Add litellm docs. (#2058)

docs/config/models.md

@@ -8,9 +8,38 @@ GraphRAG was built and tested using OpenAI models, so this is the default model
 
 GraphRAG also utilizes a language model wrapper library used by several projects within our team, called fnllm. fnllm provides two important functions for GraphRAG: rate limiting configuration to help us maximize throughput for large indexing jobs, and robust caching of API calls to minimize consumption on repeated indexes for testing, experimentation, or incremental ingest. fnllm uses the OpenAI Python SDK under the covers, so OpenAI-compliant endpoints are a base requirement out-of-the-box.
 
+Starting with version 2.6.0, GraphRAG supports using [LiteLLM](https://docs.litellm.ai/) instead of fnllm for calling language models. LiteLLM provides support for 100+ models though it is important to note that when choosing a model it must support returning [structured outputs](https://openai.com/index/introducing-structured-outputs-in-the-api/) adhering to a [JSON schema](https://docs.litellm.ai/docs/completion/json_mode). 
+
+Example using LiteLLm as the language model tool for GraphRAG:
+
+```yaml
+models:
+  default_chat_model:
+    type: chat
+    auth_type: api_key
+    api_key: ${GEMINI_API_KEY}
+    model_provider: gemini
+    model: gemini-2.5-flash-lite
+  default_embedding_model:
+    type: embedding
+    auth_type: api_key
+    api_key: ${GEMINI_API_KEY}
+    model_provider: gemini
+    model: gemini-embedding-001
+```
+
+To use LiteLLM one must 
+
+- Set `type` to either `chat` or `embedding`.
+- Provide a `model_provider`, e.g., `openai`, `azure`, `gemini`, etc.
+- Set the `model` to a one supported by the `model_provider`'s API.
+- Provide a `deployment_name` if using `azure` as the `model_provider`.
+
+See [Detailed Configuration](yaml.md) for more details on configuration. [View LiteLLm basic usage](https://docs.litellm.ai/docs/#basic-usage) for details on how models are called (The `model_provider` is the portion prior to `/` while the `model` is the portion following the `/`).
+
 ## Model Selection Considerations
 
-GraphRAG has been most thoroughly tested with the gpt-4 series of models from OpenAI, including gpt-4 gpt-4-turbo, gpt-4o, and gpt-4o-mini. Our [arXiv paper](https://arxiv.org/abs/2404.16130), for example, performed quality evaluation using gpt-4-turbo.
+GraphRAG has been most thoroughly tested with the gpt-4 series of models from OpenAI, including gpt-4 gpt-4-turbo, gpt-4o, and gpt-4o-mini. Our [arXiv paper](https://arxiv.org/abs/2404.16130), for example, performed quality evaluation using gpt-4-turbo. As stated above, non-OpenAI models are now supported with GraphRAG 2.6.0 and onwards through the use of LiteLLM but the suite of gpt-4 series of models from OpenAI remain the most tested and supported suite of models for GraphRAG.
 
 Versions of GraphRAG before 2.2.0 made extensive use of `max_tokens` and `logit_bias` to control generated response length or content. The introduction of the o-series of models added new, non-compatible parameters because these models include a reasoning component that has different consumption patterns and response generation attributes than non-reasoning models. GraphRAG 2.2.0 now supports these models, but there are important differences that need to be understood before you switch.
 
@@ -58,11 +87,11 @@ Another option would be to avoid using a language model at all for the graph ext
 
 ## Using Non-OpenAI Models
 
-As noted above, our primary experience and focus has been on OpenAI models, so this is what is supported out-of-the-box. Many users have requested support for additional model types, but it's out of the scope of our research to handle the many models available today. There are two approaches you can use to connect to a non-OpenAI model:
+As shown above, non-OpenAI models may be used via LiteLLM starting with GraphRAG version 2.6.0 but cases may still exist in which some users wish to use models not supported by LiteLLM. There are two approaches one can use to connect to unsupported models:
 
 ### Proxy APIs
 
-Many users have used platforms such as [ollama](https://ollama.com/) to proxy the underlying model HTTP calls to a different model provider. This seems to work reasonably well, but we frequently see issues with malformed responses (especially JSON), so if you do this please understand that your model needs to reliably return the specific response formats that GraphRAG expects. If you're having trouble with a model, you may need to try prompting to coax the format, or intercepting the response within your proxy to try and handle malformed responses.
+Many users have used platforms such as [ollama](https://ollama.com/) and [LiteLLM Proxy Server](https://docs.litellm.ai/docs/simple_proxy) to proxy the underlying model HTTP calls to a different model provider. This seems to work reasonably well, but we frequently see issues with malformed responses (especially JSON), so if you do this please understand that your model needs to reliably return the specific response formats that GraphRAG expects. If you're having trouble with a model, you may need to try prompting to coax the format, or intercepting the response within your proxy to try and handle malformed responses.
 
 ### Model Protocol
 

docs/config/yaml.md

@@ -41,7 +41,8 @@ models:
 
 - `api_key` **str** - The OpenAI API key to use.
 - `auth_type` **api_key|azure_managed_identity** - Indicate how you want to authenticate requests.
-- `type` **openai_chat|azure_openai_chat|openai_embedding|azure_openai_embedding|mock_chat|mock_embeddings** - The type of LLM to use.
+- `type` **chat**|**embedding**|**openai_chat|azure_openai_chat|openai_embedding|azure_openai_embedding|mock_chat|mock_embeddings** - The type of LLM to use.
+- `model_provider` **str|None** - The model provider to use, e.g., openai, azure, anthropic, etc. Required when `type == chat|embedding`. When `type == chat|embedding`, [LiteLLM](https://docs.litellm.ai/) is used under the hood which has support for calling 100+ models. [View LiteLLm basic usage](https://docs.litellm.ai/docs/#basic-usage) for details on how models are called (The `model_provider` is the portion prior to `/` while the `model` is the portion following the `/`). [View Language Model Selection](models.md) for more details and examples on using LiteLLM.
 - `model` **str** - The model name.
 - `encoding_model` **str** - The text encoding model to use. Default is to use the encoding model aligned with the language model (i.e., it is retrieved from tiktoken if unset).
 - `api_base` **str** - The API base url to use.