wizit-context-ingestor 0.2.5b2__py3-none-any.whl → 0.3.0b1__py3-none-any.whl

wizit_context_ingestor/workflows/context_nodes.py

@@ -0,0 +1,73 @@
+from ..data.prompts import WORKFLOW_CONTEXT_CHUNKS_IN_DOCUMENT_SYSTEM_PROMPT
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.prompts import MessagesPlaceholder
+from langchain_core.messages import SystemMessage, ToolMessage
+from langgraph.graph import END
+from langgraph.pregel.main import Command
+from .context_state import ContextState
+
+
+class ContextNodes:
+    def __init__(self, llm_model, tools, context_additional_instructions):
+        self.llm_model = llm_model
+        self.tools = tools
+        self.tools_by_name = {tool.name: tool for tool in tools}
+        self.context_additional_instructions = context_additional_instructions
+
+    def gen_context(self, state: ContextState, config):
+        try:
+            messages = state["messages"]
+            document_content = state["document_content"]
+            if not messages:
+                raise ValueError("No messages provided")
+            # parser = PydanticOutputParser(pydantic_object=Transcription)
+            # format_instructions=parser.get_format_instructions(),
+            formatted_context_system_prompt = WORKFLOW_CONTEXT_CHUNKS_IN_DOCUMENT_SYSTEM_PROMPT.format(
+                context_additional_instructions=self.context_additional_instructions,
+                document_content=document_content,
+            )
+
+            prompt = ChatPromptTemplate.from_messages(
+                [
+                    SystemMessage(content=formatted_context_system_prompt),
+                    MessagesPlaceholder("messages"),
+                ]
+            )
+            model_with_structured_output = self.llm_model.bind_tools(self.tools)
+            context_chain = prompt | model_with_structured_output
+            context_result = context_chain.invoke({"messages": messages})
+            return {"messages": [context_result]}
+        except Exception as e:
+            print(f"Error occurred: {e}")
+            raise e
+
+    def return_context(self, state: ContextState, config):
+        latest_message = state["messages"][-1]
+        if type(latest_message) is ToolMessage:
+            return Command(goto=END, update={"context": latest_message.content})
+        else:
+            raise ValueError("Invalid message type to return context")
+
+    def tool_node(self, state: ContextState, config):
+        messages = state["messages"]
+        tool_calls = messages[-1].tool_calls
+        should_end_workflow = False
+        observations = []
+        for tool_call in tool_calls:
+            tool_name = tool_call["name"]
+            tool = self.tools_by_name[tool_name]
+            tool_result = tool.invoke(tool_call["args"])
+            observations.append(
+                ToolMessage(
+                    content=tool_result,
+                    name=tool_call["name"],
+                    tool_call_id=tool_call["id"],
+                )
+            )
+            if tool_call["name"] == "complete_context_gen":
+                should_end_workflow = True
+
+        if should_end_workflow:
+            return Command(goto="return_context", update={"messages": observations})
+        else:
+            return Command(goto="gen_context", update={"messages": observations})

wizit_context_ingestor/workflows/context_state.py

@@ -0,0 +1,10 @@
+from typing_extensions import Annotated, TypedDict, Sequence
+from langchain_core.messages import BaseMessage
+from langgraph.graph.message import add_messages
+
+
+class ContextState(TypedDict):
+    messages: Annotated[Sequence[BaseMessage], add_messages]
+    document_content: str
+    context: str
+    context_relevance: float

