GPTCache · Issues· 99 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #694
Similarity-evaluation test suite has no polarity cases: a query and its exact reversal clear the 0.8 hit threshold, so the cache serves the answer to the opposite question.
Updated Aug 31, 2026 - #600
[Bug]: benchmark script
Updated Aug 30, 2026 - #684
[Bug]: File and image cache keys collide because BufferedReader.peek() only reads the buffered prefix
Updated Jul 28, 2026 - #687
[Security] Unsafe YAML Deserialization leads to Remote Code Execution
Updated Jul 18, 2026 - #593
[Bug]: fail in chatComplete for gptcache.adapter openai
Updated Jul 7, 2026 - #667
[Feature]: MultiAgentCacheManager
Updated Jun 21, 2026 - #676
[vulnerability]: Remote Code Execution (RCE) via Unsafe YAML Deserialization in GPTCache Server
Updated Jan 20, 2026 - #673
[Enhancement]: Valkey support in GPTCache as an alternative to Redis for vector store functionality
Updated Nov 7, 2025 - #666
Horizontal scaling deployment causes PGVector violates unique key constraint
Updated Aug 14, 2025 - #612
[Bug]: Gptcache server: with OpenAi embedding cache seems to be not working properly.
Updated May 6, 2025 - #662
Getting Error during processing: BaseChatModel.__call__() missing 1 required positional argument: 'messages' eror
Updated Apr 21, 2025 - #658
[Bug]: Alternatively, you can pin your installation to the old version, e.g. `pip install openai==0.28`
Updated Dec 16, 2024 - #632
[Enhancement]: Remove vector data when the corresponding cache data expires in cache storage
Updated Nov 4, 2024 - #570
[Bug]: GPTCache Server and Libraries Failed for openai==1.0.0
Updated Oct 27, 2024 - #657
[Bug]: Support for GPT4o-mini or gpt4- models
Updated Oct 17, 2024