ai-parrot 0.5.9__cp311-cp311-manylinux_2_28_x86_64.whl → 0.5.11__cp311-cp311-manylinux_2_28_x86_64.whl

{ai_parrot-0.5.9.dist-info → ai_parrot-0.5.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ai-parrot
-Version: 0.5.9
+Version: 0.5.11
 Summary: Live Chatbots based on Langchain chatbots and Agents     Integrated into Navigator Framework or used into any aiohttp applications.
 Home-page: https://github.com/phenobarbital/ai-parrot
 Author: Jesus Lara

{ai_parrot-0.5.9.dist-info → ai_parrot-0.5.11.dist-info}/RECORD

@@ -4,14 +4,14 @@ parrot/exceptions.cpython-311-x86_64-linux-gnu.so,sha256=1tKBneucxl6ShNqI8KS4-pa
 parrot/manager.py,sha256=E1OdoNnZh1qCqVgZzcp8rdRnE1-xRwyQ6d1nFcOmg3U,6527
 parrot/models.py,sha256=MT88rYdITenwTuyCfeqHqaNf49rieAKz43R2TibN7G8,14314
 parrot/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-parrot/version.py,sha256=uuGJi_QomqOL8oXXvwTsmEi7k1OjqnC5QmKhiQZmywE,377
+parrot/version.py,sha256=C4CZL3SltVkkn8Nf0SUBHRIqD7QqcJGmj5peRWKjzsM,378
 parrot/bots/__init__.py,sha256=qD-WOn8n34VUCp7Mq6Mq1lZV8h_cKAeXQxn27UtBDP4,153
-parrot/bots/abstract.py,sha256=mmMEs9O_a7VJ9nx_IgvTqS7pMFML0U8sLnGaW5Qst0A,35790
+parrot/bots/abstract.py,sha256=8Oq47Cjt5-TAAdeyS3-JQd9FwPOumT2U6IIFMFXp02k,35886
 parrot/bots/agent.py,sha256=2v_5hQ3XCvCPpwTne7t-NDUpX3na1LIwXfufT-cK9LU,13432
 parrot/bots/base.py,sha256=Wl2BXRzxdGsWdHltAi0jalIPPAiM0TkVIHkRc1HQ99I,13422
 parrot/bots/basic.py,sha256=dg2kT_ynMEtZ3cMTcSovmDwrOo7BhBwL1o-Nn_7I85A,235
 parrot/bots/bose.py,sha256=gQQzAgt6wxGshihdr5H9_G4ns0lth814IkL7x1Ukjd4,759
-parrot/bots/chatbot.py,sha256=uvTCgTSCsbGRz2BZbk0Ueca3Lvzl_tBj4eUfqon0AQQ,10106
+parrot/bots/chatbot.py,sha256=E7pz0duU2-qrbo9QzvwM_Gfw2OtpcWziXvEZmfWfPeo,10201
 parrot/bots/cody.py,sha256=gPQPRcn7QNJfTF0zWI9i6K-PhyAG6PBVcoCxdvylRdI,616
 parrot/bots/copilot.py,sha256=PDK1Hj3TmxHgZT0rAplMnbbDkmV51B9tTstWWQjsLFM,2795
 parrot/bots/dataframe.py,sha256=CfZiLKIwnaku52nl2PNjciqRlH8m2lM4buO6xI7P408,3914
@@ -24,7 +24,7 @@ parrot/bots/prompts/__init__.py,sha256=rm_rAX7ZIxDIpSVOjHVuHRLMI9wS3avsu5fUfwAsd
 parrot/bots/prompts/agents.py,sha256=nXmzmRG15jiTDnjhmZ8ljSYCB1xU4RwsayZThFSj0Zg,4310
 parrot/bots/retrievals/__init__.py,sha256=AgI0mTB27tZ0Oyr7RU63G-ZO1VyX-uCJ6lwxgP4baag,45
 parrot/bots/retrievals/constitutional.py,sha256=x7kFR0KpmkR0Wz6bXNOeU3Hesn_EXc6eOSd4TdXxb8o,600
-parrot/bots/retrievals/multi.py,sha256=km1zaE2ialNYYjY5f9CrhNeA44SNeUlJ7wRUCL2yb4w,1790
+parrot/bots/retrievals/multi.py,sha256=gVsGIM6ynqDFdqryrEyQg6yYXIN3uGwAGby9fvacl_w,3667
 parrot/bots/retrievals/retrieval.py,sha256=wvMM53k76njV5b6t6CCKiYVk2o81JCHzCNmlHBKYFMg,20622