wizit_context_ingestor/workflows/context_tools.py

@@ -0,0 +1,58 @@
+from langchain_core.tools import tool
+
+
+@tool(parse_docstring=True)
+def complete_context_gen(context: str) -> str:
+    """Tool to generate comprehensive contextual information for a document chunk.
+
+    This tool creates enriched context by analyzing how a specific chunk relates to and fits
+    within the broader document structure. Use this after you've identified the chunk's role,
+    relationships, and significance within the document.
+
+    When to use:
+    - After analyzing a chunk's position and purpose within the overall document
+    - When you need to establish connections between the chunk and surrounding content
+    - Before finalizing context generation to ensure comprehensive understanding
+    - When preparing detailed contextual information for downstream processing
+
+    Analysis should address:
+    1. Document integration - How does this chunk contribute to the document's main themes and objectives?
+    2. Structural relationships - How does the chunk connect with preceding and following sections?
+    3. Content dependencies - What key concepts, references, or information does this chunk rely on or provide?
+    4. Semantic coherence - How does the chunk maintain consistency with the document's tone and message?
+
+    Args:
+        context: Your detailed analysis and contextual information for the document chunk. must use the same chunk language.
+
+    Returns:
+        The processed contextual information ready for use. must use the same chunk language.
+    """
+    return f"{context}"
+
+
+@tool(parse_docstring=True)
+def think_tool(reflection: str) -> str:
+    """Tool for strategic reflection on research progress and decision-making.
+
+    Use this tool after each search to analyze results and plan next steps systematically.
+    This creates a deliberate pause in the research workflow for quality decision-making.
+
+    When to use:
+    - After receiving search results: What key information did I find?
+    - Before deciding next steps: Do I have enough to answer comprehensively?
+    - When assessing research gaps: What specific information am I still missing?
+    - Before concluding research: Can I provide a complete answer now?
+
+    Reflection should address:
+    1. Analysis of current findings - What concrete information have I gathered?
+    2. Gap assessment - What crucial information is still missing?
+    3. Quality evaluation - Do I have sufficient evidence/examples for a good answer?
+    4. Strategic decision - Should I continue searching or provide my answer?
+
+    Args:
+        reflection: Your detailed reflection on research progress, findings, gaps, and next steps
+
+    Returns:
+        Confirmation that reflection was recorded for decision-making
+    """
+    return f"Reflection recorded: {reflection}"

wizit_context_ingestor/workflows/context_workflow.py

@@ -0,0 +1,42 @@
+from langgraph.graph import StateGraph
+from langgraph.graph import START, END
+from .context_state import ContextState
+from .context_nodes import ContextNodes
+from .context_tools import think_tool, complete_context_gen
+
+
+class ContextWorkflow:
+    __slots__ = (
+        "llm_model",
+        "tools",
+        "context_nodes",
+        "context_additional_instructions",
+    )
+
+    def __init__(self, llm_model, context_additional_instructions):
+        self.llm_model = llm_model
+        self.context_additional_instructions = context_additional_instructions
+        self.tools = [think_tool, complete_context_gen]
+        self.context_nodes = ContextNodes(
+            self.llm_model, self.tools, self.context_additional_instructions
+        )
+
+    def gen_workflow(self):
+        try:
+            workflow = StateGraph(ContextState)
+            workflow.add_node("gen_context", self.context_nodes.gen_context)
+            workflow.add_node("tools", self.context_nodes.tool_node)
+            workflow.add_node("return_context", self.context_nodes.return_context)
+            workflow.add_edge(START, "gen_context")
+            workflow.add_edge("gen_context", "tools")
+            # workflow.add_conditional_edges(
+            #     "gen_context",
+            #     self.context_nodes.should_continue,
+            #     {"tools": "tools", "return_context": "return_context"},
+            # )
+            # workflow.add_edge("tools", "gen_context")
+            workflow.add_edge("return_context", END)
+            return workflow
+        except Exception as e:
+            print(f"Error generating context workflow: {e}")
+            return None

