Precommit CI changes

Signed-off-by: Yogesh <[email protected]>

comps/integrations/langchain/README.md

@@ -1,6 +1,6 @@
 # langchain-opea
 
-This package contains the LangChain integrations for [OPEA](https://opea.dev/) Microservices.
+This package contains the LangChain integrations for OPENAI Compatible [OPEA](https://opea.dev/) Microservices.
 
 ## Installation
 
@@ -11,7 +11,7 @@ You can install LangChain OPEA package in several ways:
 To install the package from the source, run:
 
 ```bash
-pip install -e .
+pip install poetry && poetry install --with test
 ```
 
 ### Install from Wheel Package
@@ -24,15 +24,15 @@ pip install dist/langchain_opea-0.1.0-py3-none-any.whl
 
 ### Install from PyPi
 
-Once the package is available on PyPi, you can install it using:
+> **Note:** Once the package is available on PyPi, you can install it using:
 
 ```bash
 pip install -U langchain-opea
 ```
 
 ## Chat Models
 
-`ChatOPEA` class exposes chat models from OPEA.
+`ChatOPEA` class exposes OPENAI Compatible chat models from OPEA.
 
 ```python
 from langchain_opea import ChatOPEA
@@ -45,7 +45,7 @@ llm.invoke("Sing a ballad of LangChain.")
 
 ## Embeddings
 
-`OPEAEmbeddings` class exposes embeddings from OPEA.
+`OPEAEmbeddings` class exposes OPENAI Compatible embeddings from OPEA.
 
 ```python
 from langchain_opea import OPEAEmbeddings
@@ -60,7 +60,7 @@ embeddings.embed_query("What is the meaning of life?")
 
 ## LLMs
 
-`OPEALLM` class exposes LLMs from OPEA.
+`OPEALLM` class exposes OPENAI Compatible LLMs from OPEA.
 
 ```python
 from langchain_opea import OPEALLM
@@ -70,3 +70,5 @@ llm = OPEALLM(
 )
 llm.invoke("The meaning of life is")
 ```
+
+Check out [Samples](/comps/integrations/langchain/samples/README.md) for more examples using the OPEA Langchain package.

comps/integrations/langchain/langchain_opea/chat_models.py

@@ -86,7 +86,9 @@ def _llm_type(self) -> str:
         """Return type of chat model."""
         return "opea-chat"
 
-    def _get_ls_params(self, stop: Optional[List[str]] = None, **kwargs: Any) -> LangSmithParams:
+    def _get_ls_params(
+        self, stop: Optional[List[str]] = None, **kwargs: Any
+    ) -> LangSmithParams:
         """Get the parameters used to invoke the model."""
         params = super()._get_ls_params(stop=stop, **kwargs)
         params["ls_provider"] = "opea"
@@ -101,7 +103,9 @@ def validate_environment(self) -> Self:
             raise ValueError("n must be 1 when streaming.")
 
         client_params: dict = {
-            "api_key": (self.opea_api_key.get_secret_value() if self.opea_api_key else None),
+            "api_key": (
+                self.opea_api_key.get_secret_value() if self.opea_api_key else None
+            ),
             "base_url": self.opea_api_base,
         }
 
@@ -113,10 +117,14 @@ def validate_environment(self) -> Self:
 
         if not (self.client or None):
             sync_specific: dict = {"http_client": self.http_client}
-            self.client = openai.OpenAI(**client_params, **sync_specific).chat.completions
+            self.client = openai.OpenAI(
+                **client_params, **sync_specific
+            ).chat.completions
         if not (self.async_client or None):
             async_specific: dict = {"http_client": self.http_async_client}
-            self.async_client = openai.AsyncOpenAI(**client_params, **async_specific).chat.completions
+            self.async_client = openai.AsyncOpenAI(
+                **client_params, **async_specific
+            ).chat.completions
         return self
 
     @property

comps/integrations/langchain/langchain_opea/llms.py

@@ -76,7 +76,9 @@ def validate_environment(self) -> Self:
         if self.streaming and self.best_of > 1:
             raise ValueError("Cannot stream results when best_of > 1.")
         client_params: dict = {
-            "api_key": self.opea_api_key.get_secret_value() if self.opea_api_key else None,
+            "api_key": self.opea_api_key.get_secret_value()
+            if self.opea_api_key
+            else None,
             "base_url": self.opea_api_base,
         }
 

comps/integrations/langchain/samples/README.md

@@ -1,6 +1,6 @@
 # Running Langchain OPEA SDK with OPEA microservices
 
-## 1. Starting the compose microservices
+## 1. Starting the microservices using compose 
 
 Set up the environment variables:
 
@@ -35,20 +35,30 @@ curl http://${host_ip}:9009/v1/chat/completions \
 
 ## 3. Install Langchain OPEA package
 
+You can install LangChain OPEA package in several ways:
+
+### Install from Source
+
+To install the package from the source, run:
+
 ```bash
-pip install langchain-opea
+pip install poetry && poetry install --with test
 ```
 
-or build from source
+### Install from Wheel Package
+
+To install the package from a pre-built wheel, run:
 
 ```bash
-pip install -e .
+pip install dist/langchain_opea-0.1.0-py3-none-any.whl
 ```
 
-or install from wheel package
+### Install from PyPi
+
+> **Note:** Once the package is available on PyPi, you can install it using:
 
 ```bash
-pip install dist/langchain_opea-0.1.0-py3-none-any.whl
+pip install -U langchain-opea
 ```
 
 ## 4. Install Jupyter Notebook
@@ -65,6 +75,6 @@ Start Jupyter Notebook:
 jupyter notebook
 ```
 
-Open the `summarize.ipynb` notebook and run the cells to execute the summarization example.
+Open the [`summarize.ipynb`](/comps/integrations/langchain/samples/summarize.ipynb) notebook and run the cells to execute the summarization example.
 
-Open the `qa_streaming.ipynb` notebook and run the cells to execute the QA chatbot with retrieval example.
+Open the [`qa_streaming.ipynb`](/comps/integrations/langchain/samples/qa_streaming.ipynb) notebook and run the cells to execute the QA chatbot with retrieval example.