[LLM Docs] Remain API Docs Issues Solution (#8780)

* langchain readthedocs update

* solve langchain.llms.transformersllm issues

* langchain.embeddings.transformersembeddings/transfortmersllms issues

* update docs for get_num_tokens

* add low_bit api doc

* add optimizer model api doc

* update rst index

* fix coomments style

* update docs following the comments

* update api doc

docs/readthedocs/source/doc/PythonAPI/LLM/index.rst

@@ -2,7 +2,8 @@ BigDL-LLM API
 ==================
 
 .. toctree::
-    :maxdepth: 2
+    :maxdepth: 3
 
     transformers.rst
     langchain.rst
+    optimize.rst

docs/readthedocs/source/doc/PythonAPI/LLM/langchain.rst

@@ -4,10 +4,59 @@ BigDL-LLM LangChain API
 llm.langchain.embeddings.bigdlllm
 ----------------------------------------
 
-.. automodule:: bigdl.llm.langchain.embeddings.bigdlllm
+.. autoclass:: bigdl.llm.langchain.embeddings.bigdlllm.LlamaEmbeddings
     :members:
     :undoc-members:
     :show-inheritance:
+    :exclude-members: ggml_model , ggml_module
+
+    .. automethod:: validate_environment
+    .. automethod:: embed_documents
+    .. automethod:: embed_query 
+
+
+.. autoclass:: bigdl.llm.langchain.embeddings.bigdlllm.BloomEmbeddings
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: ggml_model , ggml_module
+
+    .. automethod:: validate_environment
+    .. automethod:: embed_documents
+    .. automethod:: embed_query
+
+
+.. autoclass:: bigdl.llm.langchain.embeddings.bigdlllm.GptneoxEmbeddings
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: ggml_model , ggml_module
+
+    .. automethod:: validate_environment
+    .. automethod:: embed_documents
+    .. automethod:: embed_query
+
+
+.. autoclass:: bigdl.llm.langchain.embeddings.bigdlllm.ChatGLMEmbeddings
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: ggml_model , ggml_module
+
+    .. automethod:: validate_environment
+    .. automethod:: embed_documents
+    .. automethod:: embed_query
+
+
+.. autoclass:: bigdl.llm.langchain.embeddings.bigdlllm.StarcoderEmbeddings
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: ggml_model , ggml_module
+
+    .. automethod:: validate_environment
+    .. automethod:: embed_documents
+    .. automethod:: embed_query
 
 
 llm.langchain.embeddings.transformersembeddings
@@ -22,10 +71,59 @@ llm.langchain.embeddings.transformersembeddings
 llm.langchain.llms.bigdlllm
 ----------------------------------------
 
-.. automodule:: bigdl.llm.langchain.llms.bigdlllm
+.. autoclass:: bigdl.llm.langchain.llms.bigdlllm.LlamaLLM
     :members:
     :undoc-members:
     :show-inheritance:
+    :exclude-members: ggml_model , ggml_module
+
+    .. automethod:: validate_environment
+    .. automethod:: stream
+    .. automethod:: get_num_tokens
+
+
+.. autoclass:: bigdl.llm.langchain.llms.bigdlllm.BloomLLM
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: ggml_model , ggml_module
+
+    .. automethod:: validate_environment
+    .. automethod:: stream
+    .. automethod:: get_num_tokens 
+
+
+.. autoclass:: bigdl.llm.langchain.llms.bigdlllm.GptneoxLLM
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: ggml_model , ggml_module
+
+    .. automethod:: validate_environment
+    .. automethod:: stream
+    .. automethod:: get_num_tokens
+
+
+.. autoclass:: bigdl.llm.langchain.llms.bigdlllm.ChatGLMLLM
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: ggml_model , ggml_module
+
+    .. automethod:: validate_environment
+    .. automethod:: stream
+    .. automethod:: get_num_tokens
+
+
+.. autoclass:: bigdl.llm.langchain.llms.bigdlllm.StarcoderLLM
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: ggml_model , ggml_module
+
+    .. automethod:: validate_environment
+    .. automethod:: stream
+    .. automethod:: get_num_tokens
 
 
 llm.langchain.llms.transformersllm

docs/readthedocs/source/doc/PythonAPI/LLM/optimize.rst

@@ -0,0 +1,10 @@
+BigDL-LLM Optimize API
+=====================
+
+llm.optimize
+----------------------------------------
+
+.. automodule:: bigdl.llm.optimize
+    :members: optimize_model
+    :undoc-members:
+    :show-inheritance:

