centersl/librechat.ai
1
0
Fork 0
mirror of https://github.com/LibreChat-AI/librechat.ai.git synced 2026-03-27 10:48:32 +07:00
Code Issues Packages Projects Releases Wiki Activity

chore: Remove forcePrompt, add Moonshot Provider (#495)

Browse Source 
* docs: add Moonshot AI configuration documentation and update known endpoints list

* docs: remove forcePrompt configuration from various AI endpoint examples and documentation
This commit is contained in:
Danny Avila
2026-02-11 15:03:26 -05:00
committed by GitHub
parent 6903a90c65
commit 72a7a934ab
20 changed files with 41 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
pages/blog/2023-11-30_litellm.mdx
View File

@@ -268,7 +268,6 @@ custom:
titleModel: "gpt-3.5-turbo"
summarize: false
summaryModel: "gpt-3.5-turbo"
forcePrompt: false
modelDisplayLabel: "Lite LLM"
```

3
pages/docs/configuration/azure.mdx
View File

@@ -183,7 +183,6 @@ options={[
['serverless', 'boolean', 'Specifies if the group is a serverless inference chat completions endpoint from Azure Model Catalog, for which only a model identifier, baseURL, and apiKey are needed. For more info, see serverless inference endpoints.', 'serverless: true'],
['addParams', 'object', 'Adds or overrides additional parameters for Azure OpenAI API requests. Useful for specifying API-specific options as key-value pairs.', 'addParams: {temperature: 0.7}'],
['dropParams', 'array', 'Allows for the exclusion of certain default parameters from Azure OpenAI API requests. Useful for APIs that do not accept or recognize specific parameters. This should be specified as a list of strings.', 'dropParams: [top_p, stop]'],
['forcePrompt', 'boolean', 'Dictates whether to send a prompt parameter instead of messages in the request body. This option is useful when needing to format the request in a manner consistent with OpenAI API expectations, particularly for scenarios preferring a single text payload.', 'forcePrompt: true'],
]}
/>
@@ -215,7 +214,6 @@ endpoints:
dropParams:
- "frequency_penalty"
- "presence_penalty"
forcePrompt: false
models:
# ... (model-level configurations)
```
@@ -583,4 +581,3 @@ endpoints:
- Compatibility with LibreChat relies on parity with OpenAI API specs, which at the time of writing, are typically **"Pay-as-you-go"** or "Models as a Service" (MaaS) deployments on Azure AI Studio, that are OpenAI-SDK-compatible with either `v1/completions` or `models/chat/completions` endpoint handling.
- All models that offer serverless deployments ("Serverless APIs") are compatible from the Azure model catalog. You can filter by "Serverless API" under Deployment options and "Chat completion" under inference tasks to see the full list; however, real time endpoint models have not been tested.
- These serverless inference endpoint/models may or may not support function calling according to OpenAI API specs, which enables their use with Agents.
- If using legacy "/v1/completions" (without "chat"), you need to set the `forcePrompt` field to `true` in your [group config.](#group-level-configuration)

1
pages/docs/configuration/librechat_yaml/ai_endpoints/anyscale.mdx
View File

@@ -24,7 +24,6 @@ description: Example configuration for Anyscale
titleModel: "meta-llama/Llama-2-7b-chat-hf"
summarize: false
summaryModel: "meta-llama/Llama-2-7b-chat-hf"
forcePrompt: false
modelDisplayLabel: "Anyscale"
```

1
pages/docs/configuration/librechat_yaml/ai_endpoints/fireworks.mdx
View File

@@ -25,7 +25,6 @@ description: Example configuration for Fireworks
titleModel: "accounts/fireworks/models/llama-v2-7b-chat"
summarize: false
summaryModel: "accounts/fireworks/models/llama-v2-7b-chat"
forcePrompt: false
modelDisplayLabel: "Fireworks"
dropParams: ["user"]
```

