vector-vault 2.2.0__tar.gz → 2.2.2__tar.gz

{vector_vault-2.2.0 → vector_vault-2.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vector_vault
-Version: 2.2.0
+Version: 2.2.2
 Summary: Customize ChatGPT and unleash the full potential of generative AI with Vector Vault
 Home-page: https://github.com/John-Rood/VectorVault
 Author: VectorVault.io
@@ -19,9 +19,9 @@ License-File: LICENSE
 
 Vector Vault is a cloud-native vector database combined with OpenAI. Easily call ChatGPT or GPT4 and customize how they respond. Take any text data, vectorize it, and add it to the cloud vector database in 3 lines of code. Vector Vault enables you to quickly and securely create and interact with your vector databases - aka "Vaults". Vaults are hosted on serverless distributed cloud architecture backed by Google, making `vectorvault` scalable to any project size. 
 
-`vectorvault` takes inspiration from LangChain and integrates their most popular chat features and LLM tools. However, by combining vector databases with OpenAI's chat into one single package, `vectorvault` is able to hide most of the complexity, making it simple to build custom chat experiences. The main value of the `vectorvault` package is how few lines of code you'll need to write to create the expirience you're goign for. It's much simpler and easier to use ChatGPT with the `vectorvault` package than OpenAI's default package. Customize what ChatGPT says by adding the kind of things you want it to say to the Vault. When you call the `get_chat()` function with "get_context=True", whatever you have added to the Vault will be the way ChatGPT sounds. Check out [PhilosophyGPT](https://philbrosophy.web.app) for an example of this (which was made using Vector Vault).
+`vectorvault` takes inspiration from LangChain, integrating their most popular chat features and LLM tools. However, by combining vector databases with OpenAI's chat into one single package, `vectorvault` is able to hide most of the complexity, making it simple to build custom chat experiences. It's even easier to use ChatGPT with the `vectorvault` package than OpenAI's default package, and you can customize what ChatGPT says by adding the kind of things you want it to say to the Vault. When you call the `get_chat()` function with "get_context=True", whatever you have added to the Vault will be the way ChatGPT sounds. Check out [PhilosophyGPT](https://philbrosophy.web.app) for an example of this (PhilosophyGPT is powered by Vector Vault in this way).
 
-Make bots with knowledge and personalities. Create dynamic game characters with goals and opinions, AI support reps for a product/service, or your alter ego AI self. Use the "LLM Exclusive Tools" to create AI smart automation in code. The possibilities are endless and only limited by your imagination.
+You can bots with knowledge and personalities, create dynamic game characters with goals and opinions, AI support reps for a product/service, or your alter ego AI self. Use the "LLM Exclusive Tools" to create AI smart automation in code. The possibilities are endless and limited only by your imagination.
 
 Check out the tutorials in the Examples folder. You don't need a Vector Vault API key to use the tools or chat features, but you will need one to access the Vault Cloud. If you don't already have one, you can sign up for a free account at [VectorVault.io](https://vectorvault.io). While the service is paid at production scale, the first tier is free, and the following tiers are very affordable.
 

{vector_vault-2.2.0 → vector_vault-2.2.2}/README.md

@@ -2,9 +2,9 @@
 
 Vector Vault is a cloud-native vector database combined with OpenAI. Easily call ChatGPT or GPT4 and customize how they respond. Take any text data, vectorize it, and add it to the cloud vector database in 3 lines of code. Vector Vault enables you to quickly and securely create and interact with your vector databases - aka "Vaults". Vaults are hosted on serverless distributed cloud architecture backed by Google, making `vectorvault` scalable to any project size. 
 
-`vectorvault` takes inspiration from LangChain and integrates their most popular chat features and LLM tools. However, by combining vector databases with OpenAI's chat into one single package, `vectorvault` is able to hide most of the complexity, making it simple to build custom chat experiences. The main value of the `vectorvault` package is how few lines of code you'll need to write to create the expirience you're goign for. It's much simpler and easier to use ChatGPT with the `vectorvault` package than OpenAI's default package. Customize what ChatGPT says by adding the kind of things you want it to say to the Vault. When you call the `get_chat()` function with "get_context=True", whatever you have added to the Vault will be the way ChatGPT sounds. Check out [PhilosophyGPT](https://philbrosophy.web.app) for an example of this (which was made using Vector Vault).
+`vectorvault` takes inspiration from LangChain, integrating their most popular chat features and LLM tools. However, by combining vector databases with OpenAI's chat into one single package, `vectorvault` is able to hide most of the complexity, making it simple to build custom chat experiences. It's even easier to use ChatGPT with the `vectorvault` package than OpenAI's default package, and you can customize what ChatGPT says by adding the kind of things you want it to say to the Vault. When you call the `get_chat()` function with "get_context=True", whatever you have added to the Vault will be the way ChatGPT sounds. Check out [PhilosophyGPT](https://philbrosophy.web.app) for an example of this (PhilosophyGPT is powered by Vector Vault in this way).
 
