feat: new summary using phi-4 and llama-index (#519)

* feat: add litellm backend implementation

* refactor: improve generate/completion methods for base LLM

* refactor: remove tokenizer logic

* style: apply code formatting

* fix: remove hallucinations from LLM responses

* refactor: comprehensive LLM and summarization rework

* chore: remove debug code

* feat: add structured output support to LiteLLM

* refactor: apply self-review improvements

* docs: add model structured output comments

* docs: update model structured output comments

* style: apply linting and formatting fixes

* fix: resolve type logic bug

* refactor: apply PR review feedback

* refactor: apply additional PR review feedback

* refactor: apply final PR review feedback

* fix: improve schema passing for LLMs without structured output

* feat: add PR comments and logger improvements

* docs: update README and add HTTP logging

* feat: improve HTTP logging

* feat: add summary chunking functionality

* fix: resolve title generation runtime issues

* refactor: apply self-review improvements

* style: apply linting and formatting

* feat: implement LiteLLM class structure

* style: apply linting and formatting fixes

* docs: env template model name fix

* chore: remove older litellm class

* chore: format

* refactor: simplify OpenAILLM

* refactor: OpenAILLM tokenizer

* refactor: self-review

* refactor: self-review

* refactor: self-review

* chore: format

* chore: remove LLM_USE_STRUCTURED_OUTPUT from envs

* chore: roll back migration lint changes

* chore: roll back migration lint changes

* fix: make summary llm configuration optional for the tests

* fix: missing f-string

* fix: tweak the prompt for summary title

* feat: try llamaindex for summarization

* fix: complete refactor of summary builder using llamaindex and structured output when possible

* fix: separate prompt as constant

* fix: typings

* fix: enhance prompt to prevent mentioning others subject while summarize one

* fix: various changes after self-review

* fix: from igor review

---------

Co-authored-by: Igor Loskutov <igor.loskutoff@gmail.com>

CLAUDE.md

@@ -172,3 +172,7 @@ Modal.com integration for scalable ML processing:
 - **Audio Routing**: Use BlackHole (Mac) for merging multiple audio sources
 - **WebRTC**: Ensure proper CORS configuration for cross-origin streaming
 - **Database**: Run `uv run alembic upgrade head` after pulling schema changes
+
+## Pipeline/worker related info
+
+If you need to do any worker/pipeline related work, search for "Pipeline" classes and their "create" or "build" methods to find the main processor sequence. Look for task orchestration patterns (like "chord", "group", or "chain") to identify the post-processing flow with parallel execution chains. This will give you abstract vision on how processing pipeling is organized.

README.md

@@ -4,8 +4,8 @@
 
 Reflector Audio Management and Analysis is a cutting-edge web application under development by Monadical. It utilizes AI to record meetings, providing a permanent record with transcripts, translations, and automated summaries.
 
-[![Tests](https://github.com/monadical-sas/cubbi/actions/workflows/pytests.yml/badge.svg?branch=main&event=push)](https://github.com/monadical-sas/cubbi/actions/workflows/pytests.yml)
+[![Tests](https://github.com/monadical-sas/reflector/actions/workflows/pytests.yml/badge.svg?branch=main&event=push)](https://github.com/monadical-sas/reflector/actions/workflows/pytests.yml)
-[![License: MIT](https://img.shields.io/badge/license-AGPL--v3-green.svg)](https://opensource.org/licenses/AGPL-v3)
+[![License: MIT](https://img.shields.io/badge/license-MIT-green.svg)](https://opensource.org/licenses/MIT)
 </div>
 
 ## Screenshots
@@ -74,7 +74,7 @@ Note: We currently do not have instructions for Windows users.
 
 ### Frontend
 
-Start with `cd backend`.
+Start with `cd www`.
 
 **Installation**
 

server/.env_template

@@ -14,3 +14,8 @@ BASE_URL=https://xxxxx.ngrok.app
 DIARIZATION_ENABLED=false
 
 SQS_POLLING_TIMEOUT_SECONDS=60
+
+# Summary LLM configuration
+SUMMARY_MODEL=monadical/private/smart
+SUMMARY_LLM_URL=
+SUMMARY_LLM_API_KEY=

server/README.md

@@ -20,3 +20,23 @@ Polls SQS every 60 seconds via /server/reflector/worker/process.py:24-62:
 # Every 60 seconds, check for new recordings
 sqs = boto3.client("sqs", ...)
 response = sqs.receive_message(QueueUrl=queue_url, ...)
+
+# Requeue
+
+```bash
+uv run /app/requeue_uploaded_file.py TRANSCRIPT_ID
+```
+
+## Pipeline Management
+
+### Continue stuck pipeline from final summaries (identify_participants) step:
+
+```bash
+uv run python -c "from reflector.pipelines.main_live_pipeline import task_pipeline_final_summaries; result = task_pipeline_final_summaries.delay(transcript_id='TRANSCRIPT_ID'); print(f'Task queued: {result.id}')"
+```
+
+### Run full post-processing pipeline (continues to completion):
+
+```bash
+uv run python -c "from reflector.pipelines.main_live_pipeline import pipeline_post; pipeline_post(transcript_id='TRANSCRIPT_ID')"
+```

server/env.example

@@ -70,6 +70,16 @@ ZEPHYR_LLM_URL=https://monadical-sas--reflector-llm-zephyr-web.modal.run
 ## Cache directory to store models
 CACHE_DIR=data
 
+## =======================================================
+## Summary LLM configuration
+## =======================================================
+
+## Context size for summary generation (tokens)
+SUMMARY_LLM_CONTEXT_SIZE_TOKENS=16000
+SUMMARY_LLM_URL=
+SUMMARY_LLM_API_KEY=sk-
+SUMMARY_MODEL=
+
 ## =======================================================
 ## Diarization
 ##

server/gpu/modal_deployments/reflector_llm.py

@@ -9,7 +9,6 @@ import os
 import threading
 from typing import Optional
 
-import modal
 from modal import App, Image, Secret, asgi_app, enter, exit, method
 
 # LLM

server/gpu/modal_deployments/reflector_llm_zephyr.py

@@ -9,7 +9,6 @@ import os
 import threading
 from typing import Optional
 
-import modal
 from modal import App, Image, Secret, asgi_app, enter, exit, method
 
 # LLM

server/pyproject.toml

@@ -38,6 +38,8 @@ dependencies = [
     "jsonschema>=4.23.0",
     "openai>=1.59.7",
     "psycopg2-binary>=2.9.10",
+    "llama-index>=0.12.52",
+    "llama-index-llms-openai-like>=0.4.0",
 ]
 
