Merge pull request #99 from pinecone-io/rename_canopy

Rename canopy

.github/workflows/pre-release-CI.yml

@@ -38,7 +38,7 @@ jobs:
 
       - name: Install the wheel
         run: |
-          pip install dist/pinecone_resin*.whl
+          pip install dist/pinecone_canopy*.whl
 
       - name: Create dev requirements file
         run: |

docs/library.md

@@ -1,16 +1,16 @@
-# Resin Library
+# Canopy Library
 
-For most common use cases, users can simply deploy the fully-configurable [Resin service](../README.md), which provides a REST API backend for your own RAG-infused Chatbot.  
+For most common use cases, users can simply deploy the fully-configurable [Canopy service](../README.md), which provides a REST API backend for your own RAG-infused Chatbot.  
 
-For advanced users, this page describes how to use `resin` core library directly to implement their own custom applications. 
+For advanced users, this page describes how to use `canopy` core library directly to implement their own custom applications. 
 
-The idea behind Resin library is to provide a framework to build AI applications on top of Pinecone as a long memory storage for you own data. Resin library designed with the following principles in mind:
+The idea behind Canopy library is to provide a framework to build AI applications on top of Pinecone as a long memory storage for you own data. Canopy library designed with the following principles in mind:
 
-- **Easy to use**: Resin is designed to be easy to use. It is well packaged and can be installed with a single command.
-- **Modularity**: Resin is built as a collection of modules that can be used together or separately. For example, you can use the `chat_engine` module to build a chatbot on top of your data, or you can use the `knowledge_base` module to directly store and search your data.
-- **Extensibility**: Resin is designed to be extensible. You can easily add your own components and extend the functionality.
-- **Production ready**: Resin designed to be production ready, tested, well documented, maintained and supported.
-- **Open source**: Resin is open source and free to use. It built in partnership with the community and for the community.
+- **Easy to use**: Canopy is designed to be easy to use. It is well packaged and can be installed with a single command.
+- **Modularity**: Canopy is built as a collection of modules that can be used together or separately. For example, you can use the `chat_engine` module to build a chatbot on top of your data, or you can use the `knowledge_base` module to directly store and search your data.
+- **Extensibility**: Canopy is designed to be extensible. You can easily add your own components and extend the functionality.
+- **Production ready**: Canopy designed to be production ready, tested, well documented, maintained and supported.
+- **Open source**: Canopy is open source and free to use. It built in partnership with the community and for the community.
 
 
 ## High level architecture
@@ -19,27 +19,27 @@ The idea behind Resin library is to provide a framework to build AI applications
 
 ## Setup
 
-To setup resin, please follow the instructions [here](../README.md#setup).
+To setup canopy, please follow the instructions [here](../README.md#setup).
 
 ## Quickstart
 
 ### Step 1: Initialize global Tokenizer
 
 The `Tokenizer` object is used for converting text into tokens, which is the basic data represntation that is used for processing.
 
-Since manny different classes rely on a tokenizer,  Resin uses a singleton `Tokenizer` object which needs to be initialized once. 
+Since manny different classes rely on a tokenizer,  Canopy uses a singleton `Tokenizer` object which needs to be initialized once. 
 
-Before instantiating any other resin core objects, please initialize the `Tokenizer` singleton:
+Before instantiating any other canopy core objects, please initialize the `Tokenizer` singleton:
 
 ```python
-from resin.tokenizer import Tokenizer
+from canopy.tokenizer import Tokenizer
 Tokenizer.initialize()
 ```
 