 parrot/chatbots/__init__.py,sha256=ypskCnME0xUv6psBEGCEyXCrD0J0ULHSllpVmSxqb4A,200
 parrot/chatbots/abstract.py,sha256=CmDn3k4r9uKImOZRN4L9zxLbCdC-1MPUAorDlfZT-kA,26421
@@ -101,12 +101,12 @@ parrot/loaders/handlers/data.py,sha256=olZ2p-wyUMGoazah7tgHY7V9buGX1FOeJ-cv2vGEo
 parrot/loaders/utils/__init__.py,sha256=SkDyK3MuPGhp0NM6kHvaxQDe97Gcl3n9t5A741OVh1c,28
 parrot/loaders/utils/models.py,sha256=BHcnFzS7oOKUGG-vPy_TlqeFNAC8puRgsIMX2mSgKxY,1059
 parrot/stores/__init__.py,sha256=W7Ggvvxw4Dn13IWbuXaT0KTTJJORpvLtTKuaajNUxNA,264
-parrot/stores/abstract.py,sha256=1ixPyClc8gaiafl3ZW7KtmwZTgVACFleF73DwzFsamk,7186
+parrot/stores/abstract.py,sha256=esoNpgcA_07RS3z2Qm7RtQd7pfKbhLoJMztoDwC_c1k,7387
 parrot/stores/chroma.py,sha256=UbPNs6P1o8BnUA0B_IwQ6n89VuZt7H2j0FpNmK22Ids,5932
 parrot/stores/duck.py,sha256=FTDV2HJb580ojVNBdUrC1ukuDUTyk4qUwF-LaN-IbWA,4740
 parrot/stores/empty.py,sha256=bCQJt54YPpR_pN9uHA2VA95GPPp04daMBJHbHQsRY0Q,234
 parrot/stores/faiss.py,sha256=tbur-YM7ictMh9S65Tc6WGK88JBkunQqES98w27CBtE,5694
-parrot/stores/milvus.py,sha256=Bi2geRA8yT0ux_DeYo436U38qth-Obpp_HN_NmPWRZ8,13209
+parrot/stores/milvus.py,sha256=rRM-oODKsTIEKiFBcygchqxpC94am2TLgbE0gw0NfJg,13275
 parrot/stores/postgres.py,sha256=7mZ4l8EKcTMegWw6ooI9nfIUCdlutMCzJfQ0ULQFh6k,24908
 parrot/stores/qdrant.py,sha256=u07DUoFHWDf-IU5tHbhinhMjPGWFgUbzaBhT_lWrvCA,6003
 parrot/stores/embeddings/__init__.py,sha256=ZQPpLBhiBx27Q5FhB_v-Vibcq3rHEP7x9GXfn_LGFOc,283
@@ -144,8 +144,8 @@ resources/users/handlers.py,sha256=BGzqBvPY_OaIF_nONWX4b_B5OyyBrdGuSihIsdlFwjk,2
 resources/users/models.py,sha256=glk7Emv7QCi6i32xRFDrGc8UwK23_LPg0XUOJoHnwRU,6799
 settings/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 settings/settings.py,sha256=9ueEvyLNurUX-AaIeRPV8GKX1c4YjDLbksUAeqEq6Ck,1854
-ai_parrot-0.5.9.dist-info/LICENSE,sha256=vRKOoa7onTsLNvSzJtGtMaNhWWh8B3YAT733Tlu6M4o,1070
-ai_parrot-0.5.9.dist-info/METADATA,sha256=kyo9XvvUMJ8Nhi8w-nD4P-Q2TFseOPbmjs9H9PxEx5g,9715
-ai_parrot-0.5.9.dist-info/WHEEL,sha256=lNWVJ6q28SO2kTKDIyc1kQ-4wE2w5snxBQXSv06oiUw,113
-ai_parrot-0.5.9.dist-info/top_level.txt,sha256=VCLpdIu_5wkShgIQjK85jFzL9HEVVjAqlQa_gupLekI,17
-ai_parrot-0.5.9.dist-info/RECORD,,
+ai_parrot-0.5.11.dist-info/LICENSE,sha256=vRKOoa7onTsLNvSzJtGtMaNhWWh8B3YAT733Tlu6M4o,1070
+ai_parrot-0.5.11.dist-info/METADATA,sha256=3cT8zN64WE4sXyaO5CwVAe5WkLs7-UHsrojIY7jy3bU,9716
+ai_parrot-0.5.11.dist-info/WHEEL,sha256=lNWVJ6q28SO2kTKDIyc1kQ-4wE2w5snxBQXSv06oiUw,113
+ai_parrot-0.5.11.dist-info/top_level.txt,sha256=VCLpdIu_5wkShgIQjK85jFzL9HEVVjAqlQa_gupLekI,17
+ai_parrot-0.5.11.dist-info/RECORD,,

