Update docs

CONTRIBUTING.md

@@ -14,22 +14,20 @@ pip install -r requirements-dev.txt
 ## Dev Flow
 After making your changes, please make a PR to get your changes merged upstream.
 
-## Running vLLM Models
-To use vLLM for model serving, you just need to make an OpenAI compatible vLLM server. Then, the `OpenAIModel` class can be used to point to the server. See an example below.
+## Running Models
+To run a model, you can use the `LM` class in `lotus.models.LM`. We use the `litellm` library to interface with the model.
+This allows you to use any model provider that is supported by `litellm`.
 
-Create the server
+Here's an example of creating an `LM` object for `gpt-4o`
 ```
-python -m vllm.entrypoints.openai.api_server --model meta-llama/Meta-Llama-3.1-70B-Instruct --port 8000 --tensor-parallel-size 8
+from lotus.models import LM
+lm = LM(model="gpt-4o")
 ```
 
-In LOTUS, you should instantiate your model as follows
+Here's an example of creating an `LM` object to use `llama3.2` on Ollama
 ```
-from lotus.models import OpenAIModel
-lm = OpenAIModel(
-    model="meta-llama/Meta-Llama-3.1-70B-Instruct",
-    api_base="http://localhost:8000/v1",
-    provider="vllm",
-)
+from lotus.models import LM
+lm = LM(model="ollama/llama3.2")
 ```
 
 ## Helpful Examples

README.md

@@ -45,10 +45,10 @@ If you're already familiar with Pandas, getting started will be a breeze! Below
 ```python
 import pandas as pd
 import lotus
-from lotus.models import OpenAIModel
+from lotus.models import LM
 
 # configure the LM, and remember to export your API key
-lm = OpenAIModel()
+lm = LM()
 lotus.settings.configure(lm=lm)
 
 # create dataframes with course names and skills

docs/quickstart.rst

@@ -50,10 +50,10 @@ This can be achieved by applying a semantic filter followed by a semantic aggreg
     import pandas as pd
 
     import lotus
-    from lotus.models import E5Model, OpenAIModel
+    from lotus.models import E5Model, LM
 
     # Configure models for LOTUS
-    lm = OpenAIModel(max_tokens=512)
+    lm = LM()
     rm = E5Model()
 
     lotus.settings.configure(lm=lm, rm=rm)
@@ -90,7 +90,7 @@ If we wanted the challenge of taking courses with a high workload, we can also u
 
 .. code-block:: python
 
-    top_2_hardest = df.sem_topk("What {Description} indicates the highest workload?", 2)
+    top_2_hardest = df.sem_topk("What {Description} indicates the highest workload?", K=2)
 
 LOTUS's semantic join operator can be used to join two dataframes based on a predicate.
 Suppose we had a second dataframe containing skills we wanted to get better at (SQL and Chip Design in our case).
@@ -113,7 +113,7 @@ Let's create a semantic index on the course description column and then search f
 
     # Create a semantic index on the description column and save it to the index_dir directory
     df = df.sem_index("Description", "index_dir")
-    top_conv_df = df.sem_search("Description", "Convolutional Neural Network", 1)
+    top_conv_df = df.sem_search("Description", "Convolutional Neural Network", K=1)
 
 Another useful operator is the semantic map operator. Let's see how it can be used to get some next topics to explore for each class.
 Additionally, let's provide some examples to the model that can be used for demonstrations.