Formatting

CONTRIBUTING.md

@@ -29,20 +29,19 @@ Please run this script before submitting a pull request.
 
 ## Adding a new Vector Database
 
-1. Setup your local environment by following the Development setup.
-
-2. Create a new directory under phi/vectordb for the new vector database.
-
-3. Create a Class for your VectorDb that implements the VectorDb interface:
-
-4. Your Class will be in the phi/vectordb/<your_db>/<your_db>.py file.
-5. The VectorDb interface is defined in phi/vectordb/base.
-6. Import your VectorDb Class in phi/vectordb/<your_db>/__init__.py.
-7. Check out the phi/vectordb/pgvector/pgvector2 file for an example.
-8. Add a recipe for using your VectorDb under cookbook/<your_db>:
-
-9. Check out phidata/cookbook/pgvector for an example (you do not need to add the resources.py file).
-Important: Format and validate your code by running ./scripts/format.sh.
+1. Setup your local environment by following the [Development setup](#development-setup).
+2. Create a new directory under `phi/llm` for the new LLM provider.
+3. If the LLM provider supports the OpenAI API spec:
+   - Create a Class for your LLM provider that inherits the `OpenAILike` Class from `phi/llm/openai/like.py`.
+   - Your Class will be in the `phi/llm/<your_llm>/<your_llm>.py` file.
+   - Import your Class in the `phi/llm/<your_llm>/__init__.py` file.
+   - Checkout the [`phi/llm/together/together.py`](https://github.com/phidatahq/phidata/blob/main/phi/llm/together/together.py) file for an example.
+4. If the LLM provider does not support the OpenAI API spec:
+   - Reach out to us on [Discord](https://discord.gg/4MtYHHrgA8) or open an issue to discuss the best way to integrate your LLM provider.
+5. Add a recipe for using your LLM provider under `cookbook/<your_llm>`.
+   - Checkout [`phidata/cookbook/together`](https://github.com/phidatahq/phidata/tree/main/cookbook/together) for an example.
+6. Important: Format and validate your code by running `./scripts/format.sh`.
+7. Submit a pull request.
 
 Submit a pull request
 

cookbook/knowledge/text.py

@@ -1,9 +1,10 @@
+from pathlib import Path
+
+from phi.assistant import Assistant
 from phi.knowledge.text import TextKnowledgeBase
 from phi.vectordb.pgvector import PgVector2
-from phi.assistant import Assistant
-from resources import vector_db
-from knowledge_base import knowledge_base
-from pathlib import Path
+
+from resources import vector_db  # type: ignore
 
 
 # Initialize the TextKnowledgeBase
@@ -13,19 +14,16 @@
         collection="text_documents",
         db_url=vector_db.get_db_connection_local(),
     ),
-    formats=[".txt"],  # Formats accepted by this knowledge base
     num_documents=5,  # Number of documents to return on search
-    optimize_on=10,  # Number of documents to optimize the vector db on
 )
+# Load the knowledge base
+knowledge_base.load(recreate=False)
 
 # Initialize the Assistant with the knowledge_base
 assistant = Assistant(
     knowledge_base=knowledge_base,
     add_references_to_prompt=True,
 )
 
-# Load the knowledge base
-assistant.knowledge_base.load(recreate=False)
-
 # Use the assistant
-assistant.print_response("Ask me about something from the knowledge base",markdown=True)
+assistant.print_response("Ask me about something from the knowledge base", markdown=True)

phi/llm/anyscale/anyscale.py

@@ -2,7 +2,7 @@
 from typing import Optional
 
 from phi.llm.openai.like import OpenAILike
-  
+
 
 class Anyscale(OpenAILike):
     name: str = "Anyscale"