parrot/bots/abstract.py

@@ -466,6 +466,7 @@ class AbstractBot(DBInterface, ABC):
 
     def configure_store(self, **kwargs):
         # TODO: Implement VectorStore Configuration
+        print('SELF > ', self._vector_store)
         if isinstance(self._vector_store, list):
             # Is a list of vector stores instances:
             for st in self._vector_store:
@@ -959,6 +960,7 @@ class AbstractBot(DBInterface, ABC):
                 return_messages=True
             )
         async with self.store as store:  #pylint: disable=E1101
+            print('STORES > ', self.stores, store)
             if self._use_vector:
                 if len(self.stores) > 1:
                     retriever = MultiVectorStoreRetriever(

parrot/bots/chatbot.py

@@ -244,6 +244,9 @@ class Chatbot(AbstractBot):
         vector_db = database.pop('vector_database', None)
         # configure vector database:
         if vector_db:
+            # Initialize the store:
+            self.stores = []
+            self.store = None
             self._use_vector = vector_store
             self._vector_store = database
             self.configure_store()

parrot/bots/retrievals/multi.py

@@ -1,50 +1,102 @@
-from typing import List
-from collections.abc import Callable
-from langchain.schema import Document
+from typing import List, Dict, Any, Optional
+from langchain_core.retrievers import BaseRetriever
+from langchain_core.callbacks import CallbackManagerForRetrieverRun
+from langchain_core.documents import Document
 
-class MultiVectorStoreRetriever:
+
+class MultiVectorStoreRetriever(BaseRetriever):
     """
     This aggregator retriever queries multiple vector stores
     and merges the results into a single list.
     """
 
+    stores: List[Any]
+    search_kwargs: Dict[str, Any]
+    chain_type: str
+    search_type: str
+    metric_type: str
+
     def __init__(
         self,
-        stores: List[Callable],
+        stores: List[Any],
         metric_type: str = 'COSINE',
         chain_type: str = 'stuff',
         search_type: str = 'similarity',
-        search_kwargs: dict = None,
+        search_kwargs: Optional[Dict[str, Any]] = None,
     ):
         """
-        stores: List of AbstractStore or anything that provides an as_retriever() method
-        search_kwargs: dict to pass on to each store's retrieve method (like 'k' for top_k)
+        Initialize the MultiVectorStoreRetriever.
+
+        Args:
+            stores: List of vector stores that provide an as_retriever() method
+            metric_type: Similarity metric (COSINE, EUCLIDEAN, DOT_PRODUCT)
+            chain_type: Chain type for the retriever
+            search_type: Search type (similarity, mmr)
+            search_kwargs: Dict to pass to each store's retrieve method (like 'k' for top_k)
         """
+        super().__init__()
         self.stores = stores
         self.search_kwargs = search_kwargs or {}
         self.chain_type = chain_type
         self.search_type = search_type
         self.metric_type = metric_type
 