-Make bots with knowledge and personalities. Create dynamic game characters with goals and opinions, AI support reps for a product/service, or your alter ego AI self. Use the "LLM Exclusive Tools" to create AI smart automation in code. The possibilities are endless and only limited by your imagination.
+You can bots with knowledge and personalities, create dynamic game characters with goals and opinions, AI support reps for a product/service, or your alter ego AI self. Use the "LLM Exclusive Tools" to create AI smart automation in code. The possibilities are endless and limited only by your imagination.
 
 Check out the tutorials in the Examples folder. You don't need a Vector Vault API key to use the tools or chat features, but you will need one to access the Vault Cloud. If you don't already have one, you can sign up for a free account at [VectorVault.io](https://vectorvault.io). While the service is paid at production scale, the first tier is free, and the following tiers are very affordable.
 

{vector_vault-2.2.0 → vector_vault-2.2.2}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name="vector_vault",
-    version="2.2.0",
+    version="2.2.2",
     packages=find_packages(),
     author="VectorVault.io",
     author_email="john@johnrood.com",

{vector_vault-2.2.0 → vector_vault-2.2.2}/vector_vault.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vector-vault
-Version: 2.2.0
+Version: 2.2.2
 Summary: Customize ChatGPT and unleash the full potential of generative AI with Vector Vault
 Home-page: https://github.com/John-Rood/VectorVault
 Author: VectorVault.io
@@ -19,9 +19,9 @@ License-File: LICENSE
 
 Vector Vault is a cloud-native vector database combined with OpenAI. Easily call ChatGPT or GPT4 and customize how they respond. Take any text data, vectorize it, and add it to the cloud vector database in 3 lines of code. Vector Vault enables you to quickly and securely create and interact with your vector databases - aka "Vaults". Vaults are hosted on serverless distributed cloud architecture backed by Google, making `vectorvault` scalable to any project size. 
 
-`vectorvault` takes inspiration from LangChain and integrates their most popular chat features and LLM tools. However, by combining vector databases with OpenAI's chat into one single package, `vectorvault` is able to hide most of the complexity, making it simple to build custom chat experiences. The main value of the `vectorvault` package is how few lines of code you'll need to write to create the expirience you're goign for. It's much simpler and easier to use ChatGPT with the `vectorvault` package than OpenAI's default package. Customize what ChatGPT says by adding the kind of things you want it to say to the Vault. When you call the `get_chat()` function with "get_context=True", whatever you have added to the Vault will be the way ChatGPT sounds. Check out [PhilosophyGPT](https://philbrosophy.web.app) for an example of this (which was made using Vector Vault).
+`vectorvault` takes inspiration from LangChain, integrating their most popular chat features and LLM tools. However, by combining vector databases with OpenAI's chat into one single package, `vectorvault` is able to hide most of the complexity, making it simple to build custom chat experiences. It's even easier to use ChatGPT with the `vectorvault` package than OpenAI's default package, and you can customize what ChatGPT says by adding the kind of things you want it to say to the Vault. When you call the `get_chat()` function with "get_context=True", whatever you have added to the Vault will be the way ChatGPT sounds. Check out [PhilosophyGPT](https://philbrosophy.web.app) for an example of this (PhilosophyGPT is powered by Vector Vault in this way).
 
-Make bots with knowledge and personalities. Create dynamic game characters with goals and opinions, AI support reps for a product/service, or your alter ego AI self. Use the "LLM Exclusive Tools" to create AI smart automation in code. The possibilities are endless and only limited by your imagination.
+You can bots with knowledge and personalities, create dynamic game characters with goals and opinions, AI support reps for a product/service, or your alter ego AI self. Use the "LLM Exclusive Tools" to create AI smart automation in code. The possibilities are endless and limited only by your imagination.
 
 Check out the tutorials in the Examples folder. You don't need a Vector Vault API key to use the tools or chat features, but you will need one to access the Vault Cloud. If you don't already have one, you can sign up for a free account at [VectorVault.io](https://vectorvault.io). While the service is paid at production scale, the first tier is free, and the following tiers are very affordable.
 

{vector_vault-2.2.0 → vector_vault-2.2.2}/vectorvault/ai.py

@@ -147,6 +147,7 @@ class AI:
                 else: # no history. If it was overlimit, then it was taken care of above
                     pass
             prompt = prompt_template.format(content=user_input)
+
         if history:
             response = openai.ChatCompletion.create(
                 model=model,
@@ -161,10 +162,10 @@ class AI:
                     if 'content' in delta:
                         content = delta['content']
                         yield content
-        else:
+        else: # make no changes, and return response to custom_prompt
             response = openai.ChatCompletion.create(
                 model=model,
-                messages=[{"role": "user", "content": f"{prompt}"}],
+                messages=[{"role": "user", "content": f"{custom_prompt}"}],
                 stream=True
             )
             for message in response: