community: Update OCI data science integration

docs/docs/integrations/llms/oci_model_deployment_endpoint.ipynb

@@ -8,9 +8,11 @@
     "\n",
     "[OCI Data Science](https://docs.oracle.com/en-us/iaas/data-science/using/home.htm) is a fully managed and serverless platform for data science teams to build, train, and manage machine learning models in the Oracle Cloud Infrastructure.\n",
     "\n",
+    "> For the latest updates, examples and experimental features, please see [ADS LangChain Integration](https://accelerated-data-science.readthedocs.io/en/latest/user_guide/large_language_model/langchain_models.html).\n",
+    "\n",
     "This notebooks goes over how to use an LLM hosted on a [OCI Data Science Model Deployment](https://docs.oracle.com/en-us/iaas/data-science/using/model-dep-about.htm).\n",
     "\n",
-    "To authenticate, [oracle-ads](https://accelerated-data-science.readthedocs.io/en/latest/user_guide/cli/authentication.html) has been used to automatically load credentials for invoking endpoint."
+    "For authentication, the [oracle-ads](https://accelerated-data-science.readthedocs.io/en/latest/user_guide/cli/authentication.html) library is used to automatically load credentials required for invoking the endpoint."
    ]
   },
   {
@@ -29,29 +31,52 @@
     "## Prerequisite\n",
     "\n",
     "### Deploy model\n",
-    "Check [Oracle GitHub samples repository](https://github.com/oracle-samples/oci-data-science-ai-samples/tree/main/model-deployment/containers/llama2) on how to deploy your llm on OCI Data Science Model deployment.\n",
+    "You can easily deploy, fine-tune, and evaluate foundation models using the [AI Quick Actions](https://docs.oracle.com/en-us/iaas/data-science/using/ai-quick-actions.htm) on OCI Data Science Model deployment. For additional deployment examples, please visit the [Oracle GitHub samples repository](https://github.com/oracle-samples/oci-data-science-ai-samples/blob/main/ai-quick-actions/llama3-with-smc.md). \n",
     "\n",
     "### Policies\n",
     "Make sure to have the required [policies](https://docs.oracle.com/en-us/iaas/data-science/using/model-dep-policies-auth.htm#model_dep_policies_auth__predict-endpoint) to access the OCI Data Science Model Deployment endpoint.\n",
     "\n",
     "## Set up\n",
     "\n",
-    "### vLLM\n",
-    "After having deployed model, you have to set up following required parameters of the `OCIModelDeploymentVLLM` call:\n",
-    "\n",
-    "- **`endpoint`**: The model HTTP endpoint from the deployed model, e.g. `https://<MD_OCID>/predict`. \n",
-    "- **`model`**: The location of the model.\n",
+    "After having deployed model, you have to set up following required parameters of the call:\n",
     "\n",
-    "### Text generation inference (TGI)\n",
-    "You have to set up following required parameters of the `OCIModelDeploymentTGI` call:\n",
+    "- **`endpoint`**: The model HTTP endpoint from the deployed model, e.g. `https://modeldeployment.<region>.oci.customer-oci.com/<md_ocid>/predict`. \n",
     "\n",
-    "- **`endpoint`**: The model HTTP endpoint from the deployed model, e.g. `https://<MD_OCID>/predict`. \n",
     "\n",
     "### Authentication\n",
     "\n",
     "You can set authentication through either ads or environment variables. When you are working in OCI Data Science Notebook Session, you can leverage resource principal to access other OCI resources. Check out [here](https://accelerated-data-science.readthedocs.io/en/latest/user_guide/cli/authentication.html) to see more options. \n",
     "\n",
-    "## Example"
+    "## Examples"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import ads\n",
+    "from langchain_community.llms import OCIModelDeploymentLLM\n",
+    "\n",
+    "# Set authentication through ads\n",
+    "# Use resource principal are operating within a\n",
+    "# OCI service that has resource principal based\n",
+    "# authentication configured\n",
+    "ads.set_auth(\"resource_principal\")\n",
+    "\n",
+    "# Create an instance of OCI Model Deployment Endpoint\n",
+    "# Replace the endpoint uri and model name with your own\n",
+    "# Using generic class as entry point, you will be able\n",
+    "# to pass model parameters through model_kwargs during\n",
+    "# instantiation.\n",
+    "llm = OCIModelDeploymentLLM(\n",
+    "    endpoint=\"https://modeldeployment.<region>.oci.customer-oci.com/<md_ocid>/predict\",\n",
+    "    model=\"odsc-llm\",\n",
+    ")\n",
+    "\n",
+    "# Run the LLM\n",
+    "llm.invoke(\"Who is the first president of United States?\")"
    ]
   },
   {
@@ -71,7 +96,11 @@
     "\n",
     "# Create an instance of OCI Model Deployment Endpoint\n",
     "# Replace the endpoint uri and model name with your own\n",
-    "llm = OCIModelDeploymentVLLM(endpoint=\"https://<MD_OCID>/predict\", model=\"model_name\")\n",
+    "# Using framework specific class as entry point, you will\n",
+    "# be able to pass model parameters in constructor.\n",
+    "llm = OCIModelDeploymentVLLM(\n",
+    "    endpoint=\"https://modeldeployment.<region>.oci.customer-oci.com/<md_ocid>/predict\",\n",
+    ")\n",
     "\n",
     "# Run the LLM\n",
     "llm.invoke(\"Who is the first president of United States?\")"
@@ -97,14 +126,64 @@
     "\n",
     "# Set endpoint through environment variables\n",
     "# Replace the endpoint uri with your own\n",
-    "os.environ[\"OCI_LLM_ENDPOINT\"] = \"https://<MD_OCID>/predict\"\n",
+    "os.environ[\"OCI_LLM_ENDPOINT\"] = (\n",
+    "    \"https://modeldeployment.<region>.oci.customer-oci.com/<md_ocid>/predict\"\n",
+    ")\n",
     "\n",
     "# Create an instance of OCI Model Deployment Endpoint\n",
+    "# Using framework specific class as entry point, you will\n",
+    "# be able to pass model parameters in constructor.\n",
     "llm = OCIModelDeploymentTGI()\n",
     "\n",
     "# Run the LLM\n",
     "llm.invoke(\"Who is the first president of United States?\")"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Asynchronous calls"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "await llm.ainvoke(\"Tell me a joke.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Streaming calls"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for chunk in llm.stream(\"Tell me a joke.\"):\n",
+    "    print(chunk, end=\"\", flush=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For comprehensive details on all features and configurations, please refer to the API reference documentation for each class:\n",
+    "\n",
+    "* [OCIModelDeploymentLLM](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentLLM.html)\n",
+    "* [OCIModelDeploymentVLLM](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentVLLM.html)\n",
+    "* [OCIModelDeploymentTGI](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI.html)"
+   ]
   }
  ],
  "metadata": {

