fix/pip install messages (#1095)

src/distilabel/models/embeddings/llamacpp.py

@@ -181,7 +181,7 @@ def load(self) -> None:
         except ImportError as ie:
             raise ImportError(
                 "`llama-cpp-python` package is not installed. Please install it using"
-                " `pip install llama-cpp-python`."
+                " `pip install 'distilabel[llama-cpp]'`."
             ) from ie
 
         if self.repo_id is not None:

src/distilabel/models/embeddings/sentence_transformers.py

@@ -110,7 +110,7 @@ def load(self) -> None:
         except ImportError as e:
             raise ImportError(
                 "`sentence-transformers` package is not installed. Please install it using"
-                " `pip install sentence-transformers`."
+                " `pip install 'distilabel[sentence-transformers]'`."
             ) from e
 
         self._model = SentenceTransformer(

src/distilabel/models/embeddings/vllm.py

@@ -93,7 +93,7 @@ def load(self) -> None:
 
         except ImportError as ie:
             raise ImportError(
-                "vLLM is not installed. Please install it using `pip install vllm`."
+                "vLLM is not installed. Please install it using `pip install 'distilabel[vllm]'`."
             ) from ie
 
         self._model = _vLLM(

src/distilabel/models/llms/anthropic.py

@@ -176,7 +176,7 @@ def load(self) -> None:
         except ImportError as ie:
             raise ImportError(
                 "Anthropic Python client is not installed. Please install it using"
-                " `pip install anthropic`."
+                " `pip install 'distilabel[anthropic]'`."
             ) from ie
 
         if self.api_key is None:

src/distilabel/models/llms/azure.py

@@ -131,7 +131,7 @@ def load(self) -> None:
         except ImportError as ie:
             raise ImportError(
                 "OpenAI Python client is not installed. Please install it using"
-                " `pip install openai`."
+                " `pip install 'distilabel[openai]'`."
             ) from ie
 
         if self.api_key is None:

src/distilabel/models/llms/groq.py

@@ -144,7 +144,7 @@ def load(self) -> None:
         except ImportError as ie:
             raise ImportError(
                 "Groq Python client is not installed. Please install it using"
-                ' `pip install groq` or from the extras as `pip install "distilabel[groq]"`.'
+                ' `pip install "distilabel[groq]"`.'
             ) from ie
 
         if self.api_key is None:

src/distilabel/models/llms/huggingface/inference_endpoints.py

@@ -262,7 +262,7 @@ def load(self) -> None:  # noqa: C901
         except ImportError as ie:
             raise ImportError(
                 "Hugging Face Hub Python client is not installed. Please install it using"
-                " `pip install huggingface-hub`."
+                " `pip install 'distilabel[hf-inference-endpoints]'`."
             ) from ie
 
         if self.api_key is None:
@@ -311,7 +311,7 @@ def load(self) -> None:  # noqa: C901
             except ImportError as ie:
                 raise ImportError(
                     "Transformers Python client is not installed. Please install it using"
-                    " `pip install transformers`."
+                    " `pip install 'distilabel[hf-inference-endpoints]'`."
                 ) from ie
 
             self._tokenizer = AutoTokenizer.from_pretrained(self.tokenizer_id)

src/distilabel/models/llms/huggingface/transformers.py

@@ -122,7 +122,7 @@ def load(self) -> None:
             from transformers import pipeline
         except ImportError as ie:
             raise ImportError(
-                "Transformers is not installed. Please install it using `pip install transformers`."
+                "Transformers is not installed. Please install it using `pip install 'distilabel[hf-transformers]'`."
             ) from ie
 
         token = self.token.get_secret_value() if self.token is not None else self.token

src/distilabel/models/llms/litellm.py

@@ -104,7 +104,7 @@ def load(self) -> None:
         except ImportError as e:
             raise ImportError(
                 "LiteLLM Python client is not installed. Please install it using"
-                " `pip install litellm`."
+                " `pip install 'distilabel[litellm]'`."
             ) from e
         self._aclient = litellm.acompletion
 

src/distilabel/models/llms/mistral.py

@@ -140,7 +140,7 @@ def load(self) -> None:
         except ImportError as ie:
             raise ImportError(
                 "MistralAI Python client is not installed. Please install it using"
-                " `pip install mistralai`."
+                " `pip install 'distilabel[mistralai]'`."
             ) from ie
 
         if self.api_key is None:

src/distilabel/models/llms/ollama.py

@@ -163,7 +163,7 @@ def load(self) -> None:
         except ImportError as e:
             raise ImportError(
                 "Ollama Python client is not installed. Please install it using"
-                " `pip install ollama`."
+                " `pip install 'distilabel[ollama]'`."
             ) from e
 
