feat: Remove ModelType enums (#105)

GETTING_STARTED.md

@@ -2,7 +2,6 @@
 
 ## <a name='TableofContents'></a>Table of Contents
 
-<!-- vscode-markdown-toc -->
 * [Table of Contents](#table-of-contents)
 * [Installation](#installation)
 * [Gen AI Endpoint](#gen-ai-endpoint)
@@ -23,10 +22,13 @@
 ```bash
 pip install ibm-generative-ai
 ```
+
 #### <a name='KnownIssueFixes:'></a>Known Issue Fixes:
+
 - **[SSL Issue]** If you run into "SSL_CERTIFICATE_VERIFY_FAILED" please run the following code snippet here: [support](SUPPORT.md).
 
 ### <a name='Prerequisites'></a>Prerequisites
+
 Python version >= 3.9
 
 Pip version >= 22.0.1
@@ -71,13 +73,11 @@ creds = Credentials(api_key=my_api_key, api_endpoint=my_api_endpoint)
 
 ```
 
-
 ## <a name='Examples'></a>Examples
 
 There are a number of examples you can try in the [`examples/user`](examples/user) directory.
 Login to [workbench.res.ibm.com](https://workbench.res.ibm.com/) and get your GenAI API key. Then, create a `.env` file and assign the `GENAI_KEY` value as below example. [More information](#gen-ai-endpoint)
 
-
 ```ini
 GENAI_KEY=YOUR_GENAI_API_KEY
 # GENAI_API=GENAI_API_ENDPOINT << for a different endpoint
@@ -258,6 +258,7 @@ To learn more about logging in python, you can follow the tutorial [here](https:
 
 Since generating responses for a large number of prompts can be time-consuming and there could be unforeseen circumstances such as internet connectivity issues, here are some strategies
 to work with:
+
 - Start with a small number of prompts to prototype the code. You can enable logging as described above for debugging during prototyping.
 - Include exception handling in sensitive sections such as callbacks.
 - Checkpoint/save prompts and received responses periodically.
@@ -292,10 +293,13 @@ us if you want support for some framework as an extension or want to design an e
 ### <a name='LangChainExtension'></a>LangChain Extension
 
 Install the langchain extension as follows:
+
 ```bash
 pip install "ibm-generative-ai[langchain]"
 ```
+
 Currently the langchain extension allows IBM Generative AI models to be wrapped as Langchain LLMs and translation between genai PromptPatterns and LangChain PromptTemplates. Below are sample snippets
+
 ```python
 import os
 from dotenv import load_dotenv
@@ -327,13 +331,6 @@ print(langchain_model(template.format(question="What is life?")))
 print(genai_model.generate([pattern.sub("question", "What is life?")])[0].generated_text)
 ```
 
-## <a name='[Deprecated] Model Types'></a>[Deprecated] Model Types
-
-Model types can be imported from the [ModelType class](src/genai/schemas/models.py). If you want to use a model that is not included in this class, you can pass it as a string as exemplified [here](src/genai/schemas/models.py).
-
-Models can be selected by passing their string id to the Model class as exemplified [here](src/genai/schemas/models.py).
-
-
 ## <a name='Support'></a>Support
 
 Need help? Check out how to get [support](SUPPORT.md)

documentation/docs/source/rst_source/genai.schemas.rst

@@ -10,7 +10,6 @@ Submodules
    genai.schemas.descriptions
    genai.schemas.generate_params
    genai.schemas.history_params
-   genai.schemas.models
    genai.schemas.responses
    genai.schemas.token_params
    genai.schemas.tunes_params

examples/dev/async-flaky-request-handler.py

@@ -7,7 +7,7 @@
 from dotenv import load_dotenv
 
 from genai.model import Credentials, Model
-from genai.schemas import GenerateParams, ModelType, TokenParams
+from genai.schemas import GenerateParams, TokenParams
 from genai.services.connection_manager import ConnectionManager
 from genai.services.request_handler import RequestHandler
 
@@ -80,7 +80,7 @@ async def flaky_async_generate(
 tokenize_params = TokenParams(return_tokens=True)
 
 
-flan_ul2 = Model(ModelType.FLAN_UL2, params=generate_params, credentials=creds)
+flan_ul2 = Model("google/flan-ul2", params=generate_params, credentials=creds)
 prompts = ["Generate a random number > {}: ".format(i) for i in range(25)]
 for response in flan_ul2.generate_async(prompts, ordered=True):
     pass

examples/dev/async-flaky-responses-ordered.py

@@ -6,7 +6,7 @@
 from dotenv import load_dotenv
 
 from genai.model import Credentials, GenAiException, Model
-from genai.schemas import GenerateParams, ModelType, TokenParams
+from genai.schemas import GenerateParams, TokenParams
 from genai.services.async_generator import AsyncResponseGenerator
 
 num_requests = 0
@@ -83,7 +83,7 @@ def tokenize_async(self, prompts, ordered=False, callback=None, options=None):
 tokenize_params = TokenParams(return_tokens=True)
 
