From 21aac545d9bb3e1cb950bafc4e89de18efc8fde7 Mon Sep 17 00:00:00 2001 From: writinwaters <93570324+writinwaters@users.noreply.github.com> Date: Tue, 28 May 2024 20:13:03 +0800 Subject: [PATCH] Expanded the supported LLM list (#960) ### What problem does this PR solve? _Briefly describe what this PR aims to solve. Include background context that will help reviewers understand the purpose of the PR._ ### Type of change - [x] Documentation Update --- docker/README.md | 2 +- docs/guides/llm_api_key_setup.md | 11 ++++++++--- docs/quickstart.md | 3 +++ docs/references/api.md | 8 ++++---- 4 files changed, 16 insertions(+), 8 deletions(-) diff --git a/docker/README.md b/docker/README.md index 9f3ee5d7..dc7e05bd 100644 --- a/docker/README.md +++ b/docker/README.md @@ -67,7 +67,7 @@ The serving IP and port inside the docker container. This is not updating until Newly signed-up users use LLM configured by this part. Otherwise, user need to configure his own LLM in *setting*. ### factory -The LLM suppliers. 'Tongyi-Qianwen', "OpenAI"， "Moonshot" and "ZHIPU-AI" are supported. +The LLM suppliers. "OpenAI"， "Tongyi-Qianwen", "ZHIPU-AI", "Moonshot", "DeepSeek", "Baichuan", and "VolcEngine" are supported. ### api_key The corresponding API key of your assigned LLM vendor. diff --git a/docs/guides/llm_api_key_setup.md b/docs/guides/llm_api_key_setup.md index 3477964d..07baa35c 100644 --- a/docs/guides/llm_api_key_setup.md +++ b/docs/guides/llm_api_key_setup.md @@ -10,10 +10,15 @@ You have two ways to input your LLM API key. ## Before Starting The System In **user_default_llm** of [service_conf.yaml](https://github.com/infiniflow/ragflow/blob/main/docker/service_conf.yaml), you need to specify LLM factory and your own _API_KEY_. -RagFlow supports the flowing LLM factory, and with more coming in the pipeline: +RAGFlow supports the flowing LLMs, with more coming in the pipeline: -> [OpenAI](https://platform.openai.com/login?launch), [Tongyi-Qianwen](https://dashscope.console.aliyun.com/model), -> [ZHIPU-AI](https://open.bigmodel.cn/), [Moonshot](https://platform.moonshot.cn/docs) +- [OpenAI](https://platform.openai.com/login?launch) +- [Tongyi-Qianwen](https://dashscope.console.aliyun.com/model), +- [ZHIPU-AI](https://open.bigmodel.cn/), +- [Moonshot](https://platform.moonshot.cn/docs) +- [DeepSeek](https://platform.deepseek.com/api-docs/) +- [Baichuan](https://www.baichuan-ai.com/home) +- [VolcEngine](https://www.volcengine.com/docs/82379) After sign in these LLM suppliers, create your own API-Key, they all have a certain amount of free quota. diff --git a/docs/quickstart.md b/docs/quickstart.md index 589d2931..ecf92c18 100644 --- a/docs/quickstart.md +++ b/docs/quickstart.md @@ -101,8 +101,11 @@ RAGFlow is a RAG engine, and it needs to work with an LLM to offer grounded, hal - OpenAI - Tongyi-Qianwen +- ZHIPU-AI - Moonshot - DeepSeek-V2 +- Baichuan +- VolcEngine > RAGFlow also supports deploying LLMs locally using Ollama or Xinference, but this part is not covered in this quick start guide. diff --git a/docs/references/api.md b/docs/references/api.md index 51145a3d..ec014212 100644 --- a/docs/references/api.md +++ b/docs/references/api.md @@ -108,13 +108,13 @@ This method retrieves the history of a specified conversation session. - `chunks` - `content_with_weight`: Content of the chunk. - `doc_name`: Name of the *hit* document. - - `img_id`: The image ID of the chunk. It is an optional field only for PDF, PPTX, and images. Call ['GET' /document/get/\](#get-document-content-or-image) to retrieve the image. + - `img_id`: The image ID of the chunk. It is an optional field only for PDF, PPTX, and images. Call ['GET' /document/get/\](#get-document-content) to retrieve the image. - positions: [page_number, [upleft corner(x, y)], [right bottom(x, y)]], the chunk position, only for PDF. - similarity: The hybrid similarity. - term_similarity: The keyword simimlarity. - vector_similarity: The embedding similarity. - `doc_aggs`: - - `doc_id`: ID of the *hit* document. Call ['GET' /document/get/\](#get-document-content-or-image) to retrieve the document. + - `doc_id`: ID of the *hit* document. Call ['GET' /document/get/\](#get-document-content) to retrieve the document. - `doc_name`: Name of the *hit* document. - `count`: The number of *hit* chunks in this document. @@ -235,13 +235,13 @@ This method retrieves from RAGFlow the answer to the user's latest question. - `chunks`: The retrieved chunks that contribute to the answer. - `content_with_weight`: Content of the chunk. - `doc_name`: Name of the *hit* document. - - `img_id`: The image ID of the chunk. It is an optional field only for PDF, PPTX, and images. Call ['GET' /document/get/\](#get-document-content-or-image) to retrieve the image. + - `img_id`: The image ID of the chunk. It is an optional field only for PDF, PPTX, and images. Call ['GET' /document/get/\](#get-document-content) to retrieve the image. - `positions`: [page_number, [upleft corner(x, y)], [right bottom(x, y)]], the chunk position, only for PDF. - `similarity`: The hybrid similarity. - `term_similarity`: The keyword simimlarity. - `vector_similarity`: The embedding similarity. - `doc_aggs`: - - `doc_id`: ID of the *hit* document. Call ['GET' /document/get/\](#get-document-content-or-image) to retrieve the document. + - `doc_id`: ID of the *hit* document. Call ['GET' /document/get/\](#get-document-content) to retrieve the document. - `doc_name`: Name of the *hit* document. - `count`: The number of *hit* chunks in this document.