoo made their first contribution in https://github.com/neo4j-labs/llm-graph-builder/pull/659
- @Kain-90 made their first contribution in https://github.com/neo4j-labs/llm-graph-builder/pull/688
- @destiny966113 made their first contribution in https://github.com/neo4j-labs/llm-graph-builder/pull/697
Full Changelog: https://github.com/neo4j-labs/llm-graph-builder/compare/v0.4...v0,5