 Then, each time you want to use the tokenizer, you can simply instantiate a local object:
 
 ```python
-from resin.tokenizer import Tokenizer
+from canopy.tokenizer import Tokenizer
 
 # no need to pass any parameters, the global tokenizer will be used
 tokenizer = Tokenizer()
@@ -58,7 +58,7 @@ The `Tokenizer` singleton is holding an inner `Tokenizer` object that implements
 
 You can create your own customized tokenizer by implementing a new class that derives from `BaseTokenizer`, then passing this class to the `Tokenizer` singleton during initialization. Example:
 ```python
-from resin.tokenizer import Tokenizer, BaseTokenizer
+from canopy.tokenizer import Tokenizer, BaseTokenizer
 
 class CustomTokenizer(BaseTokenizer):
     # Implement BaseToknizer's abstract methods, like `def tokenize()` etc.
@@ -70,8 +70,8 @@ Tokenizer.initialize(tokenizer_class=CustomTokenizer)
 When you initialize the `Tokenizer` singleton, you can pass init arguments to the underlying Tokenizer class. Any init argument that is expected by the underlying class's constructor, can be passed as `kwarg` directly to `Tokenizer.initalize()`. For example:
 
 ```python
-from resin.tokenizer import Tokenizer
-from resin.tokenizer.openai import OpenAITokenizer
+from canopy.tokenizer import Tokenizer
+from canopy.tokenizer.openai import OpenAITokenizer
 Tokenizer.initialize(tokenizer_class=OpenAITokenizer, model_name="gpt2")
 ```
 
@@ -85,15 +85,15 @@ Knowledge base is an object that is responsible for storing and query your data.
 To create a knowledge base, you can use the following command:
 
 ```python
-from resin.knowledge_base import KnowledgeBase
+from canopy.knowledge_base import KnowledgeBase
 
 kb = KnowledgeBase(index_name="my-index")
 ```
 
-To create a new Pinecone index and connect it to the knowledge base, you can use the `create_resin_index` method:
+To create a new Pinecone index and connect it to the knowledge base, you can use the `create_canopy_index` method:
 
 ```python
-kb.create_resin_index()
+kb.create_canopy_index()
 ```
 
 Then, you will be able to mange the index in Pinecone [console](https://app.pinecone.io/).
@@ -117,7 +117,7 @@ To learn more about customizing the KnowledgeBase and its inner components, see
 To insert data into the knowledge base, you can create a list of documents and use the `upsert` method:
 
 ```python
-from resin.models.data_models import Document
+from canopy.models.data_models import Document
 documents = [Document(id="1", text="U2 are an Irish rock band from Dublin, formed in 1976.", source="https://url.com"),
              Document(id="2", text="Arctic Monkeys are an English rock band formed in Sheffield in 2002.", source="https://another-url.com", metadata={"my-key": "my-value"})]
 kb.upsert(documents)
@@ -126,7 +126,7 @@ kb.upsert(documents)
 Now you can query the knowledge base with the `query` method to find the most similar documents to a given text:
 
 ```python
-from resin.models.query_models import Query
+from canopy.models.query_models import Query
 results = kb.query([Query("Arctic Monkeys music genre"),
                     Query(text="U2 music genre",
                           top_k=10,
@@ -146,7 +146,7 @@ The output of the context engine is designed to provide the LLM the most relevan
 To create a context engine using a knowledge base, you can use the following command:
 
 ```python
-from resin.context_engine import ContextEngine
+from canopy.context_engine import ContextEngine
 context_engine = ContextEngine(kb)
 ```
 
@@ -183,7 +183,7 @@ Given chat history, the chat engine orchestrates its underlying context engine a
 To create a chat engine using a context, you can use the following command:
 
 ```python
-from resin.chat_engine import ChatEngine
+from canopy.chat_engine import ChatEngine
 chat_engine = ChatEngine(context_engine)
 ```
 
