From 77697c97a79cefe6b63f34362035481d26f4df5b Mon Sep 17 00:00:00 2001 From: leo-gan Date: Fri, 23 Feb 2024 15:02:45 -0800 Subject: [PATCH 1/6] updated provider page --- docs/docs/integrations/llms/nvidia_trt.ipynb | 98 ++++++++++++++++++++ docs/docs/integrations/providers/nvidia.mdx | 77 ++++++++++++--- 2 files changed, 160 insertions(+), 15 deletions(-) create mode 100644 docs/docs/integrations/llms/nvidia_trt.ipynb diff --git a/docs/docs/integrations/llms/nvidia_trt.ipynb b/docs/docs/integrations/llms/nvidia_trt.ipynb new file mode 100644 index 0000000000000..63815354ba971 --- /dev/null +++ b/docs/docs/integrations/llms/nvidia_trt.ipynb @@ -0,0 +1,98 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "b56b221d", + "metadata": {}, + "source": [ + "# NVIDIA Triton Inference Server\n", + "\n", + ">[NVIDIA Triton Inference Server](https://developer.nvidia.com/triton-inference-server) is an inference server that provides an API style access to hosted LLM models. Likewise, `Nvidia TensorRT-LLM`, often abbreviated as `TRT-LLM`, is a GPU-accelerated SDK for running optimizations and inference on LLM models. This connector allows for Langchain to remotely interact with a Triton inference server over GRPC or HTTP to performance accelerated inference operations.\n", + "\n", + "[Triton Inference Server Github](https://github.com/triton-inference-server/server)\n", + "\n", + "\n", + "## TritonTensorRTLLM\n", + "\n", + "This example goes over how to use LangChain to interact with `TritonTensorRT` LLMs. To install, run the following command:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "59c710c4", + "metadata": {}, + "outputs": [], + "source": [ + "# install package\n", + "%pip install -U langchain-nvidia-trt" + ] + }, + { + "cell_type": "markdown", + "id": "0ee90032", + "metadata": {}, + "source": [ + "## Create the Triton+TRT-LLM instance\n", + "\n", + "Remember that a Triton instance represents a running server instance therefore you should ensure you have a valid server configuration running and change the `localhost:8001` to the correct IP/hostname:port combination for your server.\n", + "\n", + "An example of setting up this environment can be found at Nvidia's (GenerativeAIExamples Github Repo)[https://github.com/NVIDIA/GenerativeAIExamples/tree/main/RetrievalAugmentedGeneration]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "035dea0f", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "from langchain_core.prompts import PromptTemplate\n", + "from langchain_nvidia_trt.llms import TritonTensorRTLLM\n", + "\n", + "template = \"\"\"Question: {question}\n", + "\n", + "Answer: Let's think step by step.\"\"\"\n", + "\n", + "prompt = PromptTemplate.from_template(template)\n", + "\n", + "# Connect to the TRT-LLM Llama-2 model running on the Triton server at the url below\n", + "triton_llm = TritonTensorRTLLM(\n", + " server_url=\"localhost:8001\", model_name=\"ensemble\", tokens=500\n", + ")\n", + "\n", + "chain = prompt | triton_llm\n", + "\n", + "chain.invoke({\"question\": \"What is LangChain?\"})" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.12" + }, + "vscode": { + "interpreter": { + "hash": "e971737741ff4ec9aff7dc6155a1060a59a8a6d52c757dbbe66bf8ee389494b1" + } + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/docs/docs/integrations/providers/nvidia.mdx b/docs/docs/integrations/providers/nvidia.mdx index c00eea6416024..5397e9488e303 100644 --- a/docs/docs/integrations/providers/nvidia.mdx +++ b/docs/docs/integrations/providers/nvidia.mdx @@ -1,18 +1,28 @@ # NVIDIA -> [NVIDIA AI Foundation Endpoints](https://www.nvidia.com/en-us/ai-data-science/foundation-models/) give users easy access to NVIDIA hosted API endpoints for NVIDIA AI Foundation Models like Mixtral 8x7B, Llama 2, Stable Diffusion, etc. These models, hosted on the [NVIDIA NGC catalog](https://catalog.ngc.nvidia.com/ai-foundation-models), are optimized, tested, and hosted on the NVIDIA AI platform, making them fast and easy to evaluate, further customize, and seamlessly run at peak performance on any accelerated stack. -> -> With [NVIDIA AI Foundation Endpoints](https://www.nvidia.com/en-us/ai-data-science/foundation-models/), you can get quick results from a fully accelerated stack running on [NVIDIA DGX Cloud](https://www.nvidia.com/en-us/data-center/dgx-cloud/). Once customized, these models can be deployed anywhere with enterprise-grade security, stability, and support using [NVIDIA AI Enterprise](https://www.nvidia.com/en-us/data-center/products/ai-enterprise/). +>NVIDIA provides two integration packages for LangChain: `langchain-nvidia-ai-endpoints` and `langchain-nvidia-trt`. + +## NVIDIA AI Foundation Endpoints + +> [NVIDIA AI Foundation Endpoints](https://www.nvidia.com/en-us/ai-data-science/foundation-models/) give users easy access to NVIDIA hosted API endpoints for +> NVIDIA AI Foundation Models like `Mixtral 8x7B`, `Llama 2`, `Stable Diffusion`, etc. These models, +> hosted on the [NVIDIA NGC catalog](https://catalog.ngc.nvidia.com/ai-foundation-models), are optimized, tested, and hosted on +> the NVIDIA AI platform, making them fast and easy to evaluate, further customize, +> and seamlessly run at peak performance on any accelerated stack. > -> These models can be easily accessed via the [`langchain-nvidia-ai-endpoints`](https://pypi.org/project/langchain-nvidia-ai-endpoints/) package, as shown below. +> With [NVIDIA AI Foundation Endpoints](https://www.nvidia.com/en-us/ai-data-science/foundation-models/), you can get quick results from a fully +> accelerated stack running on [NVIDIA DGX Cloud](https://www.nvidia.com/en-us/data-center/dgx-cloud/). Once customized, these +> models can be deployed anywhere with enterprise-grade security, stability, +> and support using [NVIDIA AI Enterprise](https://www.nvidia.com/en-us/data-center/products/ai-enterprise/). -## Installation +A selection of NVIDIA AI Foundation models is supported directly in LangChain with familiar APIs. -```bash -pip install -U langchain-nvidia-ai-endpoints -``` +The supported models can be found [in NGC](https://catalog.ngc.nvidia.com/ai-foundation-models). -## Setup and Authentication +These models can be accessed via the [`langchain-nvidia-ai-endpoints`](https://pypi.org/project/langchain-nvidia-ai-endpoints/) +package, as shown below. + +### Setting up - Create a free [NVIDIA NGC](https://catalog.ngc.nvidia.com/) account. - Navigate to `Catalog > AI Foundation Models > (Model with API endpoint)`. @@ -22,6 +32,16 @@ pip install -U langchain-nvidia-ai-endpoints export NVIDIA_API_KEY=nvapi-XXXXXXXXXXXXXXXXXXXXXXXXXX ``` +- Install a package: + +```bash +pip install -U langchain-nvidia-ai-endpoints +``` + +### Chat models + +See a [usage example](/docs/integrations/chat/nvidia_ai_endpoints). + ```python from langchain_nvidia_ai_endpoints import ChatNVIDIA @@ -30,12 +50,39 @@ result = llm.invoke("Write a ballad about LangChain.") print(result.content) ``` -## Using NVIDIA AI Foundation Endpoints +### Embedding models + +See a [usage example](/docs/integrations/text_embedding/nvidia_ai_endpoints). + +```python +from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings +``` + -A selection of NVIDIA AI Foundation models are supported directly in LangChain with familiar APIs. +## NVIDIA Triton Inference Server -The active models which are supported can be found [in NGC](https://catalog.ngc.nvidia.com/ai-foundation-models). +>[NVIDIA Triton™ Inference Server](https://developer.nvidia.com/triton-inference-server), +> part of the `NVIDIA AI` platform and available with `NVIDIA AI Enterprise`, is +> open-source software that standardizes AI model deployment and execution across every workload. + +### Setting up -**The following may be useful examples to help you get started:** -- **[`ChatNVIDIA` Model](/docs/integrations/chat/nvidia_ai_endpoints).** -- **[`NVIDIAEmbeddings` Model for RAG Workflows](/docs/integrations/text_embedding/nvidia_ai_endpoints).** +See the installation guide for [NVIDIA Triton Inference Server](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/tritonserver). + +See the [client package documentation](https://github.com/triton-inference-server/client). + +- Install a package: + +```bash +pip install tritonclient +pip install -U langchain-nvidia-trt +``` + +### LLMs + +See a [usage example](/docs/integrations/llms/nvidia_trt). + + +```python +from langchain_nvidia_trt import TritonTensorRTLLM +``` From 16cf4130e76d53bf04572e95da4cca4cbf092c2d Mon Sep 17 00:00:00 2001 From: leo-gan Date: Fri, 23 Feb 2024 19:57:31 -0800 Subject: [PATCH 2/6] rolled back nvidia_trt artifacts --- docs/docs/integrations/llms/nvidia_trt.ipynb | 98 -------------------- docs/docs/integrations/providers/nvidia.mdx | 31 +------ 2 files changed, 1 insertion(+), 128 deletions(-) delete mode 100644 docs/docs/integrations/llms/nvidia_trt.ipynb diff --git a/docs/docs/integrations/llms/nvidia_trt.ipynb b/docs/docs/integrations/llms/nvidia_trt.ipynb deleted file mode 100644 index 63815354ba971..0000000000000 --- a/docs/docs/integrations/llms/nvidia_trt.ipynb +++ /dev/null @@ -1,98 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "id": "b56b221d", - "metadata": {}, - "source": [ - "# NVIDIA Triton Inference Server\n", - "\n", - ">[NVIDIA Triton Inference Server](https://developer.nvidia.com/triton-inference-server) is an inference server that provides an API style access to hosted LLM models. Likewise, `Nvidia TensorRT-LLM`, often abbreviated as `TRT-LLM`, is a GPU-accelerated SDK for running optimizations and inference on LLM models. This connector allows for Langchain to remotely interact with a Triton inference server over GRPC or HTTP to performance accelerated inference operations.\n", - "\n", - "[Triton Inference Server Github](https://github.com/triton-inference-server/server)\n", - "\n", - "\n", - "## TritonTensorRTLLM\n", - "\n", - "This example goes over how to use LangChain to interact with `TritonTensorRT` LLMs. To install, run the following command:" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "59c710c4", - "metadata": {}, - "outputs": [], - "source": [ - "# install package\n", - "%pip install -U langchain-nvidia-trt" - ] - }, - { - "cell_type": "markdown", - "id": "0ee90032", - "metadata": {}, - "source": [ - "## Create the Triton+TRT-LLM instance\n", - "\n", - "Remember that a Triton instance represents a running server instance therefore you should ensure you have a valid server configuration running and change the `localhost:8001` to the correct IP/hostname:port combination for your server.