 [dependency-groups]

server/reflector/client.py

@@ -51,7 +51,7 @@ async def main() -> NoReturn:
 
         logger.info(f"Cancelling {len(tasks)} outstanding tasks")
         await asyncio.gather(*tasks, return_exceptions=True)
-        logger.info(f'{"Flushing metrics"}')
+        logger.info(f"{'Flushing metrics'}")
         loop.stop()
 
     signals = (signal.SIGHUP, signal.SIGTERM, signal.SIGINT)

server/reflector/llm/base.py

@@ -17,6 +17,7 @@ T = TypeVar("T", bound="LLM")
 class LLM:
     _nltk_downloaded = False
     _registry = {}
+    model_name: str
     m_generate = Histogram(
         "llm_generate",
         "Time spent in LLM.generate",
@@ -69,6 +70,7 @@ class LLM:
             module_name = f"reflector.llm.llm_{name}"
             importlib.import_module(module_name)
         cls.ensure_nltk()
+
         return cls._registry[name](model_name)
 
     def get_model_name(self) -> str:
@@ -121,6 +123,11 @@ class LLM:
     def _get_tokenizer(self):
         pass
 
+    def has_structured_output(self):
+        # whether implementation supports structured output
+        # on the model side (otherwise it's prompt engineering)
+        return False
+
     async def generate(
         self,
         prompt: str,
@@ -140,6 +147,7 @@ class LLM:
                     prompt=prompt,
                     gen_schema=gen_schema,
                     gen_cfg=gen_cfg,
+                    logger=logger,
                     **kwargs,
                 )
             self.m_generate_success.inc()
@@ -167,7 +175,9 @@ class LLM:
 
         try:
             with self.m_generate.time():
-                result = await retry(self._completion)(messages=messages, **kwargs)
+                result = await retry(self._completion)(
+                    messages=messages, **{**kwargs, "logger": logger}
+                )
             self.m_generate_success.inc()
         except Exception:
             logger.exception("Failed to call llm after retrying")
@@ -253,9 +263,7 @@ class LLM:
     ) -> str:
         raise NotImplementedError
 
-    async def _completion(
+    async def _completion(self, messages: list, **kwargs) -> dict:
-        self, messages: list, logger: reflector_logger, **kwargs
-    ) -> dict:
         raise NotImplementedError
 
     def _parse_json(self, result: str) -> dict:

server/reflector/llm/llm_modal.py

@@ -31,7 +31,7 @@ class ModalLLM(LLM):
 
     async def _generate(
         self, prompt: str, gen_schema: dict | None, gen_cfg: dict | None, **kwargs
-    ):
+    ) -> str:
         json_payload = {"prompt": prompt}
         if gen_schema:
             json_payload["gen_schema"] = gen_schema
@@ -52,12 +52,14 @@ class ModalLLM(LLM):
                 timeout=self.timeout,
                 retry_timeout=60 * 5,
                 follow_redirects=True,
+                logger=kwargs.get("logger", reflector_logger),
             )
             response.raise_for_status()
             text = response.json()["text"]
             return text
 
     async def _completion(self, messages: list, **kwargs) -> dict:
+        # returns full api response
         kwargs.setdefault("temperature", 0.3)
         kwargs.setdefault("max_tokens", 2048)
         kwargs.setdefault("stream", False)
@@ -78,6 +80,7 @@ class ModalLLM(LLM):
                 timeout=self.timeout,
                 retry_timeout=60 * 5,
                 follow_redirects=True,
+                logger=kwargs.get("logger", reflector_logger),
             )
             response.raise_for_status()
             return response.json()

server/reflector/llm/openai_llm.py

@@ -0,0 +1,117 @@
+import httpx
+from transformers import AutoTokenizer
+from reflector.logger import logger
+
+
+def apply_gen_config(payload: dict, gen_cfg) -> None:
+    """Apply generation config overrides to the payload."""
+    config_mapping = {
+        "temperature": "temperature",
+        "max_new_tokens": "max_tokens",
+        "max_tokens": "max_tokens",
+        "top_p": "top_p",
+        "frequency_penalty": "frequency_penalty",
+        "presence_penalty": "presence_penalty",
+    }
+
+    for cfg_attr, payload_key in config_mapping.items():
+        value = getattr(gen_cfg, cfg_attr, None)
+        if value is not None:
+            payload[payload_key] = value
+            if cfg_attr == "max_new_tokens":  # Handle max_new_tokens taking precedence
+                break
+
+
+class OpenAILLM:
+    def __init__(self, config_prefix: str, settings):
+        self.config_prefix = config_prefix
+        self.settings_obj = settings
+        self.model_name = getattr(settings, f"{config_prefix}_MODEL")
+        self.url = getattr(settings, f"{config_prefix}_LLM_URL")
+        self.api_key = getattr(settings, f"{config_prefix}_LLM_API_KEY")
+
+        timeout = getattr(settings, f"{config_prefix}_LLM_TIMEOUT", 300)
+        self.temperature = getattr(settings, f"{config_prefix}_LLM_TEMPERATURE", 0.7)
+        self.max_tokens = getattr(settings, f"{config_prefix}_LLM_MAX_TOKENS", 1024)
+        self.client = httpx.AsyncClient(timeout=timeout)
+
+        # Use a tokenizer that approximates OpenAI token counting
+        tokenizer_name = getattr(settings, f"{config_prefix}_TOKENIZER", "gpt2")
+        try:
+            self.tokenizer = AutoTokenizer.from_pretrained(tokenizer_name)
+        except Exception:
+            logger.debug(
+                f"Failed to load tokenizer '{tokenizer_name}', falling back to default 'gpt2' tokenizer"
+            )
+            self.tokenizer = AutoTokenizer.from_pretrained("gpt2")
+
+    async def generate(
+        self, prompt: str, gen_schema=None, gen_cfg=None, logger=None
+    ) -> str:
+        if logger:
+            logger.debug(
+                "OpenAI LLM generate",
+                prompt=repr(prompt[:100] + "..." if len(prompt) > 100 else prompt),
+            )
+
+        messages = [{"role": "user", "content": prompt}]
+        result = await self.completion(
+            messages, gen_schema=gen_schema, gen_cfg=gen_cfg, logger=logger
+        )
+        return result["choices"][0]["message"]["content"]
+
+    async def completion(
+        self, messages: list, gen_schema=None, gen_cfg=None, logger=None, **kwargs
+    ) -> dict:
+        if logger:
+            logger.info("OpenAI LLM completion", messages_count=len(messages))
+
+        payload = {
+            "model": self.model_name,
+            "messages": messages,
+            "temperature": self.temperature,
+            "max_tokens": self.max_tokens,
+        }
+
+        # Apply generation config overrides
+        if gen_cfg:
+            apply_gen_config(payload, gen_cfg)
+
+        # Apply structured output schema
+        if gen_schema:
+            payload["response_format"] = {
+                "type": "json_schema",
+                "json_schema": {"name": "response", "schema": gen_schema},
+            }
+
+        headers = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {self.api_key}",
+        }
+
+        url = f"{self.url.rstrip('/')}/chat/completions"
+
+        if logger:
+            logger.debug(
+                "OpenAI API request", url=url, payload_keys=list(payload.keys())
+            )
+
+        response = await self.client.post(url, json=payload, headers=headers)
+        response.raise_for_status()
+
+        result = response.json()
+
+        if logger:
+            logger.debug(
+                "OpenAI API response",
+                status_code=response.status_code,
+                choices_count=len(result.get("choices", [])),
+            )
+
+        return result
+
+    async def __aenter__(self):
+        return self
+
+    async def __aexit__(self, exc_type, exc_val, exc_tb):
+        await self.client.aclose()

