community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463)

Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes
2025-09-15 22:44:36 +00:00 · 2023-12-11 13:53:30 -08:00
parent c0f4b95aa9
commit ed58eeb9c5
2446 changed files with 171805 additions and 137118 deletions
--- a/libs/community/langchain_community/vectorstores/tigris.py
+++ b/libs/community/langchain_community/vectorstores/tigris.py
@@ -0,0 +1,148 @@
+from __future__ import annotations
+
+import itertools
+from typing import TYPE_CHECKING, Any, Iterable, List, Optional, Tuple
+
+from langchain_core.documents import Document
+from langchain_core.embeddings import Embeddings
+from langchain_core.vectorstores import VectorStore
+
+if TYPE_CHECKING:
+    from tigrisdb import TigrisClient
+    from tigrisdb import VectorStore as TigrisVectorStore
+    from tigrisdb.types.filters import Filter as TigrisFilter
+    from tigrisdb.types.vector import Document as TigrisDocument
+
+
+class Tigris(VectorStore):
+    """`Tigris` vector store."""
+
+    def __init__(self, client: TigrisClient, embeddings: Embeddings, index_name: str):
+        """Initialize Tigris vector store."""
+        try:
+            import tigrisdb  # noqa: F401
+        except ImportError:
+            raise ImportError(
+                "Could not import tigrisdb python package. "
+                "Please install it with `pip install tigrisdb`"
+            )
+
+        self._embed_fn = embeddings
+        self._vector_store = TigrisVectorStore(client.get_search(), index_name)
+
+    @property
+    def embeddings(self) -> Embeddings:
+        return self._embed_fn
+
+    @property
+    def search_index(self) -> TigrisVectorStore:
+        return self._vector_store
+
+    def add_texts(
+        self,
+        texts: Iterable[str],
+        metadatas: Optional[List[dict]] = None,
+        ids: Optional[List[str]] = None,
+        **kwargs: Any,
+    ) -> List[str]:
+        """Run more texts through the embeddings and add to the vectorstore.
+
+        Args:
+            texts: Iterable of strings to add to the vectorstore.
+            metadatas: Optional list of metadatas associated with the texts.
+            ids: Optional list of ids for documents.
+                Ids will be autogenerated if not provided.
+            kwargs: vectorstore specific parameters
+
+        Returns:
+            List of ids from adding the texts into the vectorstore.
+        """
+        docs = self._prep_docs(texts, metadatas, ids)
+        result = self.search_index.add_documents(docs)
+        return [r.id for r in result]
+
+    def similarity_search(
+        self,
+        query: str,
+        k: int = 4,
+        filter: Optional[TigrisFilter] = None,
+        **kwargs: Any,
+    ) -> List[Document]:
+        """Return docs most similar to query."""
+        docs_with_scores = self.similarity_search_with_score(query, k, filter)
+        return [doc for doc, _ in docs_with_scores]
+
+    def similarity_search_with_score(
+        self,
+        query: str,
+        k: int = 4,
+        filter: Optional[TigrisFilter] = None,
+    ) -> List[Tuple[Document, float]]:
+        """Run similarity search with Chroma with distance.
+
+        Args:
+            query (str): Query text to search for.
+            k (int): Number of results to return. Defaults to 4.
+            filter (Optional[TigrisFilter]): Filter by metadata. Defaults to None.
+
+        Returns:
+            List[Tuple[Document, float]]: List of documents most similar to the query
+                text with distance in float.
+        """
+        vector = self._embed_fn.embed_query(query)
+        result = self.search_index.similarity_search(
+            vector=vector, k=k, filter_by=filter
+        )
+        docs: List[Tuple[Document, float]] = []
+        for r in result:
+            docs.append(
+                (
+                    Document(
+                        page_content=r.doc["text"], metadata=r.doc.get("metadata")
+                    ),
+                    r.score,
+                )
+            )
+        return docs
+
+    @classmethod
+    def from_texts(
+        cls,
+        texts: List[str],
+        embedding: Embeddings,
+        metadatas: Optional[List[dict]] = None,
+        ids: Optional[List[str]] = None,
+        client: Optional[TigrisClient] = None,
+        index_name: Optional[str] = None,
+        **kwargs: Any,
+    ) -> Tigris:
+        """Return VectorStore initialized from texts and embeddings."""
+        if not index_name:
+            raise ValueError("`index_name` is required")
+
+        if not client:
+            client = TigrisClient()
+        store = cls(client, embedding, index_name)
+        store.add_texts(texts=texts, metadatas=metadatas, ids=ids)
+        return store
+
+    def _prep_docs(
+        self,
+        texts: Iterable[str],
+        metadatas: Optional[List[dict]],
+        ids: Optional[List[str]],
+    ) -> List[TigrisDocument]:
+        embeddings: List[List[float]] = self._embed_fn.embed_documents(list(texts))
+        docs: List[TigrisDocument] = []
+        for t, m, e, _id in itertools.zip_longest(
+            texts, metadatas or [], embeddings or [], ids or []
+        ):
+            doc: TigrisDocument = {
+                "text": t,
+                "embeddings": e or [],
+                "metadata": m or {},
+            }
+            if _id:
+                doc["id"] = _id
+            docs.append(doc)
+        return docs