@@ -195,7 +195,7 @@ chat_engine.chat("what is the genre of Arctic Monkeys band?")
 ```
 
 
-Resin designed to be production ready and handle any conversation length and context length. Therefore, the chat engine uses internal components to handle long conversations and long contexts.
+Canopy designed to be production ready and handle any conversation length and context length. Therefore, the chat engine uses internal components to handle long conversations and long contexts.
 By default, long chat history is truncated to the latest messages that fits the token budget. It orchestrates the context engine to retrieve context that fits the token budget and then use the LLM to generate the next response.
 
 

pyproject.toml

@@ -1,11 +1,11 @@
 [tool.poetry]
-name = "pinecone-resin"
+name = "pinecone-canopy"
 version = "0.1.0"
-description = "Resin is an orchestration engine for intergating LLMs with Pinecone."
+description = "Canopy is an orchestration engine for intergating LLMs with Pinecone."
 authors = ["Relevance Team <relevance@pinecone.io>"]
 readme = "README.md"
-packages = [{include = "resin", from = "src"},
-            {include = "resin_cli", from = "src"},]
+packages = [{include = "canopy", from = "src"},
+            {include = "canopy_cli", from = "src"},]
 
 
 [tool.poetry.dependencies]
@@ -68,5 +68,4 @@ exclude = ['.venv']
 max-line-length = 88
 
 [tool.poetry.scripts]
-resin = "resin_cli.cli:cli"
-service = "resin_cli.service.app:start"
+canopy = "canopy_cli.cli:cli"

src/resin/__init__.py → src/canopy/__init__.py

@@ -1,4 +1,4 @@
 import importlib.metadata
 
 # Taken from https://stackoverflow.com/a/67097076
-__version__ = importlib.metadata.version("pinecone-resin")
+__version__ = importlib.metadata.version("pinecone-canopy")

src/resin/chat_engine/chat_engine.py → src/canopy/chat_engine/chat_engine.py

@@ -2,18 +2,18 @@
 from abc import ABC, abstractmethod
 from typing import Iterable, Union, Optional, cast
 
-from resin.chat_engine.models import HistoryPruningMethod
-from resin.chat_engine.prompt_builder import PromptBuilder
-from resin.chat_engine.query_generator import (QueryGenerator,
-                                               FunctionCallingQueryGenerator, )
-from resin.context_engine import ContextEngine
-from resin.tokenizer import Tokenizer
-from resin.llm import BaseLLM, OpenAILLM
-from resin.llm.models import ModelParams, SystemMessage
-from resin.models.api_models import (StreamingChatChunk, ChatResponse,
-                                     StreamingChatResponse, )
-from resin.models.data_models import Context, Messages
-from resin.utils.config import ConfigurableMixin
+from canopy.chat_engine.models import HistoryPruningMethod
+from canopy.chat_engine.prompt_builder import PromptBuilder
+from canopy.chat_engine.query_generator import (QueryGenerator,
+                                                FunctionCallingQueryGenerator, )
+from canopy.context_engine import ContextEngine
+from canopy.tokenizer import Tokenizer
+from canopy.llm import BaseLLM, OpenAILLM
+from canopy.llm.models import ModelParams, SystemMessage
+from canopy.models.api_models import (StreamingChatChunk, ChatResponse,
+                                      StreamingChatResponse, )
+from canopy.models.data_models import Context, Messages
+from canopy.utils.config import ConfigurableMixin
 
 CE_DEBUG_INFO = os.getenv("CE_DEBUG_INFO", "FALSE").lower() == "true"
 

src/resin/chat_engine/history_pruner/base.py → src/canopy/chat_engine/history_pruner/base.py

@@ -1,8 +1,8 @@
 from abc import ABC, abstractmethod
 from typing import Tuple
 
-from resin.tokenizer import Tokenizer
-from resin.models.data_models import Messages
+from canopy.tokenizer import Tokenizer
+from canopy.models.data_models import Messages
 
 
 class HistoryPruner(ABC):