1
pages/docs/configuration/librechat_yaml/ai_endpoints/litellm.mdx
View File

@@ -21,7 +21,6 @@ description: Example configuration for LiteLLM
titleModel: "gpt-3.5-turbo"
summarize: false
summaryModel: "gpt-3.5-turbo"
forcePrompt: false
modelDisplayLabel: "LiteLLM"
```

1
pages/docs/configuration/librechat_yaml/ai_endpoints/mlx.mdx
View File

@@ -27,7 +27,6 @@ description: Example configuration for Apple MLX
titleModel: "current_model"
summarize: false
summaryModel: "current_model"
forcePrompt: false
modelDisplayLabel: "Apple MLX"
addParams:
max_tokens: 2000

25
pages/docs/configuration/librechat_yaml/ai_endpoints/moonshot.mdx Normal file
View File

@@ -0,0 +1,25 @@
---
title: Moonshot
description: Example configuration for Moonshot AI (Kimi)
---
# [Moonshot](https://www.moonshot.ai/)
> Moonshot API key: [platform.moonshot.cn](https://platform.moonshot.ai)
**Notes:**
- **Known:** icon provided.
- **Important:** For models with reasoning/thinking capabilities (e.g., `kimi-k2.5`, `kimi-k2-thinking`), the endpoint `name` **must** be set to `"Moonshot"` (case-insensitive) for interleaved reasoning to work correctly with tool calls. Using a different name will result in errors like `thinking is enabled but reasoning_content is missing in assistant tool call message`. See [Moonshot's documentation](https://platform.moonshot.ai/docs/guide/use-kimi-k2-thinking-model#frequently-asked-questions) for more details.
```yaml filename="librechat.yaml"
- name: "Moonshot"
apiKey: "${MOONSHOT_API_KEY}"
baseURL: "https://api.moonshot.ai/v1"
models:
default: ["kimi-k2.5"]
fetch: true
titleConvo: true
titleModel: "current_model"
modelDisplayLabel: "Moonshot"
```

1
pages/docs/configuration/librechat_yaml/ai_endpoints/neurochain.mdx
View File

@@ -26,7 +26,6 @@ description: Example configuration for NeurochainAI
titleModel: "current_model"
summarize: false
summaryModel: "current_model"
forcePrompt: false
modelDisplayLabel: "NeurochainAI"
iconURL: "https://raw.githubusercontent.com/LibreChat-AI/librechat-config-yaml/refs/heads/main/icons/NeurochainAI.png"
```

2
pages/docs/configuration/librechat_yaml/ai_endpoints/ollama.mdx
View File

@@ -36,7 +36,6 @@ description: Example configuration for Ollama
titleModel: "current_model"
summarize: false
summaryModel: "current_model"
forcePrompt: false
modelDisplayLabel: "Ollama"
```
@@ -60,7 +59,6 @@ However, in case you experience the behavior where `llama3` does not stop genera
titleModel: "current_model"
summarize: false
summaryModel: "current_model"
forcePrompt: false
modelDisplayLabel: "Ollama"
addParams:
"stop": [

1
pages/docs/configuration/librechat_yaml/ai_endpoints/perplexity.mdx
View File

@@ -32,7 +32,6 @@ description: Example configuration for Perplexity
titleModel: "llama-3-sonar-small-32k-chat"
summarize: false
summaryModel: "llama-3-sonar-small-32k-chat"
forcePrompt: false
dropParams: ["stop", "frequency_penalty"]
modelDisplayLabel: "Perplexity"
```

2
pages/docs/configuration/librechat_yaml/ai_endpoints/portkey.mdx
View File

@@ -33,7 +33,6 @@ description: Example configuration for Portkey AI
titleModel: "current_model"
summarize: false
summaryModel: "current_model"
forcePrompt: false
modelDisplayLabel: "Portkey:OpenAI"
iconURL: https://images.crunchbase.com/image/upload/c_pad,f_auto,q_auto:eco,dpr_1/rjqy7ghvjoiu4cd1xjbf
```
@@ -55,7 +54,6 @@ description: Example configuration for Portkey AI
titleModel: "current_model"
summarize: false
summaryModel: "current_model"
forcePrompt: false
modelDisplayLabel: "Portkey:Llama"
iconURL: https://images.crunchbase.com/image/upload/c_pad,f_auto,q_auto:eco,dpr_1/rjqy7ghvjoiu4cd1xjbf
```

1
pages/docs/configuration/librechat_yaml/ai_endpoints/shuttleai.mdx
View File

@@ -24,7 +24,6 @@ description: Example configuration for ShuttleAI
titleModel: "shuttle-2.5-mini"
summarize: false
summaryModel: "shuttle-2.5-mini"
forcePrompt: false
modelDisplayLabel: "ShuttleAI"
dropParams: ["user", "stop"]
```

1
pages/docs/configuration/librechat_yaml/ai_endpoints/togetherai.mdx
View File

@@ -168,6 +168,5 @@ with open("models_togetherai.json", "w") as file:
titleModel: "togethercomputer/llama-2-7b-chat"
summarize: false
summaryModel: "togethercomputer/llama-2-7b-chat"
forcePrompt: false
modelDisplayLabel: "together.ai"
```

1
pages/docs/configuration/librechat_yaml/ai_endpoints/truefoundry.mdx
View File

@@ -25,7 +25,6 @@ To use [TrueFoundry's AI Gateway](https://www.truefoundry.com/ai-gateway) follow
titleModel: "current_model"
summarize: false
summaryModel: "current_model"
forcePrompt: false
modelDisplayLabel: "TrueFoundry:OpenAI"
```
For more details you can check: [TrueFoundry Docs](https://docs.truefoundry.com/docs/introduction)

1
pages/docs/configuration/librechat_yaml/ai_endpoints/vllm.mdx
View File

@@ -27,7 +27,6 @@ description: Example configuration for vLLM
titleMessageRole: "user"
summarize: false
summaryModel: "current_model"
forcePrompt: false
```
The configuration above connects LibreChat to a local vLLM server running on port 8023. It uses the Gemma 3 27B model as the default model, but will fetch all available models from your vLLM server.