-    def get_relevant_documents(self, query: str) -> List[Document]:
+    def _get_relevant_documents(
+        self, query: str, *, run_manager: CallbackManagerForRetrieverRun
+    ) -> List[Document]:
+        """
+        Get documents relevant to the query.
+        Implements the required method from BaseRetriever.
+
+        Args:
+            query: Query string
+            run_manager: CallbackManager for the run
+
+        Returns:
+            List of relevant documents
+        """
         all_results = []
         for store in self.stores:
-            retriever = store.as_retriever(**self.search_kwargs)
-            docs = retriever.get_relevant_documents(query)
+            retriever = store.as_retriever(
+                search_type=self.search_type,
+                search_kwargs=self.search_kwargs,
+                chain_type=self.chain_type
+            )
+            # Pass the run_manager to the sub-retrievers if they support it
+            if hasattr(retriever, "_get_relevant_documents"):
+                callback_manager = run_manager.get_child()
+                docs = retriever._get_relevant_documents(query, run_manager=callback_manager)
+            else:
+                docs = retriever.get_relevant_documents(query)
             all_results.extend(docs)
         return all_results
 
-    async def aget_relevant_documents(self, query: str) -> List[Document]:
-        # Async version
+    async def _aget_relevant_documents(
+        self, query: str, *, run_manager: CallbackManagerForRetrieverRun
+    ) -> List[Document]:
+        """
+        Asynchronously get documents relevant to the query.
+        Implements the required async method from BaseRetriever.
+
+        Args:
+            query: Query string
+            run_manager: CallbackManager for the run
+
+        Returns:
+            List of relevant documents
+        """
         all_results = []
         for store in self.stores:
-            async with store as st:
-                retriever = st.as_retriever(
-                    search_type=self.search_type,
-                    search_kwargs=self.search_kwargs,
-                    metric_type=self.metric_type,
-                    chain_type=self.chain_type,
-                )
+            retriever = store.as_retriever(
+                search_type=self.search_type,
+                search_kwargs=self.search_kwargs,
+                chain_type=self.chain_type
+            )
+            # Pass the run_manager to the sub-retrievers if they support it
+            if hasattr(retriever, "_aget_relevant_documents"):
+                callback_manager = run_manager.get_child()
+                docs = await retriever._aget_relevant_documents(query, run_manager=callback_manager)
+            else:
                 docs = await retriever.aget_relevant_documents(query)
-                all_results.extend(docs)
+            all_results.extend(docs)
         return all_results

parrot/stores/abstract.py

@@ -230,11 +230,16 @@ class AbstractStore(ABC):
     def as_retriever(
         self,
         metric_type: str = 'COSINE',
+        index_type: str = 'IVF_FLAT',
         search_type: str = 'similarity',
         chain_type: str = 'stuff',
         search_kwargs: dict = None
     ) -> Callable:
-        vector = self.get_vector(metric_type=metric_type)
+        vector = self.get_vector(metric_type=metric_type, index_type=index_type)
+        if not vector:
+            raise ConfigError(
+                "Vector Store is not connected. Check your connection."
+            )
         return VectorStoreRetriever(
             vectorstore=vector,
             search_type=search_type,

parrot/stores/milvus.py

@@ -251,6 +251,7 @@ class MilvusStore(AbstractStore):
         self,
         collection: Union[str, None] = None,
         metric_type: str = None,
+        index_type: str = None,
         nprobe: int = 32,
         metadata_field: str = None,
         consistency_level: str = 'session'
@@ -261,10 +262,11 @@ class MilvusStore(AbstractStore):
             collection = self.collection_name
         if not metric_type:
             metric_type = self._metric_type or 'COSINE'
+        _idx = index_type or self._index_type
         _search = {
             "search_params": {
                 "metric_type": metric_type,
-                "index_type": self._index_type,
+                "index_type": _idx,
                 "params": {"nprobe": nprobe, "nlist": 1024},
             }
         }

parrot/version.py

@@ -3,7 +3,7 @@
 __title__ = "ai-parrot"
 __description__ = "Live Chatbots based on Langchain chatbots and Agents \
     Integrated into Navigator Framework or used into any aiohttp applications."
-__version__ = "0.5.9"
+__version__ = "0.5.11"
 __author__ = "Jesus Lara"
 __author_email__ = "jesuslarag@gmail.com"
 __license__ = "MIT"