src/resin/chat_engine/history_pruner/raising.py → src/canopy/chat_engine/history_pruner/raising.py

@@ -1,7 +1,7 @@
 from typing import Tuple
 
-from resin.chat_engine.history_pruner.base import HistoryPruner
-from resin.models.data_models import Messages
+from canopy.chat_engine.history_pruner.base import HistoryPruner
+from canopy.models.data_models import Messages
 
 
 class RaisingHistoryPruner(HistoryPruner):

src/resin/chat_engine/history_pruner/recent.py → src/canopy/chat_engine/history_pruner/recent.py

@@ -1,7 +1,7 @@
 from typing import Tuple
 
-from resin.chat_engine.history_pruner.base import HistoryPruner
-from resin.models.data_models import Messages
+from canopy.chat_engine.history_pruner.base import HistoryPruner
+from canopy.models.data_models import Messages
 
 
 class RecentHistoryPruner(HistoryPruner):

src/resin/chat_engine/prompt_builder/prompt_builder.py → src/canopy/chat_engine/prompt_builder/prompt_builder.py

@@ -1,12 +1,12 @@
 from abc import ABC, abstractmethod
 
-from resin.chat_engine.exceptions import InvalidRequestError
-from resin.chat_engine.history_pruner import (RaisingHistoryPruner,
-                                              RecentHistoryPruner, )
-from resin.chat_engine.history_pruner.base import HistoryPruner
-from resin.chat_engine.models import HistoryPruningMethod
-from resin.tokenizer import Tokenizer
-from resin.models.data_models import Messages, Role, MessageBase
+from canopy.chat_engine.exceptions import InvalidRequestError
+from canopy.chat_engine.history_pruner import (RaisingHistoryPruner,
+                                               RecentHistoryPruner, )
+from canopy.chat_engine.history_pruner.base import HistoryPruner
+from canopy.chat_engine.models import HistoryPruningMethod
+from canopy.tokenizer import Tokenizer
+from canopy.models.data_models import Messages, Role, MessageBase
 
 
 class BasePromptBuilder(ABC):

src/resin/chat_engine/query_generator/base.py → src/canopy/chat_engine/query_generator/base.py

@@ -1,8 +1,8 @@
 from abc import ABC, abstractmethod
 from typing import List
 
-from resin.models.data_models import Messages, Query
-from resin.utils.config import ConfigurableMixin
+from canopy.models.data_models import Messages, Query
+from canopy.utils.config import ConfigurableMixin
 
 
 class QueryGenerator(ABC, ConfigurableMixin):

src/resin/chat_engine/query_generator/function_calling.py → src/canopy/chat_engine/query_generator/function_calling.py

@@ -1,12 +1,12 @@
 from typing import List, Optional
 
-from resin.chat_engine.models import HistoryPruningMethod
-from resin.chat_engine.prompt_builder import PromptBuilder
-from resin.chat_engine.query_generator import QueryGenerator
-from resin.llm import BaseLLM, OpenAILLM
-from resin.llm.models import (Function, FunctionParameters,
-                              FunctionArrayProperty)
-from resin.models.data_models import Messages, Query
+from canopy.chat_engine.models import HistoryPruningMethod
+from canopy.chat_engine.prompt_builder import PromptBuilder
+from canopy.chat_engine.query_generator import QueryGenerator
+from canopy.llm import BaseLLM, OpenAILLM
+from canopy.llm.models import (Function, FunctionParameters,
+                               FunctionArrayProperty)
+from canopy.models.data_models import Messages, Query
 
 DEFAULT_SYSTEM_PROMPT = """Your task is to formulate search queries for a search engine, to assist in responding to the user's question.
 You should break down complex questions into sub-queries if needed.

src/resin/context_engine/context_builder/base.py → src/canopy/context_engine/context_builder/base.py

@@ -1,9 +1,9 @@
 from abc import ABC, abstractmethod
 from typing import List
 
-from resin.knowledge_base.models import QueryResult
-from resin.models.data_models import Context
-from resin.utils.config import ConfigurableMixin