1
pages/docs/configuration/librechat_yaml/ai_endpoints/xai.mdx
View File

@@ -23,7 +23,6 @@ description: Example configuration for xAI
titleModel: "grok-beta"
summarize: false
summaryModel: "grok-beta"
forcePrompt: false
modelDisplayLabel: "Grok"
```

9
pages/docs/configuration/librechat_yaml/example.mdx
View File

@@ -45,7 +45,6 @@ endpoints:
titleModel: "meta-llama/Llama-2-7b-chat-hf"
summarize: false
summaryModel: "meta-llama/Llama-2-7b-chat-hf"
forcePrompt: false
modelDisplayLabel: "Anyscale"
# APIpie
@@ -99,7 +98,6 @@ endpoints:
titleModel: "accounts/fireworks/models/llama-v2-7b-chat"
summarize: false
summaryModel: "accounts/fireworks/models/llama-v2-7b-chat"
forcePrompt: false
modelDisplayLabel: "Fireworks"
dropParams: ["user"]
@@ -148,7 +146,6 @@ endpoints:
titleModel: "gpt-3.5-turbo"
summarize: false
summaryModel: "gpt-3.5-turbo"
forcePrompt: false
modelDisplayLabel: "OpenRouter"
# Perplexity
@@ -168,7 +165,6 @@ endpoints:
titleModel: "sonar-medium-chat"
summarize: false
summaryModel: "sonar-medium-chat"
forcePrompt: false
dropParams: ["stop", "frequency_penalty"]
modelDisplayLabel: "Perplexity"
@@ -185,7 +181,6 @@ endpoints:
titleModel: "gemini-pro"
summarize: false
summaryModel: "llama-summarize"
forcePrompt: false
modelDisplayLabel: "ShuttleAI"
dropParams: ["user"]
@@ -245,7 +240,6 @@ endpoints:
titleModel: "togethercomputer/llama-2-7b-chat"
summarize: false
summaryModel: "togethercomputer/llama-2-7b-chat"
forcePrompt: false
modelDisplayLabel: "together.ai"
```
@@ -379,9 +373,6 @@ endpoints:
# Summary Model: Specify the model to use if summarization is enabled.
# summaryModel: "mistral-tiny" # Defaults to "gpt-3.5-turbo" if omitted.
# Force Prompt setting: If true, sends a `prompt` parameter instead of `messages`.
# forcePrompt: false
# The label displayed for the AI model in messages.
modelDisplayLabel: 'Mistral' # Default is "AI" when not set.

16
pages/docs/configuration/librechat_yaml/object_structure/azure_openai.mdx
View File

@@ -228,22 +228,6 @@ addParams:
dropParams: ["stop", "user", "frequency_penalty", "presence_penalty"]
```
### forcePrompt
**Key:**
<OptionTable
options={[
['forcePrompt', 'Boolean', 'If `true`, sends a `prompt` parameter instead of `messages`. This combines all messages into a single text payload, following OpenAI format, and uses the `/completions` endpoint of your baseURL rather than `/chat/completions`.', ''],
]}
/>
**Default:** Not specified
**Example:**
```yaml filename="endpoints / azureOpenAI / groups / {group_item} / forcePrompt"
forcePrompt: false
```
### models
**Key:**

41
pages/docs/configuration/librechat_yaml/object_structure/custom_endpoint.mdx
View File

@@ -110,18 +110,25 @@ iconURL: https://github.com/danny-avila/LibreChat/raw/main/docs/assets/LibreChat
* If you want to use existing project icons, define the endpoint `name` as one of the main endpoints (case-sensitive):
- "openAI" | "azureOpenAI" | "google" | "anthropic" | "assistants" | "gptPlugins"
* There are also "known endpoints" (case-insensitive), which have icons provided. If your endpoint `name` matches the following names, you should omit this field:
- "Mistral"
- "Deepseek"
- "OpenRouter"
- "groq"
- "APIpie"
- "Anyscale"
- "APIpie"
- "Cohere"
- "Deepseek"
- "Fireworks"
- "Perplexity"
- "together.ai"
- "ollama"
- "xai"
- "groq"
- "Helicone"
- "Huggingface"
- "Mistral"
- "MLX"
- "Moonshot"
- "ollama"
- "OpenRouter"
- "Perplexity"
- "Qwen"
- "ShuttleAI"
- "together.ai"
- "Unify"
- "xai"
## models
@@ -361,22 +368,6 @@ summarize: false
summaryModel: "mistral-tiny"
```
## forcePrompt
**Key:**
<OptionTable
options={[
['forcePrompt', 'Boolean', 'If `true`, sends a `prompt` parameter instead of `messages`.', 'Combines all messages into a single text payload or "prompt", following OpenAI format, which uses the `/completions` endpoint of your baseURL rather than `/chat/completions`.'],
]}
/>
**Default:** `false`
**Example:**
```yaml filename="endpoints / custom / forcePrompt"
forcePrompt: false
```
## modelDisplayLabel
**Key:**

1
pages/docs/quick_start/custom_endpoints.mdx
View File

@@ -53,7 +53,6 @@ services:
titleModel: "current_model"
summarize: false
summaryModel: "current_model"
forcePrompt: false
modelDisplayLabel: "OpenRouter"
- name: "Ollama"
apiKey: "ollama"