 
-flan_ul2 = FlakyModel(ModelType.FLAN_UL2_20B, params=generate_params, credentials=creds)
+flan_ul2 = FlakyModel("google/flan-ul2", params=generate_params, credentials=creds)
 prompts = ["Generate a random number > {}: ".format(i) for i in range(17)]
 print("======== Async Generate with ordered=True ======== ")
 counter = 0
@@ -97,7 +97,7 @@ def tokenize_async(self, prompts, ordered=False, callback=None, options=None):
 num_requests = 0
 
 # Instantiate a model proxy object to send your requests
-flan_ul2 = FlakyModel(ModelType.FLAN_UL2_20B, params=tokenize_params, credentials=creds)
+flan_ul2 = FlakyModel("google/flan-ul2", params=tokenize_params, credentials=creds)
 prompts = ["Generate a random number > {}: ".format(i) for i in range(23)]
 print("======== Async Tokenize with ordered=True ======== ")
 counter = 0

examples/dev/generate-all-models.py

@@ -3,7 +3,7 @@
 from dotenv import load_dotenv
 
 from genai.model import Credentials, Model
-from genai.schemas import GenerateParams, ModelType
+from genai.schemas import GenerateParams
 
 # make sure you have a .env file under genai root with
 # GENAI_KEY=<your-genai-key>
@@ -24,7 +24,8 @@
     " during iteration it will do symb1 symb1 symb1 due to how it"
     " maps internally. ===="
 )
-for key, modelid in ModelType.__members__.items():
+for model_card in Model.models(credentials=creds):
+    modelid = model_card.id
     model = Model(modelid, params=params, credentials=creds)
     responses = [response.generated_text for response in model.generate(prompts)]
     print(modelid, ":", responses)

examples/dev/logging_example.py

@@ -4,7 +4,7 @@
 from dotenv import load_dotenv
 
 from genai.model import Credentials, Model
-from genai.schemas import GenerateParams, ModelType
+from genai.schemas import GenerateParams
 
 logging.basicConfig(level=logging.INFO)
 
@@ -22,7 +22,7 @@
 params = GenerateParams(decoding_method="sample", max_new_tokens=10)
 
 # Instantiate a model proxy object to send your requests
-flan_ul2 = Model(ModelType.FLAN_UL2, params=params, credentials=creds)
+flan_ul2 = Model("google/flan-ul2", params=params, credentials=creds)
 
 prompts = ["Hello! How are you?", "How's the weather?"]
 for response in flan_ul2.generate_async(prompts):

examples/user/prompt_templating/watsonx-prompt-output.py

@@ -2,9 +2,10 @@
 
 from dotenv import load_dotenv
 
-from genai.model import Credentials, Model
+from genai.credentials import Credentials
+from genai.model import Model
 from genai.prompt_pattern import PromptPattern
-from genai.schemas import GenerateParams, ModelType
+from genai.schemas import GenerateParams
 
 # make sure you have a .env file under genai root with
 # GENAI_KEY=<your-genai-key>
@@ -15,7 +16,7 @@
 creds = Credentials(api_key, api_endpoint=api_url)
 params = GenerateParams(temperature=0.5)
 
-model = Model(ModelType.FLAN_UL2, params=params, credentials=creds)
+model = Model("google/flan-ul2", params=params, credentials=creds)
 
 
 _template = """

examples/user/prompt_templating/watsonx-prompt-pattern-ux-async.py

@@ -3,10 +3,11 @@
 
 from dotenv import load_dotenv
 
-from genai.model import Credentials, Model
+from genai.credentials import Credentials
+from genai.model import Model
 from genai.options import Options
 from genai.prompt_pattern import PromptPattern
-from genai.schemas import GenerateParams, ModelType
+from genai.schemas import GenerateParams
 
 # make sure you have a .env file under genai root with
 # GENAI_KEY=<your-genai-key>
@@ -18,7 +19,7 @@
 creds = Credentials(api_key, api_endpoint=api_url)
 params = GenerateParams(temperature=0.5)
 
-model = Model(ModelType.FLAN_UL2, params=params, credentials=creds)
+model = Model("google/flan-ul2", params=params, credentials=creds)
 
 
 _template = """

examples/user/prompt_templating/watsonx-prompt-pattern-ux.py

@@ -3,10 +3,11 @@
 
 from dotenv import load_dotenv
 
-from genai.model import Credentials, Model
+from genai.credentials import Credentials
+from genai.model import Model
 from genai.options import Options
 from genai.prompt_pattern import PromptPattern
-from genai.schemas import GenerateParams, ModelType
+from genai.schemas import GenerateParams
 
