diff options
author | Nate Sesti <33237525+sestinj@users.noreply.github.com> | 2023-10-09 18:37:27 -0700 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-10-09 18:37:27 -0700 |
commit | f09150617ed2454f3074bcf93f53aae5ae637d40 (patch) | |
tree | 5cfe614a64d921dfe58b049f426d67a8b832c71f /server/continuedev/plugins/context_providers/embeddings.py | |
parent | 985304a213f620cdff3f8f65f74ed7e3b79be29d (diff) | |
download | sncontinue-f09150617ed2454f3074bcf93f53aae5ae637d40.tar.gz sncontinue-f09150617ed2454f3074bcf93f53aae5ae637d40.tar.bz2 sncontinue-f09150617ed2454f3074bcf93f53aae5ae637d40.zip |
Preview (#541)
* Strong typing (#533)
* refactor: :recycle: get rid of continuedev.src.continuedev structure
* refactor: :recycle: switching back to server folder
* feat: :sparkles: make config.py imports shorter
* feat: :bookmark: publish as pre-release vscode extension
* refactor: :recycle: refactor and add more completion params to ui
* build: :building_construction: download from preview S3
* fix: :bug: fix paths
* fix: :green_heart: package:pre-release
* ci: :green_heart: more time for tests
* fix: :green_heart: fix build scripts
* fix: :bug: fix import in run.py
* fix: :bookmark: update version to try again
* ci: 💚 Update package.json version [skip ci]
* refactor: :fire: don't check for old extensions version
* fix: :bug: small bug fixes
* fix: :bug: fix config.py import paths
* ci: 💚 Update package.json version [skip ci]
* ci: :green_heart: platform-specific builds test #1
* feat: :green_heart: ship with binary
* fix: :green_heart: fix copy statement to include.exe for windows
* fix: :green_heart: cd extension before packaging
* chore: :loud_sound: count tokens generated
* fix: :green_heart: remove npm_config_arch
* fix: :green_heart: publish as pre-release!
* chore: :bookmark: update version
* perf: :green_heart: hardcode distro paths
* fix: :bug: fix yaml syntax error
* chore: :bookmark: update version
* fix: :green_heart: update permissions and version
* feat: :bug: kill old server if needed
* feat: :lipstick: update marketplace icon for pre-release
* ci: 💚 Update package.json version [skip ci]
* feat: :sparkles: auto-reload for config.py
* feat: :wrench: update default config.py imports
* feat: :sparkles: codelens in config.py
* feat: :sparkles: select model param count from UI
* ci: 💚 Update package.json version [skip ci]
* feat: :sparkles: more model options, ollama error handling
* perf: :zap: don't show server loading immediately
* fix: :bug: fixing small UI details
* ci: 💚 Update package.json version [skip ci]
* feat: :rocket: headers param on LLM class
* fix: :bug: fix headers for openai.;y
* feat: :sparkles: highlight code on cmd+shift+L
* ci: 💚 Update package.json version [skip ci]
* feat: :lipstick: sticky top bar in gui.tsx
* fix: :loud_sound: websocket logging and horizontal scrollbar
* ci: 💚 Update package.json version [skip ci]
* feat: :sparkles: allow AzureOpenAI Service through GGML
* ci: 💚 Update package.json version [skip ci]
* fix: :bug: fix automigration
* ci: 💚 Update package.json version [skip ci]
* ci: :green_heart: upload binaries in ci, download apple silicon
* chore: :fire: remove notes
* fix: :green_heart: use curl to download binary
* fix: :green_heart: set permissions on apple silicon binary
* fix: :green_heart: testing
* fix: :green_heart: cleanup file
* fix: :green_heart: fix preview.yaml
* fix: :green_heart: only upload once per binary
* fix: :green_heart: install rosetta
* ci: :green_heart: download binary after tests
* ci: 💚 Update package.json version [skip ci]
* ci: :green_heart: prepare ci for merge to main
---------
Co-authored-by: GitHub Action <action@github.com>
Diffstat (limited to 'server/continuedev/plugins/context_providers/embeddings.py')
-rw-r--r-- | server/continuedev/plugins/context_providers/embeddings.py | 81 |
1 files changed, 81 insertions, 0 deletions
diff --git a/server/continuedev/plugins/context_providers/embeddings.py b/server/continuedev/plugins/context_providers/embeddings.py new file mode 100644 index 00000000..86cba311 --- /dev/null +++ b/server/continuedev/plugins/context_providers/embeddings.py @@ -0,0 +1,81 @@ +import os +import uuid +from typing import List, Optional + +from pydantic import BaseModel + +from ...core.context import ContextProvider +from ...core.main import ContextItem, ContextItemDescription, ContextItemId +from ...libs.chroma.query import ChromaIndexManager + + +class EmbeddingResult(BaseModel): + filename: str + content: str + + +class EmbeddingsProvider(ContextProvider): + title = "embed" + + display_title = "Embeddings Search" + description = "Search the codebase using embeddings" + dynamic = True + requires_query = True + + workspace_directory: str + + EMBEDDINGS_CONTEXT_ITEM_ID = "embeddings" + + index_manager: Optional[ChromaIndexManager] = None + + class Config: + arbitrary_types_allowed = True + + @property + def index(self): + if self.index_manager is None: + self.index_manager = ChromaIndexManager(self.workspace_directory) + return self.index_manager + + @property + def BASE_CONTEXT_ITEM(self): + return ContextItem( + content="", + description=ContextItemDescription( + name="Embedding Search", + description="Enter a query to embedding search codebase", + id=ContextItemId( + provider_title=self.title, item_id=self.EMBEDDINGS_CONTEXT_ITEM_ID + ), + ), + ) + + async def _get_query_results(self, query: str) -> str: + results = self.index.query_codebase_index(query) + + ret = [] + for node in results.source_nodes: + resource_name = list(node.node.relationships.values())[0] + filepath = resource_name[: resource_name.index("::")] + ret.append(EmbeddingResult(filename=filepath, content=node.node.text)) + + return ret + + async def provide_context_items(self) -> List[ContextItem]: + self.index.create_codebase_index() # TODO Synchronous here is not ideal + + return [self.BASE_CONTEXT_ITEM] + + async def add_context_item(self, id: ContextItemId, query: str): + if not id.provider_title == self.title: + raise Exception("Invalid provider title for item") + + results = await self._get_query_results(query) + + for i in range(len(results)): + result = results[i] + ctx_item = self.BASE_CONTEXT_ITEM.copy() + ctx_item.description.name = os.path.basename(result.filename) + ctx_item.content = f"{result.filename}\n```\n{result.content}\n```" + ctx_item.description.id.item_id = uuid.uuid4().hex + self.selected_items.append(ctx_item) |