> For the complete documentation index, see [llms.txt](https://changelog.graphlit.dev/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://changelog.graphlit.dev/december-2023/december-10-support-for-openai-gpt-4-turbo-llama-2-and-mistral-models-query-by-example-bug-fixes.md).

# December 10: Support for OpenAI GPT-4 Turbo, Llama 2 and Mistral models; query by example, bug fixes

### New Features

* :bulb: Graphlit now supports the [OpenAI GPT-4 Turbo 128k](https://openai.com/research/gpt-4v-system-card) model, both in Azure OpenAI and native OpenAI services.  Added new model enum `GPT4_TURBO_VISION_128K`.
* :bulb: Graphlit now supports Llama 2 7b, 13b, 70b models and Mistral 7b model, via [Replicate](https://replicate.com/).  Developers can use their own Replicate API key, or be charged as credits for Graphlit usage.
* :bulb: Graphlit now supports the [Anthropic Claude 2.1](https://www.anthropic.com/index/claude-2-1) model. Added new model enum `CLAUDE_2_1`.
* :bulb: Graphlit now supports the [OpenAI GPT-4 Vision](https://openai.com/research/gpt-4v-system-card) model for image descriptions and text extraction.  Added new model enum `GPT4_TURBO_VISION_128K`. See usage example in ["Multimodal RAG" blog post](https://www.graphlit.com/blog/multimodal-rag-insurance-insights).
* Added query by example to `contents` query.  Developers can specify one or more example contents, and query will use vector embeddings to return similar contents.
* Added query by example to `conversations` query.  Developers can specify one or more example conversations, and query will use vector embeddings to return similar conversations.
* Added vector search support for `conversations` queries.  Developers can provide search text which will use vector embeddings to return similar conversations.
* Added `promptSpecifications` mutation for directly prompting multiple models.  This can be used to evaluate prompts against multiple models or compare different specification parameters in parallel.
* Added `promptStrategy` field to Specification, which supports multiple strategy types for preprocessing the prompt before being sent to the LLM model.  For example, `REWRITE` prompt strategy will ask LLM to rewrite the incoming user prompt based on the previous conversation messages.
* Added `suggestConversation` mutation, which returns a list of suggested followup questions based on the specified conversation and related contents.  This can be used to auto-suggest questions for chatbot users.
* Added new summarization types: `CHAPTERS`, `QUESTIONS` and `POSTS`.   See usage examples in the ["LLMs for Podcasters" blog post](https://www.graphlit.com/blog/llms-for-podcasters).
* Added versioned model enums such as `GPT4_0613` and `GPT35_TURBO_16K_1106`.  Without version specified, such as `GPT35_TURBO_16K`, Graphlit will use the latest production model version, as defined by the LLM vendor.
* Added `lookupContents` query to get multiple contents by id in one query.
* :zap: In Content type, `headline` field was renamed to `headlines` and now returns an array of strings.
* :zap: Entity names are now limited to 1024 characters.  Names will be truncated if they exceed the maximum length.
* :zap: In SummarizationTypes enum, `BULLET_POINTS` was renamed to `BULLETS`.
* :zap: In ProjectStorage type, `originalTotalSize` was renamed to `totalSize`, and `totalRenditionSize` field was added.  `totalSize` is the sum of the ingested source file sizes, and `totalRenditionSize` is the sum of the source file sizes and any derived rendition sizes.
* :zap: In ConversationStrategy type, `strategyType` was renamed to `type` for consistency with rest of data model.
* :zap: In Specification type, `optimizeSearchConversation` was removed, and now is handled by `OPTIMIZE_SEARCH` prompt strategy.

### Bugs Fixed

* GPLA-1725: Should ignore RSS.xml from web feed sitemap
* GPLA-1726: GPT-3.5 Turbo 16k LLM is adding "Citation #" to response
* GPLA-1698: Workflow not applied to link-crawled content
* GPLA-1692: Mismatched project storage total size, when some content has errored
* GPLA-1237: Add relevance threshold for semantic search