server/reflector/pipelines/main_live_pipeline.py

@@ -16,7 +16,7 @@ import functools
 from contextlib import asynccontextmanager
 
 import boto3
-from celery import chord, group, shared_task
+from celery import chord, group, shared_task, current_task
 from pydantic import BaseModel
 from reflector.db.meetings import meeting_consent_controller, meetings_controller
 from reflector.db.recordings import recordings_controller
@@ -111,16 +111,29 @@ def get_transcript(func):
     Decorator to fetch the transcript from the database from the first argument
     """
 
+    @functools.wraps(func)
     async def wrapper(**kwargs):
         transcript_id = kwargs.pop("transcript_id")
         transcript = await transcripts_controller.get_by_id(transcript_id=transcript_id)
         if not transcript:
             raise Exception("Transcript {transcript_id} not found")
+
+        # Enhanced logger with Celery task context
         tlogger = logger.bind(transcript_id=transcript.id)
+        if current_task:
+            tlogger = tlogger.bind(
+                task_id=current_task.request.id,
+                task_name=current_task.name,
+                worker_hostname=current_task.request.hostname,
+                task_retries=current_task.request.retries,
+                transcript_id=transcript_id,
+            )
+
         try:
-            return await func(transcript=transcript, logger=tlogger, **kwargs)
+            result = await func(transcript=transcript, logger=tlogger, **kwargs)
+            return result
         except Exception as exc:
-            tlogger.error("Pipeline error", exc_info=exc)
+            tlogger.error("Pipeline error", function_name=func.__name__, exc_info=exc)
             raise
 
     return wrapper

server/reflector/processors/transcript_final_summary.py

@@ -1,7 +1,8 @@
-from reflector.llm import LLM
+from reflector.llm.openai_llm import OpenAILLM
 from reflector.processors.base import Processor
 from reflector.processors.summary.summary_builder import SummaryBuilder
 from reflector.processors.types import FinalLongSummary, FinalShortSummary, TitleSummary
+from reflector.settings import settings
 
 
 class TranscriptFinalSummaryProcessor(Processor):
@@ -16,14 +17,14 @@ class TranscriptFinalSummaryProcessor(Processor):
         super().__init__(**kwargs)
         self.transcript = transcript
         self.chunks: list[TitleSummary] = []
-        self.llm = LLM.get_instance(model_name="NousResearch/Hermes-3-Llama-3.1-8B")
+        self.llm = OpenAILLM(config_prefix="SUMMARY", settings=settings)
         self.builder = None
 
     async def _push(self, data: TitleSummary):
         self.chunks.append(data)
 
     async def get_summary_builder(self, text) -> SummaryBuilder:
-        builder = SummaryBuilder(self.llm)
+        builder = SummaryBuilder(self.llm, logger=self.logger)
         builder.set_transcript(text)
         await builder.identify_participants()
         await builder.generate_summary()

server/reflector/processors/transcript_final_title.py

@@ -49,7 +49,7 @@ class TranscriptFinalTitleProcessor(Processor):
                     gen_cfg=self.params.gen_cfg,
                     logger=self.logger,
                 )
-                accumulated_titles += title_result["summary"]
+                accumulated_titles += title_result["title"]
 
             return await self.get_title(accumulated_titles)
 

server/reflector/processors/transcript_translator.py

@@ -52,6 +52,7 @@ class TranscriptTranslatorProcessor(Processor):
                 params=json_payload,
                 timeout=self.timeout,
                 follow_redirects=True,
+                logger=self.logger,
             )
             response.raise_for_status()
             result = response.json()["text"]

server/reflector/settings.py

@@ -82,6 +82,12 @@ class Settings(BaseSettings):
     # LLM Modal configuration
     LLM_MODAL_API_KEY: str | None = None
 
+    # per-task cases
+    SUMMARY_MODEL: str = "monadical/private/smart"
+    SUMMARY_LLM_URL: str | None = None
+    SUMMARY_LLM_API_KEY: str | None = None
+    SUMMARY_LLM_CONTEXT_SIZE_TOKENS: int = 16000
+
     # Diarization
     DIARIZATION_ENABLED: bool = True
     DIARIZATION_BACKEND: str = "modal"

server/reflector/stream_client.py

@@ -126,7 +126,7 @@ class StreamClient:
         answer = RTCSessionDescription(sdp=params["sdp"], type=params["type"])
         await pc.setRemoteDescription(answer)
 