python/llm/src/bigdl/llm/langchain/embeddings/transformersembeddings.py

@@ -68,13 +68,15 @@ class TransformersEmbeddings(BaseModel, Embeddings):
     """
 
     model: Any  #: :meta private:
+    """BigDL-LLM Transformers-INT4 model."""
     tokenizer: Any  #: :meta private:
+    """Huggingface tokenizer model."""
     model_id: str = DEFAULT_MODEL_NAME
-    """Model id to use."""
+    """Model name or model path to use."""
     model_kwargs: Dict[str, Any] = Field(default_factory=dict)
-    """Key word arguments to pass to the model."""
+    """Keyword arguments to pass to the model."""
     encode_kwargs: Dict[str, Any] = Field(default_factory=dict)
-    """Key word arguments to pass when calling the `encode` method of the model."""
+    """Keyword arguments to pass when calling the `encode` method of the model."""
 
     @classmethod
     def from_model_id(
@@ -83,7 +85,18 @@ class TransformersEmbeddings(BaseModel, Embeddings):
         model_kwargs: Optional[dict] = None,
         **kwargs: Any,
     ):
-        """Construct object from model_id"""
+        """
+        Construct object from model_id.
+
+        Args:
+
+            model_id: Path for the huggingface repo id to be downloaded or the huggingface
+                      checkpoint folder.
+            model_kwargs: Keyword arguments that will be passed to the model and tokenizer.
+            kwargs: Extra arguments that will be passed to the model and tokenizer.
+        
+        Returns: An object of TransformersEmbeddings.
+        """
         try:
             from bigdl.llm.transformers import AutoModel
             from transformers import AutoTokenizer, LlamaTokenizer

python/llm/src/bigdl/llm/langchain/llms/bigdlllm.py

@@ -659,6 +659,16 @@ class _BaseCausalLM(LLM):
             yield chunk
 
     def get_num_tokens(self, text: str) -> int:
+        """Get the number of tokens that present in the text.
+
+        Useful for checking if an input will fit in a model's context window.
+
+        Args:
+            text: The string input to tokenize.
+
+        Returns:
+            The number of tokens in the text.
+        """
         tokenized_text = self.client.tokenize(text.encode("utf-8"))
         return len(tokenized_text)
 

python/llm/src/bigdl/llm/langchain/llms/transformersllm.py

@@ -71,9 +71,9 @@ class TransformersLLM(LLM):
     model_id: str = DEFAULT_MODEL_ID
     """Model name or model path to use."""
     model_kwargs: Optional[dict] = None
-    """Key word arguments passed to the model."""
+    """Keyword arguments passed to the model."""
     model: Any  #: :meta private:
-    """BigDL-LLM Transformer-INT4 model."""
+    """BigDL-LLM Transformers-INT4 model."""
     tokenizer: Any  #: :meta private:
     """Huggingface tokenizer model."""
     streaming: bool = True
@@ -91,7 +91,18 @@ class TransformersLLM(LLM):
         model_kwargs: Optional[dict] = None,
         **kwargs: Any,
     ) -> LLM:
-        """Construct object from model_id"""
+        """
+        Construct object from model_id
+        
+        Args:
+        
+            model_id: Path for the huggingface repo id to be downloaded or
+                      the huggingface checkpoint folder.
+            model_kwargs: Keyword arguments that will be passed to the model and tokenizer.
+            kwargs: Extra arguments that will be passed to the model and tokenizer.
+
+        Returns: An object of TransformersLLM.
+        """
         try:
             from bigdl.llm.transformers import (
                 AutoModel,
@@ -139,7 +150,17 @@ class TransformersLLM(LLM):
         model_kwargs: Optional[dict] = None,
         **kwargs: Any,
     ) -> LLM:
-        """Construct object from model_id"""
+        """
+        Construct low_bit object from model_id
+        
+        Args:
+        
+            model_id: Path for the bigdl transformers low-bit model checkpoint folder.
+            model_kwargs: Keyword arguments that will be passed to the model and tokenizer.
+            kwargs: Extra arguments that will be passed to the model and tokenizer.
+
+        Returns: An object of TransformersLLM.
+        """
         try:
             from bigdl.llm.transformers import (
                 AutoModel,