\n", - "\n", - "An example of setting up this environment can be found at Nvidia's (GenerativeAIExamples Github Repo)[https://github.com/NVIDIA/GenerativeAIExamples/tree/main/RetrievalAugmentedGeneration]" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "035dea0f", - "metadata": { - "tags": [] - }, - "outputs": [], - "source": [ - "from langchain_core.prompts import PromptTemplate\n", - "from langchain_nvidia_trt.llms import TritonTensorRTLLM\n", - "\n", - "template = \"\"\"Question: {question}\n", - "\n", - "Answer: Let's think step by step.\"\"\"\n", - "\n", - "prompt = PromptTemplate.from_template(template)\n", - "\n", - "# Connect to the TRT-LLM Llama-2 model running on the Triton server at the url below\n", - "triton_llm = TritonTensorRTLLM(\n", - " server_url=\"localhost:8001\", model_name=\"ensemble\", tokens=500\n", - ")\n", - "\n", - "chain = prompt | triton_llm\n", - "\n", - "chain.invoke({\"question\": \"What is LangChain?\"})" - ] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3 (ipykernel)", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.10.12" - }, - "vscode": { - "interpreter": { - "hash": "e971737741ff4ec9aff7dc6155a1060a59a8a6d52c757dbbe66bf8ee389494b1" - } - } - }, - "nbformat": 4, - "nbformat_minor": 5 -} diff --git a/docs/docs/integrations/providers/nvidia.mdx b/docs/docs/integrations/providers/nvidia.mdx index 5397e9488e303..0be21e38f7178 100644 --- a/docs/docs/integrations/providers/nvidia.mdx +++ b/docs/docs/integrations/providers/nvidia.mdx @@ -1,6 +1,6 @@ # NVIDIA ->NVIDIA provides two integration packages for LangChain: `langchain-nvidia-ai-endpoints` and `langchain-nvidia-trt`. +>NVIDIA provides an integration package for LangChain: `langchain-nvidia-ai-endpoints`. ## NVIDIA AI Foundation Endpoints @@ -57,32 +57,3 @@ See a [usage example](/docs/integrations/text_embedding/nvidia_ai_endpoints). ```python from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings ``` - - -## NVIDIA Triton Inference Server - ->[NVIDIA Triton™ Inference Server](https://developer.nvidia.com/triton-inference-server), -> part of the `NVIDIA AI` platform and available with `NVIDIA AI Enterprise`, is -> open-source software that standardizes AI model deployment and execution across every workload. - -### Setting up - -See the installation guide for [NVIDIA Triton Inference Server](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/tritonserver). - -See the [client package documentation](https://github.com/triton-inference-server/client). - -- Install a package: - -```bash -pip install tritonclient -pip install -U langchain-nvidia-trt -``` - -### LLMs - -See a [usage example](/docs/integrations/llms/nvidia_trt). - - -```python -from langchain_nvidia_trt import TritonTensorRTLLM -``` From 996aec827f6cc3925e223b719a8ef3c83dfec475 Mon Sep 17 00:00:00 2001 From: leo-gan Date: Fri, 23 Feb 2024 15:18:01 -0800 Subject: [PATCH 3/6] added the example notebook and link to it --- docs/docs/integrations/llms/nvidia_trt.ipynb | 96 ++++++++++++++++++++ 1 file changed, 96 insertions(+) create mode 100644 docs/docs/integrations/llms/nvidia_trt.ipynb diff --git a/docs/docs/integrations/llms/nvidia_trt.ipynb b/docs/docs/integrations/llms/nvidia_trt.ipynb new file mode 100644 index 0000000000000..961f393372b2b --- /dev/null +++ b/docs/docs/integrations/llms/nvidia_trt.ipynb @@ -0,0 +1,96 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "b56b221d", + "metadata": {}, + "source": [ + "# NVIDIA Triton Inference Server\n", + "\n", + ">[NVIDIA Triton Inference Server](https://developer.nvidia.com/triton-inference-server) is an inference server that provides an API style access to hosted LLM models. Likewise, `Nvidia TensorRT-LLM`, often abbreviated as `TRT-LLM`, is a GPU-accelerated SDK for running optimizations and inference on LLM models. This connector allows for Langchain to remotely interact with a Triton inference server over GRPC or HTTP to performance accelerated inference operations.