-        self.reader = self.worker(f'{"worker"}', self.queue)
+        self.reader = self.worker(f"{'worker'}", self.queue)
 
     def get_reader(self):
         return self.reader

server/reflector/tools/exportdb.py

@@ -36,9 +36,13 @@ async def export_db(filename: str) -> None:
             if entry["event"] == "TRANSCRIPT":
                 yield tid, "event_transcript", idx, "text", entry["data"]["text"]
                 if entry["data"].get("translation") is not None:
-                    yield tid, "event_transcript", idx, "translation", entry[
+                    yield (
-                        "data"
+                        tid,
-                    ].get("translation", None)
+                        "event_transcript",
+                        idx,
+                        "translation",
+                        entry["data"].get("translation", None),
+                    )
 
     def export_transcripts(transcripts):
         for transcript in transcripts:

server/reflector/utils/retry.py

@@ -34,6 +34,7 @@ def retry(fn):
             ),
         )
         retry_ignore_exc_types = kwargs.pop("retry_ignore_exc_types", (Exception,))
+        retry_logger = kwargs.pop("logger", logger)
 
         result = None
         last_exception = None
@@ -58,17 +59,33 @@ def retry(fn):
                 if result:
                     return result
             except HTTPStatusError as e:
-                logger.exception(e)
+                retry_logger.exception(e)
                 status_code = e.response.status_code
-                logger.debug(f"HTTP status {status_code} - {e}")
+
+                # Log detailed error information including response body
+                try:
+                    response_text = e.response.text
+                    response_headers = dict(e.response.headers)
+                    retry_logger.error(
+                        f"HTTP {status_code} error for {e.request.method} {e.request.url}\n"
+                        f"Response headers: {response_headers}\n"
+                        f"Response body: {response_text}"
+                    )
+
+                except Exception as log_error:
+                    retry_logger.warning(
+                        f"Failed to log detailed error info: {log_error}"
+                    )
+                    retry_logger.debug(f"HTTP status {status_code} - {e}")
+
                 if status_code in retry_httpx_status_stop:
                     message = f"HTTP status {status_code} is in retry_httpx_status_stop"
                     raise RetryHTTPException(message) from e
             except retry_ignore_exc_types as e:
-                logger.exception(e)
+                retry_logger.exception(e)
                 last_exception = e
 
-            logger.debug(
+            retry_logger.debug(
                 f"Retrying {fn_name} - in {retry_backoff_interval:.1f}s "
                 f"({monotonic() - start:.1f}s / {retry_timeout:.1f}s)"
             )

server/reflector/utils/text_utils.py

@@ -253,9 +253,7 @@ def summarize(
         LOGGER.info("Breaking transcript into smaller chunks")
         chunks = chunk_text(transcript_text)
 
-        LOGGER.info(
+        LOGGER.info(f"Transcript broken into {len(chunks)} chunks of at most 500 words")
-            f"Transcript broken into {len(chunks)} " f"chunks of at most 500 words"
-        )
 
         LOGGER.info(f"Writing summary text to: {output_file}")
         with open(output_file, "w") as f:

server/tests/conftest.py

@@ -20,17 +20,23 @@ async def setup_database():
 
 @pytest.fixture
 def dummy_processors():
-    with patch(
+    with (
+        patch(
             "reflector.processors.transcript_topic_detector.TranscriptTopicDetectorProcessor.get_topic"
-    ) as mock_topic, patch(
+        ) as mock_topic,
+        patch(
             "reflector.processors.transcript_final_title.TranscriptFinalTitleProcessor.get_title"
-    ) as mock_title, patch(
+        ) as mock_title,
+        patch(
             "reflector.processors.transcript_final_summary.TranscriptFinalSummaryProcessor.get_long_summary"
-    ) as mock_long_summary, patch(
+        ) as mock_long_summary,
+        patch(
             "reflector.processors.transcript_final_summary.TranscriptFinalSummaryProcessor.get_short_summary"
-    ) as mock_short_summary, patch(
+        ) as mock_short_summary,
+        patch(
             "reflector.processors.transcript_translator.TranscriptTranslatorProcessor.get_translation"
-    ) as mock_translate:
+        ) as mock_translate,
+    ):
         mock_topic.return_value = {"title": "LLM TITLE", "summary": "LLM SUMMARY"}
         mock_title.return_value = {"title": "LLM TITLE"}
         mock_long_summary.return_value = "LLM LONG SUMMARY"

server/uv.lock

@@ -1,6 +1,10 @@
 version = 1
 revision = 2
 requires-python = ">=3.11, <3.13"
+resolution-markers = [
+    "python_full_version >= '3.12'",
+    "python_full_version < '3.12'",
+]
 
 [[package]]
 name = "aioboto3"
@@ -302,6 +306,35 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/28/76/3f1cf0568592f100fd68eb40ed8c491ce95ca3c1378cc2d4c1f6d1bd295d/av-14.4.0-cp312-cp312-win_amd64.whl", hash = "sha256:fbbeef1f421a3461086853d6464ad5526b56ffe8ccb0ab3fd0a1f121dfbf26ad", size = 27925944, upload-time = "2025-05-16T19:10:16.485Z" },
 ]
 
+[[package]]
+name = "banks"
+version = "2.2.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "deprecated" },
+    { name = "griffe" },
+    { name = "jinja2" },
+    { name = "platformdirs" },
+    { name = "pydantic" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/7d/f8/25ef24814f77f3fd7f0fd3bd1ef3749e38a9dbd23502fbb53034de49900c/banks-2.2.0.tar.gz", hash = "sha256:d1446280ce6e00301e3e952dd754fd8cee23ff277d29ed160994a84d0d7ffe62", size = 179052, upload-time = "2025-07-18T16:28:26.892Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b4/d6/f9168956276934162ec8d48232f9920f2985ee45aa7602e3c6b4bc203613/banks-2.2.0-py3-none-any.whl", hash = "sha256:963cd5c85a587b122abde4f4064078def35c50c688c1b9d36f43c92503854e7d", size = 29244, upload-time = "2025-07-18T16:28:27.835Z" },
+]
+
+[[package]]
+name = "beautifulsoup4"
+version = "4.13.4"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "soupsieve" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/d8/e4/0c4c39e18fd76d6a628d4dd8da40543d136ce2d1752bd6eeeab0791f4d6b/beautifulsoup4-4.13.4.tar.gz", hash = "sha256:dbb3c4e1ceae6aefebdaf2423247260cd062430a410e38c66f2baa50a8437195", size = 621067, upload-time = "2025-04-15T17:05:13.836Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/50/cd/30110dc0ffcf3b131156077b90e9f60ed75711223f306da4db08eff8403b/beautifulsoup4-4.13.4-py3-none-any.whl", hash = "sha256:9bbbb14bfde9d79f38b8cd5f8c7c85f4b8f2523190ebed90e950a8dea4cb1c4b", size = 187285, upload-time = "2025-04-15T17:05:12.221Z" },
+]
+
 [[package]]
 name = "billiard"
 version = "4.2.1"
@@ -650,6 +683,19 @@ asyncpg = [
     { name = "asyncpg" },
 ]
 
