|
|
@@ -27,7 +27,8 @@ The system follows a standard RAG pipeline, adapted for local development:
|
|
|
## 🛠️ Prerequisites
|
|
|
|
|
|
* Python 3.8 or higher
|
|
|
-* A Llama API key (obtained from [Llama's official site](https://www.llama.com/))
|
|
|
+* A Llama API key (obtained from [Llama's official site](https://www.llama.com/) or refer to the [Llama Developer Documentation](https://llama.developer.meta.com/docs/overview/))
|
|
|
+* A Qdrant account and API key (refer to the [Qdrant Cloud Account Setup documentation](https://qdrant.tech/documentation/cloud-account-setup/))
|
|
|
* `pip` for installing Python packages
|
|
|
|
|
|
---
|
|
|
@@ -40,20 +41,23 @@ Follow these steps to set up and run the technical blog generator.
|
|
|
|
|
|
First, clone the `llama-cookbook` repository and navigate to the specific recipe directory as per the below:
|
|
|
|
|
|
+```bash
|
|
|
git clone https://github.com/meta-llama/llama-cookbook
|
|
|
+
|
|
|
cd llama-cookbook/end-to-end-use-cases/technical_blogger
|
|
|
+
|
|
|
pip install -r requirements.txt
|
|
|
+```
|
|
|
|
|
|
|
|
|
### Step 2: Configure Your API Key
|
|
|
-You'll need to configure your Llama API key. You can do this by setting an environment variable named LLAMA_API_KEY. For more information on obtaining a Llama API key, refer to the [Llama Developer Documentation](https://llama.developer.meta.com/docs/overview/).
|
|
|
-
|
|
|
-Similarly, you'll need to set up a Qdrant account and generate an access token. You can follow the instructions in the [Qdrant Cloud Account Setup documentation](https://qdrant.tech/documentation/cloud-account-setup/) to create an account and obtain an API key.
|
|
|
+See the Prerequisites section for details on obtaining and configuring your Llama and Qdrant API keys.
|
|
|
|
|
|
|
|
|
### Step 3: Prepare Your Knowledge Base (Data Ingestion)
|
|
|
-Before generating a blog post, you'll need to prepare your knowledge base by populating a Qdrant collection with relevant data. You can use the provided qdrant_setup_partial.py script to create and populate a Qdrant collection.
|
|
|
-For more information on setting up a Qdrant collection, refer to the qdrant_setup_partial.py script.
|
|
|
+Before generating a blog post, you'll need to prepare your knowledge base by populating a Qdrant collection with relevant data. You can use the provided [`setup_qdrant_collection.py`](setup_qdrant_collection.py) script to create and populate a Qdrant collection.
|
|
|
+
|
|
|
+For more information on setting up a Qdrant collection, refer to the [`setup_qdrant_collection.py`](setup_qdrant_collection.py) script.
|
|
|
|
|
|
### Step 4: Run the Notebook
|
|
|
-Once you've completed the previous steps, you can run the notebook to generate a technical blog post. Simply execute the cells in the notebook, and it will guide you through the process of generating a high-quality blog post based on your technical documentation.
|
|
|
+Once you've completed the previous steps, you can run the notebook to generate a technical blog post. Simply execute the cells in the [`Technical_Blog_Generator.ipynb`](Technical_Blog_Generator.ipynb) notebook, and it will guide you through the process of generating a high-quality blog post based on your technical documentation.
|
llamatest