docs/docs/integrations/providers/oci.mdx

@@ -32,20 +32,18 @@ from langchain_community.embeddings import OCIGenAIEmbeddings
 > as an OCI Model Deployment Endpoint using the
 > [OCI Data Science Model Deployment Service](https://docs.oracle.com/en-us/iaas/data-science/using/model-dep-about.htm).
 
-If you deployed a LLM with the VLLM or TGI framework, you can use the
-`OCIModelDeploymentVLLM` or `OCIModelDeploymentTGI` classes to interact with it.
-
 To use, you should have the latest `oracle-ads` python SDK installed.
 
 ```bash
 pip install -U oracle-ads
 ```
 
-See [usage examples](/docs/integrations/llms/oci_model_deployment_endpoint).
+See [chat](/docs/integrations/chat/oci_data_science) and [complete](/docs/integrations/llms/oci_model_deployment_endpoint) usage examples.
+
 
 ```python
-from langchain_community.llms import OCIModelDeploymentVLLM
+from langchain_community.chat_models import ChatOCIModelDeployment
 
-from langchain_community.llms import OCIModelDeploymentTGI
+from langchain_community.llms import OCIModelDeploymentLLM
 ```
 

libs/community/extended_testing_deps.txt

@@ -38,6 +38,7 @@ jinja2>=3,<4
 jq>=1.4.1,<2
 jsonschema>1
 keybert>=0.8.5
+langchain_openai>=0.2.1
 litellm>=1.30,<=1.39.5
 lxml>=4.9.3,<6.0
 markdownify>=0.11.6,<0.12

libs/community/langchain_community/chat_models/__init__.py

@@ -125,6 +125,11 @@
     from langchain_community.chat_models.moonshot import (
         MoonshotChat,
     )
+    from langchain_community.chat_models.oci_data_science import (
+        ChatOCIModelDeployment,
+        ChatOCIModelDeploymentTGI,
+        ChatOCIModelDeploymentVLLM,
+    )
     from langchain_community.chat_models.oci_generative_ai import (
         ChatOCIGenAI,  # noqa: F401
     )
@@ -211,6 +216,9 @@
     "ChatMlflow",
     "ChatNebula",
     "ChatOCIGenAI",
+    "ChatOCIModelDeployment",
+    "ChatOCIModelDeploymentVLLM",
+    "ChatOCIModelDeploymentTGI",
     "ChatOllama",
     "ChatOpenAI",
     "ChatPerplexity",
@@ -272,6 +280,9 @@
     "ChatNebula": "langchain_community.chat_models.symblai_nebula",
     "ChatOctoAI": "langchain_community.chat_models.octoai",
     "ChatOCIGenAI": "langchain_community.chat_models.oci_generative_ai",
+    "ChatOCIModelDeployment": "langchain_community.chat_models.oci_data_science",
+    "ChatOCIModelDeploymentVLLM": "langchain_community.chat_models.oci_data_science",
+    "ChatOCIModelDeploymentTGI": "langchain_community.chat_models.oci_data_science",
     "ChatOllama": "langchain_community.chat_models.ollama",
     "ChatOpenAI": "langchain_community.chat_models.openai",
     "ChatPerplexity": "langchain_community.chat_models.perplexity",