+[[package]]
+name = "dataclasses-json"
+version = "0.6.7"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "marshmallow" },
+    { name = "typing-inspect" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/64/a4/f71d9cf3a5ac257c993b5ca3f93df5f7fb395c725e7f1e6479d2514173c3/dataclasses_json-0.6.7.tar.gz", hash = "sha256:b6b3e528266ea45b9535223bc53ca645f5208833c29229e847b3f26a1cc55fc0", size = 32227, upload-time = "2024-06-09T16:20:19.103Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c3/be/d0d44e092656fe7a06b55e6103cbce807cdbdee17884a5367c68c9860853/dataclasses_json-0.6.7-py3-none-any.whl", hash = "sha256:0dbf33f26c8d5305befd61b39d2b3414e8a407bedc2834dea9b8d642666fb40a", size = 28686, upload-time = "2024-06-09T16:20:16.715Z" },
+]
+
 [[package]]
 name = "debugpy"
 version = "1.8.15"
@@ -667,6 +713,36 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/07/d5/98748d9860e767a1248b5e31ffa7ce8cb7006e97bf8abbf3d891d0a8ba4e/debugpy-1.8.15-py2.py3-none-any.whl", hash = "sha256:bce2e6c5ff4f2e00b98d45e7e01a49c7b489ff6df5f12d881c67d2f1ac635f3d", size = 5282697, upload-time = "2025-07-15T16:44:07.996Z" },
 ]
 
+[[package]]
+name = "defusedxml"
+version = "0.7.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/0f/d5/c66da9b79e5bdb124974bfe172b4daf3c984ebd9c2a06e2b8a4dc7331c72/defusedxml-0.7.1.tar.gz", hash = "sha256:1bb3032db185915b62d7c6209c5a8792be6a32ab2fedacc84e01b52c51aa3e69", size = 75520, upload-time = "2021-03-08T10:59:26.269Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/07/6c/aa3f2f849e01cb6a001cd8554a88d4c77c5c1a31c95bdf1cf9301e6d9ef4/defusedxml-0.7.1-py2.py3-none-any.whl", hash = "sha256:a352e7e428770286cc899e2542b6cdaedb2b4953ff269a210103ec58f6198a61", size = 25604, upload-time = "2021-03-08T10:59:24.45Z" },
+]
+
+[[package]]
+name = "deprecated"
+version = "1.2.18"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "wrapt" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/98/97/06afe62762c9a8a86af0cfb7bfdab22a43ad17138b07af5b1a58442690a2/deprecated-1.2.18.tar.gz", hash = "sha256:422b6f6d859da6f2ef57857761bfb392480502a64c3028ca9bbe86085d72115d", size = 2928744, upload-time = "2025-01-27T10:46:25.7Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/6e/c6/ac0b6c1e2d138f1002bcf799d330bd6d85084fece321e662a14223794041/Deprecated-1.2.18-py2.py3-none-any.whl", hash = "sha256:bd5011788200372a32418f888e326a09ff80d0214bd961147cfed01b5c018eec", size = 9998, upload-time = "2025-01-27T10:46:09.186Z" },
+]
+
+[[package]]
+name = "dirtyjson"
+version = "1.0.8"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/db/04/d24f6e645ad82ba0ef092fa17d9ef7a21953781663648a01c9371d9e8e98/dirtyjson-1.0.8.tar.gz", hash = "sha256:90ca4a18f3ff30ce849d100dcf4a003953c79d3a2348ef056f1d9c22231a25fd", size = 30782, upload-time = "2022-11-28T23:32:33.319Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/68/69/1bcf70f81de1b4a9f21b3a62ec0c83bdff991c88d6cc2267d02408457e88/dirtyjson-1.0.8-py3-none-any.whl", hash = "sha256:125e27248435a58acace26d5c2c4c11a1c0de0a9c5124c5a94ba78e517d74f53", size = 25197, upload-time = "2022-11-28T23:32:31.219Z" },
+]
+
 [[package]]
 name = "distro"
 version = "1.9.0"
@@ -826,6 +902,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/4d/36/2a115987e2d8c300a974597416d9de88f2444426de9571f4b59b2cca3acc/filelock-3.18.0-py3-none-any.whl", hash = "sha256:c401f4f8377c4464e6db25fff06205fd89bdd83b65eb0488ed1b160f780e21de", size = 16215, upload-time = "2025-03-14T07:11:39.145Z" },
 ]
 
+[[package]]
+name = "filetype"
+version = "1.2.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/bb/29/745f7d30d47fe0f251d3ad3dc2978a23141917661998763bebb6da007eb1/filetype-1.2.0.tar.gz", hash = "sha256:66b56cd6474bf41d8c54660347d37afcc3f7d1970648de365c102ef77548aadb", size = 998020, upload-time = "2022-11-02T17:34:04.141Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/18/79/1b8fa1bb3568781e84c9200f951c735f3f157429f44be0495da55894d620/filetype-1.2.0-py2.py3-none-any.whl", hash = "sha256:7ce71b6880181241cf7ac8697a2f1eb6a8bd9b429f7ad6d27b8db9ba5f1c2d25", size = 19970, upload-time = "2022-11-02T17:34:01.425Z" },
+]
+
 [[package]]
 name = "flatbuffers"
 version = "25.2.10"
@@ -933,6 +1018,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/1f/8f/8f9e56c5e82eb2c26e8cde787962e66494312dc8cb261c460e1f3a9c88bc/greenlet-3.2.3-cp312-cp312-win_amd64.whl", hash = "sha256:7454d37c740bb27bdeddfc3f358f26956a07d5220818ceb467a483197d84f849", size = 297817, upload-time = "2025-06-05T16:29:49.244Z" },
 ]
 
+[[package]]
+name = "griffe"
+version = "1.8.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "colorama" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/dd/72/10c5799440ce6f3001b7913988b50a99d7b156da71fe19be06178d5a2dd5/griffe-1.8.0.tar.gz", hash = "sha256:0b4658443858465c13b2de07ff5e15a1032bc889cfafad738a476b8b97bb28d7", size = 401098, upload-time = "2025-07-22T23:45:54.629Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/bf/c4/a839fcc28bebfa72925d9121c4d39398f77f95bcba0cf26c972a0cfb1de7/griffe-1.8.0-py3-none-any.whl", hash = "sha256:110faa744b2c5c84dd432f4fa9aa3b14805dd9519777dd55e8db214320593b02", size = 132487, upload-time = "2025-07-22T23:45:52.778Z" },
+]
+
 [[package]]
 name = "h11"
 version = "0.16.0"
@@ -1254,6 +1351,289 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/dc/1e/408fd10217eac0e43aea0604be22b4851a09e03d761d44d4ea12089dd70e/levenshtein-0.27.1-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:7987ef006a3cf56a4532bd4c90c2d3b7b4ca9ad3bf8ae1ee5713c4a3bdfda913", size = 98045, upload-time = "2025-03-02T19:44:44.527Z" },
 ]
 