wizit_context_ingestor/workflows/transcription_nodes.py

@@ -0,0 +1,136 @@
+from ..data.prompts import (
+    AGENT_TRANSCRIPTION_SYSTEM_PROMPT,
+    IMAGE_TRANSCRIPTION_CHECK_SYSTEM_PROMPT,
+)
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.prompts import MessagesPlaceholder
+from langchain_core.messages import SystemMessage
+from langgraph.graph import END
+from langgraph.pregel.main import Command
+from .transcription_schemas import Transcription, TranscriptionCheck
+from .transcription_state import TranscriptionState
+
+
+class TranscriptionNodes:
+    __slots__ = ("llm_model", "transcription_additional_instructions")
+
+    def __init__(self, llm_model, transcription_additional_instructions):
+        self.llm_model = llm_model
+        self.transcription_additional_instructions = (
+            transcription_additional_instructions
+        )
+
+    def transcribe(self, state: TranscriptionState, config):
+        try:
+            messages = state["messages"]
+            transcription_notes = ""
+            if "transcription_notes" in state.keys():
+                transcription_notes = state["transcription_notes"]
+            if not messages:
+                raise ValueError("No messages provided")
+            # parser = PydanticOutputParser(pydantic_object=Transcription)
+            # format_instructions=parser.get_format_instructions(),
+            formatted_transcription_system_prompt = AGENT_TRANSCRIPTION_SYSTEM_PROMPT.format(
+                transcription_additional_instructions=self.transcription_additional_instructions,
+                transcription_notes=transcription_notes,
+            )
+
+            prompt = ChatPromptTemplate.from_messages(
+                [
+                    SystemMessage(content=formatted_transcription_system_prompt),
+                    MessagesPlaceholder("messages"),
+                ]
+            )
+            model_with_structured_output = self.llm_model.with_structured_output(
+                Transcription
+            )
+            transcription_chain = prompt | model_with_structured_output
+            transcription_result = transcription_chain.invoke({"messages": messages})
+            return Command(
+                goto="check_transcription",
+                update={
+                    "transcription": transcription_result.transcription,
+                    "transcription_status": "in_progress",
+                },
+            )
+        except Exception as e:
+            print(f"Error occurred: {e}")
+            return Command(goto=END)
+
+    def check_transcription(self, state, config):
+        try:
+            transcription = state["transcription"]
+            messages = state["messages"]
+            print("last message, ", messages[-1])
+            if not transcription:
+                raise ValueError("No transcription provided")
+            # parser = PydanticOutputParser(pydantic_object=TranscriptionCheck)
+
+            formatted_image_transcription_check_system_prompt = IMAGE_TRANSCRIPTION_CHECK_SYSTEM_PROMPT.format(
+                transcription_additional_instructions=self.transcription_additional_instructions,
+                transcription=transcription,
+            )
+            prompt = ChatPromptTemplate.from_messages(
+                [
+                    SystemMessage(
+                        content=formatted_image_transcription_check_system_prompt
+                    ),
+                    MessagesPlaceholder("messages"),
+                ]
+            )
+            model_with_structured_output = self.llm_model.with_structured_output(
+                TranscriptionCheck
+            )
+            transcription_check_chain = prompt | model_with_structured_output
+            transcription_check_result = transcription_check_chain.invoke(
+                {"transcription": transcription, "messages": messages}
+            )
+            return Command(
+                goto="validate_transcription_results",
+                update={
+                    "transcription_accuracy": transcription_check_result.transcription_accuracy,
+                    "transcription_notes": transcription_check_result.transcription_notes,
+                },
+            )
+        except Exception as e:
+            print(f"Error occurred: {e}")
+            return Command(goto=END, update={"transcription_accuracy": 0.0})
+
+    def validate_transcription_results(self, state, config):
+        try:
+            if "transcription_accuracy" not in state:
+                raise ValueError("Missing 'transcription_accuracy' in state")
+
+            if "transcription_retries" not in state:
+                transcription_retries = 0
+            else:
+                transcription_retries = state["transcription_retries"]
+
+            transcription_accuracy = state["transcription_accuracy"]
+
+            max_transcription_retries = config["configurable"][
+                "max_transcription_retries"
+            ]
+            transcription_accuracy_threshold = config["configurable"][
+                "transcription_accuracy_threshold"
+            ]
+
+            if transcription_accuracy < transcription_accuracy_threshold:
+                if transcription_retries < max_transcription_retries:
+                    # retry transcription
+                    return Command(
+                        goto="transcribe",
+                        update={
+                            "transcription_retries": transcription_retries + 1,
+                            "transcription_accuracy": 0.0,
+                            "transcription_status": "failed",
+                        },
+                    )
+                else:
+                    return Command(goto=END, update={"transcription_status": "failed"})
+            else:
+                # success
+                return Command(goto=END, update={"transcription_status": "completed"})
+        except Exception as e:
+            print(f"Error occurred: {e}")
+            return Command(goto=END, update={"transcription_status": "failed"})

wizit_context_ingestor/workflows/transcription_schemas.py

@@ -0,0 +1,25 @@
+from pydantic import BaseModel, Field
+
+
+class Transcription(BaseModel):
+    """Schema for transcription."""
+
+    transcription: str = Field(
+        description="document page transcription",
+    )
+
+
+class TranscriptionCheck(BaseModel):
+    """Schema for transcription check."""
+
+    is_correct_transcription: bool = Field(
+        description="is a correct transcription",
+    )
+
+    transcription_accuracy: float = Field(
+        description="transcription accuracy from 0.0 to 1.0",
+    )
+
+    transcription_notes: str = Field(
+        description="why is a correct transcription or not, why transcription accuracy is not 100%",
+    )

