add pinecone service

.gitignore

@@ -0,0 +1,163 @@
+*.ipynb
+script/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

service/__init__.py

@@ -0,0 +1 @@
+from .vector_store import VectorStore

service/pinecone.py

@@ -1,23 +0,0 @@
-import os
-import pinecone
-from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.vectorstores import Pinecone
-
-
-class VectorStore(Pinecone):
-
-    def __init__(self,index_name) -> None:
-        pinecone.init(
-            api_key=os.getenv("PINECONE_API_KEY"),  # find at app.pinecone.io
-            environment=os.getenv("PINECONE_ENV"),  # next to api key in console
-        )
-        self.index_name = index_name
-        self.embeddings = OpenAIEmbeddings()
-        self.dims = 1536
-        index = pinecone.Index(self.index_name)
-        super().__init__(index, self.embeddings, "text")  
-
-    def add_docs(self,docs):
-        if self.index_name not in pinecone.list_indexes():
-            pinecone.create_index(name=self.index_name, metric="cosine", dimension=self.dims)
-        Pinecone.from_documents(docs, self.embeddings, index_name=self.index_name)

service/vector_store.py

@@ -0,0 +1,118 @@
+import os
+import pinecone
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores import Pinecone
+from typing import TYPE_CHECKING, Any, Callable, Iterable, List, Optional, Tuple, Union
+from langchain.docstore.document import Document
+from langchain.schema.embeddings import Embeddings
+from langchain.vectorstores.utils import DistanceStrategy, maximal_marginal_relevance
+import numpy as np
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+class VectorStore(Pinecone):
+
+    def __init__(self,index_name) -> None:
+        pinecone.init(
+            api_key=os.getenv("PINECONE_API_KEY"),  # find at app.pinecone.io
+            environment=os.getenv("PINECONE_ENV"),  # next to api key in console
+        )
+        self.index_name = index_name
+        self.dims = 1536
+        index = pinecone.Index(self.index_name)
+        super().__init__(index, OpenAIEmbeddings(), "text")  
+
+    def add_docs(self,docs):
+        if self.index_name not in pinecone.list_indexes():
+            pinecone.create_index(name=self.index_name, metric="cosine", dimension=self.dims)
+        Pinecone.from_documents(docs, self.embeddings, index_name=self.index_name)
+
+    def similarity_search_by_vector_with_score(
+        self,
+        embedding: List[float],
+        *,
+        k: int = 4,
+        filter: Optional[dict] = None,
+        namespace: Optional[str] = None,
+    ) -> List[Tuple[Document, float]]:
+        """Return pinecone documents most similar to embedding, along with scores."""
+
+        if namespace is None:
+            namespace = self._namespace
+        docs = []
+        results = self._index.query(
+            [embedding],
+            top_k=k,
+            include_metadata=True,
+            namespace=namespace,
+            filter=filter,
+        )
+        for res in results["matches"]:
+            metadata = res["metadata"]
+            if self._text_key in metadata:
+                text = metadata.pop(self._text_key)
+                score = res["score"]
+                metadata['score'] = score
+                print(f"metadata {metadata}")
+                docs.append((Document(page_content=text, metadata=metadata), score))
+            else:
+                logger.warning(
+                    f"Found document with no `{self._text_key}` key. Skipping."
+                )
+        return docs
+    
+    def max_marginal_relevance_search_by_vector(
+        self,
+        embedding: List[float],
+        k: int = 4,
+        fetch_k: int = 20,
+        lambda_mult: float = 0.5,
+        filter: Optional[dict] = None,
+        namespace: Optional[str] = None,
+        **kwargs: Any,
+    ) -> List[Document]:
+        """Return docs selected using the maximal marginal relevance.
+
+        Maximal marginal relevance optimizes for similarity to query AND diversity
+        among selected documents.
+
+        Args:
+            embedding: Embedding to look up documents similar to.
+            k: Number of Documents to return. Defaults to 4.
+            fetch_k: Number of Documents to fetch to pass to MMR algorithm.
+            lambda_mult: Number between 0 and 1 that determines the degree
+                        of diversity among the results with 0 corresponding
+                        to maximum diversity and 1 to minimum diversity.
+                        Defaults to 0.5.
+        Returns:
+            List of Documents selected by maximal marginal relevance.
+        """
+        if namespace is None:
+            namespace = self._namespace
+        results = self._index.query(
+            [embedding],
+            top_k=fetch_k,
+            include_values=True,
+            include_metadata=True,
+            namespace=namespace,
+            filter=filter,
+        )
+        mmr_selected = maximal_marginal_relevance(
+            np.array([embedding], dtype=np.float32),
+            [item["values"] for item in results["matches"]],
+            k=k,
+            lambda_mult=lambda_mult,
+        )
+        selected = []
+        for i in mmr_selected:
+            metadata = results["matches"][i]["metadata"]
+            score = results["matches"][i]["score"]
+            metadata['score'] = score
+            selected.append(metadata)
+        # selected = [results["matches"][i]["metadata"] for i in mmr_selected]
+        return [
+            Document(page_content=metadata.pop((self._text_key)), metadata=metadata)
+            for metadata in selected
+        ]

test/vector_store.py

@@ -0,0 +1,7 @@
+from service import VectorStore
+
+index_name = 'filecoin'
+vector_store = VectorStore(index_name)
+print(vector_store.similarity_search("what is filecoin"))
+
+print(vector_store.max_marginal_relevance_search("what is filecoin"))