\n", + "\n", + "[Triton Inference Server Github](https://github.com/triton-inference-server/server)\n", + "\n", + "\n", + "## TritonTensorRTLLM\n", + "\n", + "This example goes over how to use LangChain to interact with `TritonTensorRT` LLMs. To install, run the following command:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "59c710c4", + "metadata": {}, + "outputs": [], + "source": [ + "# install package\n", + "%pip install -U langchain-nvidia-trt" + ] + }, + { + "cell_type": "markdown", + "id": "0ee90032", + "metadata": {}, + "source": [ + "## Create the Triton+TRT-LLM instance\n", + "\n", + "Remember that a Triton instance represents a running server instance therefore you should ensure you have a valid server configuration running and change the `localhost:8001` to the correct IP/hostname:port combination for your server.\n", + "\n", + "An example of setting up this environment can be found at Nvidia's (GenerativeAIExamples Github Repo)[https://github.com/NVIDIA/GenerativeAIExamples/tree/main/RetrievalAugmentedGeneration]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "035dea0f", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "from langchain_core.prompts import PromptTemplate\n", + "from langchain_nvidia_trt.llms import TritonTensorRTLLM\n", + "\n", + "template = \"\"\"Question: {question}\n", + "\n", + "Answer: Let's think step by step.\"\"\"\n", + "\n", + "prompt = PromptTemplate.from_template(template)\n", + "\n", + "# Connect to the TRT-LLM Llama-2 model running on the Triton server at the url below\n", + "triton_llm = TritonTensorRTLLM(server_url =\"localhost:8001\", model_name=\"ensemble\", tokens=500)\n", + "\n", + "chain = prompt | triton_llm \n", + "\n", + "chain.invoke({\"question\": \"What is LangChain?\"})" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.12" + }, + "vscode": { + "interpreter": { + "hash": "e971737741ff4ec9aff7dc6155a1060a59a8a6d52c757dbbe66bf8ee389494b1" + } + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} From d6e411a7670b83dba0aa653f33c2429e8689f1d3 Mon Sep 17 00:00:00 2001 From: leo-gan Date: Fri, 23 Feb 2024 15:26:57 -0800 Subject: [PATCH 4/6] fixed format --- docs/docs/integrations/llms/nvidia_trt.ipynb | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/docs/docs/integrations/llms/nvidia_trt.ipynb b/docs/docs/integrations/llms/nvidia_trt.ipynb index 961f393372b2b..d0943c6a33768 100644 --- a/docs/docs/integrations/llms/nvidia_trt.ipynb +++ b/docs/docs/integrations/llms/nvidia_trt.ipynb @@ -59,7 +59,9 @@ "prompt = PromptTemplate.from_template(template)\n", "\n", "# Connect to the TRT-LLM Llama-2 model running on the Triton server at the url below\n", - "triton_llm = TritonTensorRTLLM(server_url =\"localhost:8001\", model_name=\"ensemble\", tokens=500)\n", + "triton_llm = TritonTensorRTLLM(\n", + " server_url=\"localhost:8001\", model_name=\"ensemble\", tokens=500\n", + ")\n", "\n", "chain = prompt | triton_llm \n", "\n", From cecf8ffb5e87aec144694dc413fcd025cbe74eac Mon Sep 17 00:00:00 2001 From: leo-gan Date: Fri, 23 Feb 2024 15:28:15 -0800 Subject: [PATCH 5/6] fixed format --- docs/docs/integrations/llms/nvidia_trt.