wizit_context_ingestor/workflows/transcription_state.py

@@ -0,0 +1,17 @@
+from typing import Literal
+from typing_extensions import Annotated, TypedDict, Sequence
+from langchain_core.messages import BaseMessage
+from langgraph.graph.message import add_messages
+
+
+class TranscriptionInputState(TypedDict):
+    messages: Annotated[Sequence[BaseMessage], add_messages]
+
+
+class TranscriptionState(TypedDict):
+    messages: Annotated[Sequence[BaseMessage], add_messages]
+    transcription: str
+    transcription_retries: int
+    transcription_notes: str
+    transcription_status: Literal["pending", "in_progress", "completed", "failed"]
+    transcription_accuracy: float

wizit_context_ingestor/workflows/transcription_tools.py

@@ -0,0 +1,54 @@
+from langchain_core.tools import tool, InjectedToolArg
+from typing import Annotated
+
+
+@tool(parse_docstring=True)
+def transcribe_page(image_base_64: Annotated[str, InjectedToolArg]) -> str:
+    """Transcribe a document using the provided text.
+
+    Args:
+        image_base_64: Base64 encoded image string containing the document to transcribe.
+
+    Returns:
+        The transcribed text content from the document.
+    """
+
+
+@tool(parse_docstring=True)
+def correct_transcription(
+    transcription: str, image_base_64: Annotated[str, InjectedToolArg]
+) -> [str, bool]:
+    """Correct a transcription using the provided text.
+
+    Args:
+        transcription: The transcribed content.
+        image_base_64: Base64 encoded image string containing the document to transcribe.
+
+    Returns:
+       The corrected transcription.
+       The transcription has been executed successfully.
+    """
+
+
+@tool(parse_docstring=True)
+def think_tool(reasoning: str) -> str:
+    """Reason about the current task and next steps.
+    Args:
+        reasoning: The reasoning content.
+
+    Returns:
+       The reasoning content.
+    """
+    pass
+
+
+@tool(parse_docstring=True)
+def finish(transcription: str) -> str:
+    """Execute a transcription using the provided text.
+    Args:
+        transcription: The transcribed content.
+
+    Returns:
+       The executed transcription.
+    """
+    pass

wizit_context_ingestor/workflows/transcription_workflow.py

@@ -0,0 +1,42 @@
+from langgraph.graph import StateGraph
+from langgraph.graph import START, END
+from .transcription_state import TranscriptionState, TranscriptionInputState
+from .transcription_nodes import TranscriptionNodes
+# from .transcription_tools import transcribe_page, correct_transcription
+
+
+class TranscriptionWorkflow:
+    __slots__ = (
+        "llm_model",
+        "transcription_nodes",
+        "transcription_additional_instructions",
+    )
+
+    def __init__(self, llm_model, transcription_additional_instructions):
+        self.llm_model = llm_model
+        self.transcription_additional_instructions = (
+            transcription_additional_instructions
+        )
+        self.transcription_nodes = TranscriptionNodes(
+            self.llm_model, self.transcription_additional_instructions
+        )
+
+    def gen_workflow(self):
+        try:
+            workflow = StateGraph(
+                TranscriptionState, input_schema=TranscriptionInputState
+            )
+            workflow.add_node("transcribe", self.transcription_nodes.transcribe)
+            workflow.add_node(
+                "check_transcription", self.transcription_nodes.check_transcription
+            )
+            workflow.add_node(
+                "validate_transcription_results",
+                self.transcription_nodes.validate_transcription_results,
+            )
+            workflow.add_edge(START, "transcribe")
+            # workflow.add_edge("transcribe", "validate_transcription_results")
+            return workflow
+        except Exception as e:
+            print(f"Error generating transcription workflow: {e}")
+            return None

{wizit_context_ingestor-0.2.5b2.dist-info → wizit_context_ingestor-0.3.0b1.dist-info}/METADATA