+[[package]]
+name = "llama-cloud"
+version = "0.1.32"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "certifi" },
+    { name = "httpx" },
+    { name = "pydantic" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/1c/a4/1eed89c7820e273f74e80bc43ac7dd46953ecdc9e3dc5a1e30210beb400e/llama_cloud-0.1.32.tar.gz", hash = "sha256:cea98241127311ea91f191c3c006aa6558f01d16f9539ed93b24d716b888f10e", size = 99578, upload-time = "2025-07-08T14:23:41.44Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c5/54/08fc9ec16b483e57803309645c239ca72100d6e821849aa711971737ab17/llama_cloud-0.1.32-py3-none-any.whl", hash = "sha256:c42b2d5fb24acc8595bcc3626fb84c872909a16ab6d6879a1cb1101b21c238bd", size = 284617, upload-time = "2025-07-08T14:23:39.892Z" },
+]
+
+[[package]]
+name = "llama-cloud-services"
+version = "0.6.43"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "click" },
+    { name = "llama-cloud" },
+    { name = "llama-index-core" },
+    { name = "platformdirs" },
+    { name = "pydantic" },
+    { name = "python-dotenv" },
+    { name = "tenacity" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/56/30/82274bb0fc17430162a4f88f7ca0d25fd249767271d37af24b4a3e4cfcf7/llama_cloud_services-0.6.43.tar.gz", hash = "sha256:fa6be33bf54d467cace809efee8c2aeeb9de74ce66708513d37b40d738d3350f", size = 35169, upload-time = "2025-07-08T18:18:26.346Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/40/c3/1e82bd37f16e6d99988e9b53829303d3124504341862721f24c9b6f4f614/llama_cloud_services-0.6.43-py3-none-any.whl", hash = "sha256:2349195f501ba9151ea3ab384d20cae8b4dc4f335f60bd17607332626bdfa2e4", size = 40382, upload-time = "2025-07-08T18:18:25.517Z" },
+]
+
+[[package]]
+name = "llama-index"
+version = "0.12.52"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "llama-index-agent-openai" },
+    { name = "llama-index-cli" },
+    { name = "llama-index-core" },
+    { name = "llama-index-embeddings-openai" },
+    { name = "llama-index-indices-managed-llama-cloud" },
+    { name = "llama-index-llms-openai" },
+    { name = "llama-index-multi-modal-llms-openai" },
+    { name = "llama-index-program-openai" },
+    { name = "llama-index-question-gen-openai" },
+    { name = "llama-index-readers-file" },
+    { name = "llama-index-readers-llama-parse" },
+    { name = "nltk" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/a3/33/496f90bc77536c89b0b1266063977d99cf38e6a3458fd62a88c846f2c4f2/llama_index-0.12.52.tar.gz", hash = "sha256:3a81fa4fbf1a36e30502d2fb7da26d53bc1a1ab02db1db12e62f06bb014d5ad9", size = 8092, upload-time = "2025-07-23T18:11:59.26Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e0/ca/b1bb3edca7140b8d9e8957c95c6c59f2596071e89d5a10b0814976de9450/llama_index-0.12.52-py3-none-any.whl", hash = "sha256:21e05e5a02b3601e18358eeed8748384eac8d35d384fdcbe16d03f0ffb09ea61", size = 7090, upload-time = "2025-07-23T18:11:57.548Z" },
+]
+
+[[package]]
+name = "llama-index-agent-openai"
+version = "0.4.12"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "llama-index-core" },
+    { name = "llama-index-llms-openai" },
+    { name = "openai" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/0e/94/69decc46d11e954c6a8c64999cc237af5932d116eeb7a06515856641a6d4/llama_index_agent_openai-0.4.12.tar.gz", hash = "sha256:d2fe53feb69cfe45752edb7328bf0d25f6a9071b3c056787e661b93e5b748a28", size = 12443, upload-time = "2025-06-29T00:52:03.606Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/89/f5/857ea1c136f422234e298e868af74094a71bf98687be40a365ad6551a660/llama_index_agent_openai-0.4.12-py3-none-any.whl", hash = "sha256:6dbb6276b2e5330032a726b28d5eef5140825f36d72d472b231f08ad3af99665", size = 14704, upload-time = "2025-06-29T00:52:02.528Z" },
+]
+
+[[package]]
+name = "llama-index-cli"
+version = "0.4.4"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "llama-index-core" },
+    { name = "llama-index-embeddings-openai" },
+    { name = "llama-index-llms-openai" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/d6/44/6acba0b8425d15682def89a4dbba68c782fd74ce6e74a4fa48beb08632f6/llama_index_cli-0.4.4.tar.gz", hash = "sha256:c3af0cf1e2a7e5ef44d0bae5aa8e8872b54c5dd6b731afbae9f13ffeb4997be0", size = 25308, upload-time = "2025-07-07T05:17:40.556Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/cc/21/89989b7fa8ce4b9bc6f0f7326ae7f959a887c1281f007a718eafd6ef614f/llama_index_cli-0.4.4-py3-none-any.whl", hash = "sha256:1070593cf79407054735ab7a23c5a65a26fc18d264661e42ef38fc549b4b7658", size = 28598, upload-time = "2025-07-07T05:17:39.522Z" },
+]
+
+[[package]]
+name = "llama-index-core"
+version = "0.12.52.post1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "aiohttp" },
+    { name = "aiosqlite" },
+    { name = "banks" },
+    { name = "dataclasses-json" },
+    { name = "deprecated" },
+    { name = "dirtyjson" },
+    { name = "filetype" },
+    { name = "fsspec" },
+    { name = "httpx" },
+    { name = "llama-index-workflows" },
+    { name = "nest-asyncio" },
+    { name = "networkx" },
+    { name = "nltk" },
+    { name = "numpy" },
+    { name = "pillow" },
+    { name = "platformdirs" },
+    { name = "pydantic" },
+    { name = "pyyaml" },
+    { name = "requests" },
+    { name = "setuptools" },
+    { name = "sqlalchemy", extra = ["asyncio"] },
+    { name = "tenacity" },
+    { name = "tiktoken" },
+    { name = "tqdm" },
+    { name = "typing-extensions" },