         if self.tokenizer_id:

src/distilabel/models/llms/openai.py

@@ -54,6 +54,7 @@ class OpenAILLM(AsyncLLM):
         api_key: the API key to authenticate the requests to the OpenAI API. Defaults to
             `None` which means that the value set for the environment variable `OPENAI_API_KEY`
             will be used, or `None` if not set.
+        default_headers: the default headers to use for the OpenAI API requests.
         max_retries: the maximum number of times to retry the request to the API before
             failing. Defaults to `6`.
         timeout: the maximum time in seconds to wait for a response from the API. Defaults
@@ -186,7 +187,7 @@ def load(self) -> None:
         except ImportError as ie:
             raise ImportError(
                 "OpenAI Python client is not installed. Please install it using"
-                " `pip install openai`."
+                " `pip install 'distilabel[openai]'`."
             ) from ie
 
         if self.api_key is None:

src/distilabel/models/llms/vertexai.py

@@ -89,7 +89,7 @@ def load(self) -> None:
         except ImportError as e:
             raise ImportError(
                 "vertexai is not installed. Please install it using"
-                " `pip install google-cloud-aiplatform`."
+                " `pip install 'distilabel[vertexai]'`."
             ) from e
 
         if _is_gemini_model(self.model):

src/distilabel/models/llms/vllm.py

@@ -189,7 +189,7 @@ def load(self) -> None:
             from vllm import LLM as _vLLM
         except ImportError as ie:
             raise ImportError(
-                "vLLM is not installed. Please install it using `pip install vllm`."
+                "vLLM is not installed. Please install it using `pip install 'distilabel[vllm]'`."
             ) from ie
 
         self._model = _vLLM(
@@ -585,7 +585,7 @@ def load(self) -> None:
         except ImportError as ie:
             raise ImportError(
                 "OpenAI Python client is not installed. Please install it using"
-                " `pip install openai`."
+                " `pip install 'distilabel[openai]'`."
             ) from ie
 
         self._client = OpenAI(
@@ -602,7 +602,7 @@ def load(self) -> None:
         except ImportError as ie:
             raise ImportError(
                 "To use `ClientvLLM` you need to install `transformers`."
-                "Please install it using `pip install transformers`."
+                "Please install it using `pip install 'distilabel[hf-transformers]'`."
             ) from ie
 
         self._tokenizer = AutoTokenizer.from_pretrained(

src/distilabel/pipeline/ray.py

@@ -204,7 +204,7 @@ def _init_ray(self) -> None:
             import ray
         except ImportError as ie:
             raise ImportError(
-                "ray is not installed. Please install it using `pip install ray[default]`."
+                "ray is not installed. Please install it using `pip install 'distilabel[ray]'`."
             ) from ie
 
         if self._ray_head_node_url:

src/distilabel/steps/argilla/base.py

@@ -94,8 +94,7 @@ def model_post_init(self, __context: Any) -> None:
 
         if importlib.util.find_spec("argilla") is None:
             raise ImportError(
-                "Argilla is not installed. Please install it using `pip install argilla"
-                " --upgrade`."
+                "Argilla is not installed. Please install it using `pip install 'distilabel[argilla]'`."
             )
 
     def _client_init(self) -> None:

src/distilabel/steps/clustering/dbscan.py

@@ -124,7 +124,7 @@ def load(self) -> None:
         super().load()
         if importlib.util.find_spec("sklearn") is None:
             raise ImportError(
-                "`sklearn` package is not installed. Please install it using `pip install scikit-learn`."
+                "`sklearn` package is not installed. Please install it using `pip install 'distilabel[text-clustering]'`."
             )
         from sklearn.cluster import DBSCAN as _DBSCAN
 

src/distilabel/steps/clustering/umap.py

@@ -112,7 +112,7 @@ def load(self) -> None:
         super().load()
         if importlib.util.find_spec("umap") is None:
             raise ImportError(
-                "`umap` package is not installed. Please install it using `pip install umap-learn`."
+                "`umap` package is not installed. Please install it using `pip install 'distilabel[text-clustering]'`."
             )
         from umap import UMAP as _UMAP
 

src/distilabel/steps/embeddings/nearest_neighbour.py

@@ -163,7 +163,7 @@ def load(self) -> None:
         if importlib.util.find_spec("faiss") is None:
             raise ImportError(
                 "`faiss` package is not installed. Please install it using `pip install"
-                " faiss-cpu` or `pip install faiss-gpu`."
+                " 'distilabel[faiss-cpu]' or 'distilabel[faiss-gpu]'`."
             )
 