@@ -1,13 +1,15 @@
 Metadata-Version: 2.3
 Name: wizit-context-ingestor
-Version: 0.2.5b2
+Version: 0.3.0b1
 Summary: Contextual Rag with Cloud Solutions
 Requires-Dist: anthropic[vertex]>=0.66.0
 Requires-Dist: boto3>=1.40.23
 Requires-Dist: langchain-aws>=0.2.31
+Requires-Dist: langchain-chroma>=0.2.6
 Requires-Dist: langchain-experimental>=0.3.4
 Requires-Dist: langchain-google-vertexai>=2.0.28
 Requires-Dist: langchain-redis>=0.2.3
+Requires-Dist: langgraph>=0.6.8
 Requires-Dist: pillow>=11.3.0
 Requires-Dist: pymupdf>=1.26.4
 Requires-Python: >=3.12
@@ -137,6 +139,13 @@ Finally
     poetry publish -r tbbcmegaingestor
 ```
 
+# USAGE
+
+## For transcriptions
+
+----- TODO ---
+You can provide number of retries and a transcription quality threshold
+
 ## License
 
 This project is licensed under the Apache License - see the LICENSE file for details.

wizit_context_ingestor-0.3.0b1.dist-info/RECORD

@@ -0,0 +1,44 @@
+wizit_context_ingestor/.DS_Store,sha256=c7hZ0C8v2hxprMlCgmvxXDl92phew3iSATJzE1yYTBs,6148
+wizit_context_ingestor/__init__.py,sha256=TSTm5qSpNNCz9ilKYkXRUxupvmWG2AHfv7RBWFw8T4c,107
+wizit_context_ingestor/application/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+wizit_context_ingestor/application/context_chunk_service.py,sha256=zKdnjNr5woi4PHseLEAcfdTNRvOroAkU_52pwLZLmBc,8858
+wizit_context_ingestor/application/interfaces.py,sha256=W0qonE3t-S-zwAoKtDYc4oyW_GOILKVmrdy8LnC8MVI,3193
+wizit_context_ingestor/application/transcription_service.py,sha256=4Z_STIRgExY5VnVWbyZ_oSnx_bgSfjfPA2N7tCYb5bg,7334
+wizit_context_ingestor/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+wizit_context_ingestor/data/kdb.py,sha256=GCkXQmnk2JCXV_VJ-h0k55AOIX8qohzBJN2v-9D1dlU,194
+wizit_context_ingestor/data/prompts.py,sha256=EnocoriDjPcFPd6Af9G6TUTB8NkO4EFN4AUHfpRVqYU,14406
+wizit_context_ingestor/data/storage.py,sha256=aanXY1AV696cShHtDDhlJDhKPouZ1dq2lo_57yhTd20,198
+wizit_context_ingestor/domain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+wizit_context_ingestor/domain/models.py,sha256=DV83PArMyh-VoUqnVF_ohcgStsk549ixdYw98B8o2GI,381
+wizit_context_ingestor/domain/services.py,sha256=0i9WwZ0ufBgnzNJ5dt8Iop9VLTeK_AqjcaH8p3Av26I,3347
+wizit_context_ingestor/infra/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+wizit_context_ingestor/infra/aws_model.py,sha256=glIaewSdv6PDBXoCe6QgCUIzLCjtM7KlayEERXRNFwo,2539
+wizit_context_ingestor/infra/persistence/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+wizit_context_ingestor/infra/persistence/local_storage.py,sha256=GtPUvtn8XlgcqwjWmSm2998sgyYlwkF22HoB40ri7c0,2029
+wizit_context_ingestor/infra/persistence/s3_storage.py,sha256=bzlQteLPPGS_Gbh39RkxyoK8G-CEOQewMNPuzPule9k,4906
+wizit_context_ingestor/infra/rag/chroma_embeddings.py,sha256=06calGiIGGtqvGgqfP9D1ANuhXPe_v_BGevLqGDRgFw,4426
+wizit_context_ingestor/infra/rag/pg_embeddings.py,sha256=D7onh27SvqYahYAsLy6DeyklxGyBFYH2DwV42fVCalQ,8157