+    { name = "typing-inspect" },
+    { name = "wrapt" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/9e/3b/3937a1756a02e549a776272371dd6ec3a4541833b2dbb8ef58e61167f9c9/llama_index_core-0.12.52.post1.tar.gz", hash = "sha256:ac6f447271e5ac4c12e1901373ec4b5ac7814ea33bd1ad3c3c8e9ac9771834ab", size = 7279221, upload-time = "2025-07-23T17:32:33.961Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/51/48/8f6ea9f2a2f5a080166f0a45a252609df32cc1ad626836aaad2424e2c7ec/llama_index_core-0.12.52.post1-py3-none-any.whl", hash = "sha256:3e28d65d238bad8ec5ce372659ae0a3878851c6ba9c9447d6ddb4de138694b1f", size = 7649855, upload-time = "2025-07-23T17:32:28.271Z" },
+]
+
+[[package]]
+name = "llama-index-embeddings-openai"
+version = "0.3.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "llama-index-core" },
+    { name = "openai" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/a1/02/a2604ef3a167131fdd701888f45f16c8efa6d523d02efe8c4e640238f4ea/llama_index_embeddings_openai-0.3.1.tar.gz", hash = "sha256:1368aad3ce24cbaed23d5ad251343cef1eb7b4a06d6563d6606d59cb347fef20", size = 5492, upload-time = "2024-11-27T16:04:17.017Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/bb/45/ca55b91c4ac1b6251d4099fa44121a6c012129822906cadcc27b8cfb33a4/llama_index_embeddings_openai-0.3.1-py3-none-any.whl", hash = "sha256:f15a3d13da9b6b21b8bd51d337197879a453d1605e625a1c6d45e741756c0290", size = 6177, upload-time = "2024-11-27T16:04:15.981Z" },
+]
+
+[[package]]
+name = "llama-index-indices-managed-llama-cloud"
+version = "0.7.10"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "llama-cloud" },
+    { name = "llama-index-core" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/e2/5a/7663c04257f2763a9b8089653b7e5d2d5aa241dcd8a21f2d0344f69c8ca1/llama_index_indices_managed_llama_cloud-0.7.10.tar.gz", hash = "sha256:53267907e23d8fbcbb97c7a96177a41446de18550ca6030276092e73b45ca880", size = 14769, upload-time = "2025-07-08T18:13:19.923Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e6/ea/a0aef9ccb09bd6438fd99d7f9c547bc2eac06abc32852b9e70c807585559/llama_index_indices_managed_llama_cloud-0.7.10-py3-none-any.whl", hash = "sha256:f7edcfb8f694cab547cd9324be7835dc97470ce05150d0b8888fa3bf9d2f84a8", size = 16474, upload-time = "2025-07-08T18:13:18.703Z" },
+]
+
+[[package]]
+name = "llama-index-instrumentation"
+version = "0.3.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "deprecated" },
+    { name = "pydantic" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/0f/57/76123657bf6f175382ceddee9af66507c37d603475cbf0968df8dfea9de2/llama_index_instrumentation-0.3.0.tar.gz", hash = "sha256:77741c1d9861ead080e6f98350625971488d1e046bede91cec9e0ce2f63ea34a", size = 42651, upload-time = "2025-07-17T17:41:20.468Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/cc/d4/9377a53ea2f9bdd33f5ccff78ac863705657f422bb686cad4896b058ce46/llama_index_instrumentation-0.3.0-py3-none-any.whl", hash = "sha256:edfcd71aedc453dbdb4a7073a1e39ddef6ae2c13601a4cba6f2dfea38f48eeff", size = 15011, upload-time = "2025-07-17T17:41:19.723Z" },
+]
+
+[[package]]
+name = "llama-index-llms-openai"
+version = "0.4.7"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "llama-index-core" },
+    { name = "openai" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/d9/39/a7ce514fb500951e9edb713ed918a9ffe49f1a76fccfc531a4ec5c7fe15a/llama_index_llms_openai-0.4.7.tar.gz", hash = "sha256:564af8ab39fb3f3adfeae73a59c0dca46c099ab844a28e725eee0c551d4869f8", size = 24251, upload-time = "2025-06-16T03:38:47.175Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/61/e9/391926dad180ced6bb37a62edddb8483fbecde411239bd5e726841bb77b4/llama_index_llms_openai-0.4.7-py3-none-any.whl", hash = "sha256:3b8d9d3c1bcadc2cff09724de70f074f43eafd5b7048a91247c9a41b7cd6216d", size = 25365, upload-time = "2025-06-16T03:38:45.72Z" },
+]
+
+[[package]]
+name = "llama-index-llms-openai-like"
+version = "0.4.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "llama-index-core" },
+    { name = "llama-index-llms-openai" },
+    { name = "transformers" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/df/df/807ac6bb9470295769f950562f5f7252cb491166693ee877ff77d9022fbc/llama_index_llms_openai_like-0.4.0.tar.gz", hash = "sha256:15ae1c16b01ba0bfa822d53900f03e35c19ffe47b528958234bf1942a91f587c", size = 4898, upload-time = "2025-05-30T17:47:11.689Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b8/41/e080871437ec507377126165318f2da6713a4d6dc2767f2444a8bd818791/llama_index_llms_openai_like-0.4.0-py3-none-any.whl", hash = "sha256:52a3cb5ce78049fde5c9926898b90e02bc04e3d23adbc991842e9ff574df9ea1", size = 4593, upload-time = "2025-05-30T17:47:10.456Z" },
+]
+
+[[package]]
+name = "llama-index-multi-modal-llms-openai"
+version = "0.5.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "llama-index-core" },
+    { name = "llama-index-llms-openai" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/6e/5d/8a7ff14f5ac6844722152ba35ee4e1298b4665a3cf70eaeae6d6df938e37/llama_index_multi_modal_llms_openai-0.5.3.tar.gz", hash = "sha256:b755a8b47d8d2f34b5a3d249af81d9bfb69d3d2cf9ab539d3a42f7bfa3e2391a", size = 3760, upload-time = "2025-07-07T16:22:44.922Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/18/e5/bc4ec1f373cd2195e625af483eddc5b05a55f6c6db020746f6bb2c0fadde/llama_index_multi_modal_llms_openai-0.5.3-py3-none-any.whl", hash = "sha256:be6237df8f9caaa257f9beda5317287bbd2ec19473d777a30a34e41a7c5bddf8", size = 3434, upload-time = "2025-07-07T16:22:43.898Z" },