     @property

src/distilabel/steps/filtering/_datasketch.py

@@ -43,7 +43,7 @@ def __init__(self, config, name) -> None:
         except ImportError as e:
             raise ImportError(
                 "`diskcache` is required for disk storage using `MinHashDedup`. "
-                "Please install it using `pip install diskcache`."
+                "Please install it using `pip install 'distilabel[minhash]'`."
             ) from e
 
         # Start with a clean file on each pipeline

src/distilabel/steps/filtering/minhash.py

@@ -176,7 +176,7 @@ def load(self) -> None:
         if not importlib.import_module("datasketch"):
             raise ImportError(
                 "`datasketch` is needed to deduplicate with MinHash, but is not installed. "
-                "Please install it using `pip install datasketch`."
+                "Please install it using `pip install 'distilabel[minhash]'`."
             )
         from datasketch import MinHash
 
@@ -193,7 +193,7 @@ def load(self) -> None:
             if not importlib.import_module("nltk"):
                 raise ImportError(
                     "`nltk` is needed to tokenize based on words, but is not installed. "
-                    "Please install it using `pip install nltk`. Then run `nltk.download('punkt_tab')`."
+                    "Please install it using `pip install 'distilabel[minhash]'`. Then run `nltk.download('punkt_tab')`."
                 )
             self._tokenizer = tokenized_on_words
         else:

src/distilabel/steps/reward_model.py

@@ -156,7 +156,7 @@ def load(self) -> None:
             from transformers import AutoModelForSequenceClassification, AutoTokenizer
         except ImportError as e:
             raise ImportError(
-                "`transformers` is not installed. Please install it using `pip install transformers`."
+                "`transformers` is not installed. Please install it using `pip install 'distilabel[hf-transformers]'`."
             ) from e
 
         token = self.token.get_secret_value() if self.token is not None else self.token

src/distilabel/steps/tasks/structured_outputs/instructor.py

@@ -109,7 +109,7 @@ def prepare_instructor(
     """
     if not importlib.util.find_spec("instructor"):
         raise ImportError(
-            "`instructor` is not installed. Please install it using `pip install instructor`."
+            "`instructor` is not installed. Please install it using `pip install 'distilabel[instructor]'`."
         )
     import instructor
 

src/distilabel/steps/tasks/structured_outputs/outlines.py

@@ -99,7 +99,7 @@ def prepare_guided_output(
     """
     if not importlib.util.find_spec("outlines"):
         raise ImportError(
-            "Outlines is not installed. Please install it using `pip install outlines`."
+            "Outlines is not installed. Please install it using `pip install 'distilabel[outlines]'`."
         )
 
     json_processor, regex_processor = _get_logits_processor(framework)

src/distilabel/steps/truncate.py

@@ -108,7 +108,7 @@ def load(self):
             if not importlib.util.find_spec("transformers"):
                 raise ImportError(
                     "`transformers` is needed to tokenize, but is not installed. "
-                    "Please install it using `pip install transformers`."
+                    "Please install it using `pip install 'distilabel[hf-transformers]'`."
                 )
 
             from transformers import AutoTokenizer

tests/unit/models/llms/test_anyscale.py

@@ -46,6 +46,7 @@ def test_serialization(self) -> None:
             "model": self.model_id,
             "generation_kwargs": {},
             "max_retries": 6,
+            "default_headers": None,
             "base_url": "https://api.endpoints.anyscale.com/v1",
             "timeout": 120,
             "structured_output": None,

tests/unit/models/llms/test_azure.py

@@ -71,6 +71,7 @@ def test_azure_openai_llm_env_vars(self) -> None:
                     "api_version": "preview",
                     "generation_kwargs": {},
                     "max_retries": 6,
+                    "default_headers": None,
                     "base_url": "https://example-resource.azure.openai.com/",
                     "timeout": 120,
                     "structured_output": None,
@@ -95,6 +96,7 @@ def test_azure_openai_llm_env_vars(self) -> None:
                     "generation_kwargs": {},
                     "max_retries": 6,
                     "base_url": "https://example-resource.azure.openai.com/",
+                    "default_headers": None,
                     "timeout": 120,
                     "structured_output": {
                         "schema": DummyUserDetail.model_json_schema(),

tests/unit/models/llms/test_together.py

@@ -46,6 +46,7 @@ def test_serialization(self) -> None:
             "model": self.model_id,
             "generation_kwargs": {},
             "max_retries": 6,
+            "default_headers": None,
             "base_url": "https://api.together.xyz/v1",
             "timeout": 120,
             "structured_output": None,