+wizit_context_ingestor/infra/rag/redis_embeddings.py,sha256=pCP_I1RLeIUTYMSHkZT6AjIOyHA9A47wyffrZBjiG0s,5107
+wizit_context_ingestor/infra/rag/semantic_chunks.py,sha256=Xes1MwlShKbqVulspXzfb6zJuqd8iBX3nKuy-5BtSfk,2473
+wizit_context_ingestor/infra/secrets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+wizit_context_ingestor/infra/secrets/aws_secrets_manager.py,sha256=1k_R_uzLabptiZ1GXAoqAgYpk8EykXIb-pUDdidUDJQ,1202
+wizit_context_ingestor/infra/vertex_model.py,sha256=6L2C4qH7PSVjdOSzIEZlFtUwu1pgQVXtQBIU5isn644,7582
+wizit_context_ingestor/main.py,sha256=bUdlAnxJzuDpO6GSaSMDXC47HvpfJHlwh2e-V7NkyiA,10407
+wizit_context_ingestor/services/.DS_Store,sha256=1lFlJ5EFymdzGAUAaI30vcaaLHt3F1LwpG7xILf9jsM,6148
+wizit_context_ingestor/services/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+wizit_context_ingestor/services/chunks.py,sha256=tQQsdsOscZWzqVY5WxVxr3ii62FOJ3nMARaJJz6CvjQ,2011
+wizit_context_ingestor/services/parse_doc.py,sha256=3CyZoGbiUfxbs0SXUWXjQevtusSzTBgvUVeNNSdxJLE,4491
+wizit_context_ingestor/services/pg_embeddings_manager.py,sha256=n1HOmu_Z_Z71H-rVAyJS3FdPKbBckm5W8_XethY8nuM,4998
+wizit_context_ingestor/utils/file_utils.py,sha256=QnyncN0X5E-LjAYxFPxQiOrAj0DHcAcL2GliLVikF5o,393
+wizit_context_ingestor/workflows/context_nodes.py,sha256=3qlFcxPUmehx04mQHpmouneKq--To8rwSDHCRFyWICo,3168
+wizit_context_ingestor/workflows/context_state.py,sha256=4MTIUjK-F2pWvIldovWZhMAqqCOpViKbvitJzETkSkY,324
+wizit_context_ingestor/workflows/context_tools.py,sha256=E9VTL3AC0MwSIuc1e-juZK7XCxnZfFv0-KpHfR2CNH4,2764
+wizit_context_ingestor/workflows/context_workflow.py,sha256=n1kQkiZB3F4YYP-9GzBK4Ad-8A0-J47zOHpTwAbqUzo,1643
+wizit_context_ingestor/workflows/transcription_nodes.py,sha256=PiNRBqekQXsSQ6D76IS5l0WOW9d0FUxOnZ7HueC-z50,5918
+wizit_context_ingestor/workflows/transcription_schemas.py,sha256=CQCl7LXD5voxhJOhmfihgav9K_3Liz3BKSFFqKXgDIU,638
+wizit_context_ingestor/workflows/transcription_state.py,sha256=2Z_t2aZFEH_nAjdEO6RFBEmi_fwvr9cV0aLS1eIxiCQ,590
+wizit_context_ingestor/workflows/transcription_tools.py,sha256=FtIfWFITn8_Rr5SEobCeR55aJGZoHRMgF2UxRT5vJ-E,1373
+wizit_context_ingestor/workflows/transcription_workflow.py,sha256=77cLsYGdv01Py2GaKYpACuifPeSxH7tkVodvLv97sdg,1621
+wizit_context_ingestor-0.3.0b1.dist-info/WHEEL,sha256=eh7sammvW2TypMMMGKgsM83HyA_3qQ5Lgg3ynoecH3M,79
+wizit_context_ingestor-0.3.0b1.dist-info/METADATA,sha256=GvUF4xODBm2jCQIaPglDxxF_ccwdzd7ht3Qup2TVj88,3768
+wizit_context_ingestor-0.3.0b1.dist-info/RECORD,,

{wizit_context_ingestor-0.2.5b2.dist-info → wizit_context_ingestor-0.3.0b1.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: uv 0.8.16
+Generator: uv 0.8.24
 Root-Is-Purelib: true
 Tag: py3-none-any

wizit_context_ingestor-0.2.5b2.dist-info/RECORD

@@ -1,31 +0,0 @@
-wizit_context_ingestor/.DS_Store,sha256=c7hZ0C8v2hxprMlCgmvxXDl92phew3iSATJzE1yYTBs,6148
-wizit_context_ingestor/__init__.py,sha256=GQdqSrpsSS7mdbfIn-Osse4EI54PvqlDYeBZwCuuNNA,134