 # make sure you have a .env file under genai root with
 # GENAI_KEY=<your-genai-key>
@@ -18,7 +19,7 @@
 creds = Credentials(api_key, api_endpoint=api_url)
 params = GenerateParams(temperature=0.5)
 
-model = Model(ModelType.FLAN_UL2, params=params, credentials=creds)
+model = Model("google/flan-ul2", params=params, credentials=creds)
 
 
 _template = """

src/genai/extensions/langchain/llm.py

@@ -1,6 +1,6 @@
 """Wrapper around IBM GENAI APIs for use in langchain"""
 import logging
-from typing import Any, List, Mapping, Optional, Union
+from typing import Any, List, Mapping, Optional
 
 from pydantic import BaseModel, Extra
 
@@ -11,7 +11,7 @@
     raise ImportError("Could not import langchain: Please install ibm-generative-ai[langchain] extension.")
 
 from genai import Credentials, Model
-from genai.schemas import GenerateParams, ModelType
+from genai.schemas import GenerateParams
 
 logger = logging.getLogger(__name__)
 
@@ -28,11 +28,11 @@ class LangChainInterface(LLM, BaseModel):
     parameter, which is an instance of GenerateParams.
     Example:
         .. code-block:: python
-            llm = LangChainInterface(model=ModelType.FLAN_UL2, credentials=creds)
+            llm = LangChainInterface(model="google/flan-ul2", credentials=creds)
     """
 
     credentials: Credentials = None
-    model: Optional[Union[ModelType, str]] = None
+    model: Optional[str] = None
     params: Optional[GenerateParams] = None
 
     class Config:
@@ -63,7 +63,7 @@ def _call(self, prompt: str, stop: Optional[List[str]] = None) -> str:
             The string generated by the model.
         Example:
             .. code-block:: python
-                llm = LangChainInterface(model_id=ModelType.FLAN_UL2, credentials=creds)
+                llm = LangChainInterface(model_id="google/flan-ul2", credentials=creds)
                 response = llm("What is a molecule")
         """
         params = self.params or GenerateParams()

src/genai/model.py

@@ -10,7 +10,7 @@
 from genai.metadata import Metadata
 from genai.options import Options
 from genai.prompt_pattern import PromptPattern
-from genai.schemas import GenerateParams, ModelType, TokenParams
+from genai.schemas import GenerateParams, TokenParams
 from genai.schemas.responses import (
     GenerateResponse,
     GenerateResult,
@@ -38,14 +38,14 @@ class Model:
 
     def __init__(
         self,
-        model: Union[ModelType, str],
+        model: str,
         params: Union[GenerateParams, TokenParams, Any] = None,
         credentials: Credentials = None,
     ):
         """Instantiates the Model Interface
 
         Args:
-            model (Union[ModelType, str]): The type of model to use
+            model (str): The type of model to use
             params (Union[GenerateParams, TokenParams]): Parameters to use during generate requests
             credentials (Credentials): The API Credentials
         """

src/genai/schemas/__init__.py

@@ -7,7 +7,6 @@
     ReturnOptions,
 )
 from genai.schemas.history_params import HistoryParams
-from genai.schemas.models import ModelType
 from genai.schemas.responses import GenerateResult, TokenizeResult
 from genai.schemas.token_params import TokenParams
 from genai.schemas.tunes_params import (
@@ -24,7 +23,6 @@
     "ReturnOptions",
     "TokenParams",
     "HistoryParams",
-    "ModelType",
     "GenerateResult",
     "TokenizeResult",
     "FileListParams",

src/genai/schemas/responses.py

@@ -6,7 +6,6 @@
 from pydantic import BaseModel, Extra, root_validator
 
 from genai.schemas.generate_params import GenerateParams
-from genai.schemas.models import ModelType
 
 logger = logging.getLogger(__name__)
 
@@ -76,7 +75,7 @@ class GenerateResult(GenAiResponseModel):
 
 
 class GenerateResponse(GenAiResponseModel):
-    model_id: Union[ModelType, str]
+    model_id: str
     created_at: datetime
     results: List[GenerateResult]
 
@@ -98,7 +97,7 @@ class TokenizeResult(GenAiResponseModel):
 
 
 class TokenizeResponse(GenAiResponseModel):
-    model_id: Union[ModelType, str]
+    model_id: str
     created_at: datetime
     results: List[TokenizeResult]
 

src/genai/services/async_generator.py

@@ -21,7 +21,7 @@ def __init__(
         """Instantiates the ConcurrentWrapper Interface.
 
         Args:
-            model_id (ModelType): The type of model to use
+            model_id (str): The type of model to use
             prompts (list): List of prompts
             params (GenerateParams): Parameters to use during generate requests
             service (ServiceInterface): The service interface