+from canopy.knowledge_base.models import QueryResult
+from canopy.models.data_models import Context
+from canopy.utils.config import ConfigurableMixin
 
 
 class ContextBuilder(ABC, ConfigurableMixin):

src/resin/context_engine/context_builder/stuffing.py → src/canopy/context_engine/context_builder/stuffing.py

@@ -1,11 +1,11 @@
 from itertools import zip_longest
 from typing import List, Tuple
 
-from resin.context_engine.context_builder.base import ContextBuilder
-from resin.context_engine.models import ContextQueryResult, ContextSnippet
-from resin.knowledge_base.models import QueryResult, DocumentWithScore
-from resin.tokenizer import Tokenizer
-from resin.models.data_models import Context
+from canopy.context_engine.context_builder.base import ContextBuilder
+from canopy.context_engine.models import ContextQueryResult, ContextSnippet
+from canopy.knowledge_base.models import QueryResult, DocumentWithScore
+from canopy.tokenizer import Tokenizer
+from canopy.models.data_models import Context
 
 
 class StuffingContextBuilder(ContextBuilder):

src/resin/context_engine/context_engine.py → src/canopy/context_engine/context_engine.py

@@ -2,12 +2,12 @@
 from abc import ABC, abstractmethod
 from typing import List, Optional
 
-from resin.context_engine.context_builder import StuffingContextBuilder
-from resin.context_engine.context_builder.base import ContextBuilder
-from resin.knowledge_base import KnowledgeBase
-from resin.knowledge_base.base import BaseKnowledgeBase
-from resin.models.data_models import Context, Query
-from resin.utils.config import ConfigurableMixin
+from canopy.context_engine.context_builder import StuffingContextBuilder
+from canopy.context_engine.context_builder.base import ContextBuilder
+from canopy.knowledge_base import KnowledgeBase
+from canopy.knowledge_base.base import BaseKnowledgeBase
+from canopy.models.data_models import Context, Query
+from canopy.utils.config import ConfigurableMixin
 
 CE_DEBUG_INFO = os.getenv("CE_DEBUG_INFO", "FALSE").lower() == "true"
 

src/resin/context_engine/models.py → src/canopy/context_engine/models.py

@@ -2,7 +2,7 @@
 
 from pydantic import BaseModel
 
-from resin.models.data_models import ContextContent
+from canopy.models.data_models import ContextContent
 
 
 class ContextSnippet(BaseModel):

src/resin/knowledge_base/base.py → src/canopy/knowledge_base/base.py

@@ -1,9 +1,9 @@
 from abc import ABC, abstractmethod
 from typing import List, Optional
 
-from resin.knowledge_base.models import QueryResult
-from resin.models.data_models import Query, Document
-from resin.utils.config import ConfigurableMixin
+from canopy.knowledge_base.models import QueryResult
+from canopy.models.data_models import Query, Document
+from canopy.utils.config import ConfigurableMixin
 
 
 class BaseKnowledgeBase(ABC, ConfigurableMixin):

src/resin/knowledge_base/chunker/base.py → src/canopy/knowledge_base/chunker/base.py

@@ -1,9 +1,9 @@
 from abc import ABC, abstractmethod
 from typing import List
 
-from resin.knowledge_base.models import KBDocChunk
-from resin.models.data_models import Document
-from resin.utils.config import ConfigurableMixin
+from canopy.knowledge_base.models import KBDocChunk
+from canopy.models.data_models import Document
+from canopy.utils.config import ConfigurableMixin
 
 
 class Chunker(ABC, ConfigurableMixin):

src/resin/knowledge_base/chunker/markdown.py → src/canopy/knowledge_base/chunker/markdown.py

@@ -2,8 +2,8 @@
 
 from .langchain_text_splitter import Language, RecursiveCharacterTextSplitter
 from .recursive_character import RecursiveCharacterChunker
-from resin.knowledge_base.models import KBDocChunk
-from resin.models.data_models import Document
+from canopy.knowledge_base.models import KBDocChunk
+from canopy.models.data_models import Document
 
 
 class MarkdownChunker(RecursiveCharacterChunker):