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/docs/integrations/llms/nvidia_trt.ipynb b/docs/docs/integrations/llms/nvidia_trt.ipynb index d0943c6a33768..63815354ba971 100644 --- a/docs/docs/integrations/llms/nvidia_trt.ipynb +++ b/docs/docs/integrations/llms/nvidia_trt.ipynb @@ -63,7 +63,7 @@ " server_url=\"localhost:8001\", model_name=\"ensemble\", tokens=500\n", ")\n", "\n", - "chain = prompt | triton_llm \n", + "chain = prompt | triton_llm\n", "\n", "chain.invoke({\"question\": \"What is LangChain?\"})" ] From 25e44a33b62495e322c0d0e9500a2fe4e6256071 Mon Sep 17 00:00:00 2001 From: leo-gan Date: Fri, 23 Feb 2024 20:04:21 -0800 Subject: [PATCH 6/6] rolled back nvidia_trt artifacts --- docs/docs/integrations/llms/nvidia_trt.ipynb | 98 -------------------- 1 file changed, 98 deletions(-) delete mode 100644 docs/docs/integrations/llms/nvidia_trt.ipynb diff --git a/docs/docs/integrations/llms/nvidia_trt.ipynb b/docs/docs/integrations/llms/nvidia_trt.ipynb deleted file mode 100644 index 63815354ba971..0000000000000 --- a/docs/docs/integrations/llms/nvidia_trt.ipynb +++ /dev/null @@ -1,98 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "id": "b56b221d", - "metadata": {}, - "source": [ - "# NVIDIA Triton Inference Server\n", - "\n", - ">[NVIDIA Triton Inference Server](https://developer.nvidia.com/triton-inference-server) is an inference server that provides an API style access to hosted LLM models. Likewise, `Nvidia TensorRT-LLM`, often abbreviated as `TRT-LLM`, is a GPU-accelerated SDK for running optimizations and inference on LLM models. This connector allows for Langchain to remotely interact with a Triton inference server over GRPC or HTTP to performance accelerated inference operations.\n", - "\n", - "[Triton Inference Server Github](https://github.com/triton-inference-server/server)\n", - "\n", - "\n", - "## TritonTensorRTLLM\n", - "\n", - "This example goes over how to use LangChain to interact with `TritonTensorRT` LLMs. To install, run the following command:" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "59c710c4", - "metadata": {}, - "outputs": [], - "source": [ - "# install package\n", - "%pip install -U langchain-nvidia-trt" - ] - }, - { - "cell_type": "markdown", - "id": "0ee90032", - "metadata": {}, - "source": [ - "## Create the Triton+TRT-LLM instance\n", - "\n", - "Remember that a Triton instance represents a running server instance therefore you should ensure you have a valid server configuration running and change the `localhost:8001` to the correct IP/hostname:port combination for your server.\n", - "\n", - "An example of setting up this environment can be found at Nvidia's (GenerativeAIExamples Github Repo)[https://github.com/NVIDIA/GenerativeAIExamples/tree/main/RetrievalAugmentedGeneration]" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "035dea0f", - "metadata": { - "tags": [] - }, - "outputs": [], - "source": [ - "from langchain_core.prompts import PromptTemplate\n", - "from langchain_nvidia_trt.llms import TritonTensorRTLLM\n", - "\n", - "template = \"\"\"Question: {question}\n", - "\n", - "Answer: Let's think step by step.\"\"\"\n", - "\n", - "prompt = PromptTemplate.from_template(template)\n", - "\n", - "# Connect to the TRT-LLM Llama-2 model running on the Triton server at the url below\n", - "triton_llm = TritonTensorRTLLM(\n", - " server_url=\"localhost:8001\", model_name=\"ensemble\", tokens=500\n", - ")\n", - "\n", - "chain = prompt | triton_llm\n", - "\n", - "chain.invoke({\"question\": \"What is LangChain?\"})" - ] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3 (ipykernel)", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.10.12" - }, - "vscode": { - "interpreter": { - "hash": "e971737741ff4ec9aff7dc6155a1060a59a8a6d52c757dbbe66bf8ee389494b1" - } - } - }, - "nbformat": 4, - "nbformat_minor": 5 -}