-wizit_context_ingestor/application/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wizit_context_ingestor/application/context_chunk_service.py,sha256=0nnn6vbxnLovoriu0f7EIqiAJA713Pd8L95QNK6fjnM,4916
-wizit_context_ingestor/application/interfaces.py,sha256=qz6XcA9K5THl7dBMyfOtqEuNV2hC6BwGEiULFaamDqc,3193
-wizit_context_ingestor/application/transcription_service.py,sha256=GnUoIP6gEAm3MZ1JgX0yIzcaZAARUsZYKLbfUkmC79A,4073
-wizit_context_ingestor/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wizit_context_ingestor/data/prompts.py,sha256=wK4HjgbxMOMo0qKeqYs4ujJ0jZ1oDJ6Jw8kujByDdlY,6721
-wizit_context_ingestor/domain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wizit_context_ingestor/domain/models.py,sha256=DV83PArMyh-VoUqnVF_ohcgStsk549ixdYw98B8o2GI,381
-wizit_context_ingestor/domain/services.py,sha256=0i9WwZ0ufBgnzNJ5dt8Iop9VLTeK_AqjcaH8p3Av26I,3347
-wizit_context_ingestor/infra/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wizit_context_ingestor/infra/aws_model.py,sha256=glIaewSdv6PDBXoCe6QgCUIzLCjtM7KlayEERXRNFwo,2539
-wizit_context_ingestor/infra/persistence/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wizit_context_ingestor/infra/persistence/local_storage.py,sha256=sDFat-FMN123FUWZp_ztwoVjl0HrzChCDZmicFemy5o,1707
-wizit_context_ingestor/infra/persistence/s3_storage.py,sha256=HYO3gWNE64ECSYYrxrIi9-2jWv1vwwGEE5QX-ZqpOCs,4791
-wizit_context_ingestor/infra/rag/pg_embeddings.py,sha256=5m4R4GmwMU3C7AR3Je3nCdgO-2jyIaCG4QN9phGD68Q,8072
-wizit_context_ingestor/infra/rag/redis_embeddings.py,sha256=wlgSBedq_kcrZ3SF4vGVTWM0B350kkd8C894i4mMUA8,4828
-wizit_context_ingestor/infra/rag/semantic_chunks.py,sha256=tM6bSacBvu-VWb3VkxgQNrfskz3zFxOOAU23D2kZWD8,2255
-wizit_context_ingestor/infra/secrets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wizit_context_ingestor/infra/secrets/aws_secrets_manager.py,sha256=1k_R_uzLabptiZ1GXAoqAgYpk8EykXIb-pUDdidUDJQ,1202
-wizit_context_ingestor/infra/vertex_model.py,sha256=Izpz2ZQ4Koh4PSrHAj_0iUv4Rx354SlUqqw-LrLXCOE,7256
-wizit_context_ingestor/main.py,sha256=x1bieggNs3uzLkNHXZk4fBz0fYlOyff1TGvjV3Af2yM,7966
-wizit_context_ingestor/services/.DS_Store,sha256=1lFlJ5EFymdzGAUAaI30vcaaLHt3F1LwpG7xILf9jsM,6148
-wizit_context_ingestor/services/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wizit_context_ingestor/services/chunks.py,sha256=tQQsdsOscZWzqVY5WxVxr3ii62FOJ3nMARaJJz6CvjQ,2011
-wizit_context_ingestor/services/parse_doc.py,sha256=3CyZoGbiUfxbs0SXUWXjQevtusSzTBgvUVeNNSdxJLE,4491
-wizit_context_ingestor/services/pg_embeddings_manager.py,sha256=n1HOmu_Z_Z71H-rVAyJS3FdPKbBckm5W8_XethY8nuM,4998
-wizit_context_ingestor-0.2.5b2.dist-info/WHEEL,sha256=F3mArEuDT3LDFEqo9fCiUx6ISLN64aIhcGSiIwtu4r8,79
-wizit_context_ingestor-0.2.5b2.dist-info/METADATA,sha256=AaF5SD1HqVjrW0Px_xjhioJryJXPUh9Q9SO4QJtRbwo,3577
-wizit_context_ingestor-0.2.5b2.dist-info/RECORD,,