+]
+
+[[package]]
+name = "llama-index-program-openai"
+version = "0.3.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "llama-index-agent-openai" },
+    { name = "llama-index-core" },
+    { name = "llama-index-llms-openai" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/83/81/9caa34e80adce1adb715ae083a54ad45c8fc0d9aef0f2d80d61c1b805ab6/llama_index_program_openai-0.3.2.tar.gz", hash = "sha256:04c959a2e616489894bd2eeebb99500d6f1c17d588c3da0ddc75ebd3eb7451ee", size = 6301, upload-time = "2025-05-30T23:00:27.872Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/05/80/d6ac8afafdd38115d61214891c36876e64f429809abff873660fe30862fe/llama_index_program_openai-0.3.2-py3-none-any.whl", hash = "sha256:451829ae53e074e7b47dcc60a9dd155fcf9d1dcbc1754074bdadd6aab4ceb9aa", size = 6129, upload-time = "2025-05-30T23:00:26.64Z" },
+]
+
+[[package]]
+name = "llama-index-question-gen-openai"
+version = "0.3.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "llama-index-core" },
+    { name = "llama-index-llms-openai" },
+    { name = "llama-index-program-openai" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/52/6e/19c5051c81ef5fca597d13c6d41b863535521565b1414ab5ab0e5e8c1297/llama_index_question_gen_openai-0.3.1.tar.gz", hash = "sha256:5e9311b433cc2581ff8a531fa19fb3aa21815baff75aaacdef11760ac9522aa9", size = 4107, upload-time = "2025-05-30T23:00:31.016Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/15/2a/652593d0bd24f901776db0d1778a42363ea2656530da18215f413ce4f981/llama_index_question_gen_openai-0.3.1-py3-none-any.whl", hash = "sha256:1ce266f6c8373fc8d884ff83a44dfbacecde2301785db7144872db51b8b99429", size = 3733, upload-time = "2025-05-30T23:00:29.965Z" },
+]
+
+[[package]]
+name = "llama-index-readers-file"
+version = "0.4.11"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "beautifulsoup4" },
+    { name = "defusedxml" },
+    { name = "llama-index-core" },
+    { name = "pandas" },
+    { name = "pypdf" },
+    { name = "striprtf" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/14/13/529412fcd1789607e060168ccac347bc7f012ed98c1e34614d4fb443fe39/llama_index_readers_file-0.4.11.tar.gz", hash = "sha256:1b21cb66d78dd5f60e8716607d9a47ccd81bb39106d459665be1ca7799e9597b", size = 22765, upload-time = "2025-07-07T21:03:57.312Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/54/b3/4977330c49538b0252ca014c2ef10352ecc8f14c489ca6d95858bcb0cceb/llama_index_readers_file-0.4.11-py3-none-any.whl", hash = "sha256:e71192d8d6d0bf95131762da15fa205cf6e0cc248c90c76ee04d0fbfe160d464", size = 41046, upload-time = "2025-07-07T21:03:55.877Z" },
+]
+
+[[package]]
+name = "llama-index-readers-llama-parse"
+version = "0.4.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "llama-index-core" },
+    { name = "llama-parse" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/35/30/4611821286f82ba7b5842295607baa876262db86f88b87d83595eed172bf/llama_index_readers_llama_parse-0.4.0.tar.gz", hash = "sha256:e99ec56f4f8546d7fda1a7c1ae26162fb9acb7ebcac343b5abdb4234b4644e0f", size = 2472, upload-time = "2024-11-18T00:00:08.893Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/68/4f/e30d4257fe9e4224f5612b77fe99aaceddae411b2e74ca30534491de3e6f/llama_index_readers_llama_parse-0.4.0-py3-none-any.whl", hash = "sha256:574e48386f28d2c86c3f961ca4a4906910312f3400dd0c53014465bfbc6b32bf", size = 2472, upload-time = "2024-11-18T00:00:07.293Z" },
+]
+
+[[package]]
+name = "llama-index-workflows"
+version = "1.2.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "llama-index-instrumentation" },
+    { name = "pydantic" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/26/9d/9dc7adc10d9976582bf50b074883986cb36b46f2fe45cf60550767300a29/llama_index_workflows-1.2.0.tar.gz", hash = "sha256:f6b19f01a340a1afb1d2fd2285c9dce346e304a3aae519e6103059f5afb2609f", size = 1019113, upload-time = "2025-07-23T18:32:47.86Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/36/c1/5190f102a042d36a6a495de27510c2d6e3aca98f892895bfacdcf9109c1d/llama_index_workflows-1.2.0-py3-none-any.whl", hash = "sha256:5722a7ce137e00361025768789e7e77720cd66f855791050183a3c540b6e5b8c", size = 37463, upload-time = "2025-07-23T18:32:46.294Z" },
+]
+
+[[package]]
+name = "llama-parse"
+version = "0.6.43"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "llama-cloud-services" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/79/62/22e3f73a2b33b9db1523573611281010c8258bf1d17408913e8e46bdfe58/llama_parse-0.6.43.tar.gz", hash = "sha256:d88e91c97e37f77b2619111ef43c02b7da61125f821cf77f918996eb48200d78", size = 3536, upload-time = "2025-07-08T18:20:58.786Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/fa/24/8497595be04a8a0209536e9ce70d4132f8f8e001986f4c700414b3777758/llama_parse-0.6.43-py3-none-any.whl", hash = "sha256:fe435309638c4fdec4fec31f97c5031b743c92268962d03b99bd76704f566c32", size = 4944, upload-time = "2025-07-08T18:20:57.089Z" },
+]
+
 [[package]]
 name = "loguru"
 version = "0.7.3"
@@ -1319,6 +1699,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c1/80/a61f99dc3a936413c3ee4e1eecac96c0da5ed07ad56fd975f1a9da5bc630/MarkupSafe-3.0.2-cp312-cp312-win_amd64.whl", hash = "sha256:8e06879fc22a25ca47312fbe7c8264eb0b662f6db27cb2d3bbbc74b1df4b9b87", size = 15601, upload-time = "2024-10-18T15:21:23.499Z" },
 ]
 
+[[package]]
+name = "marshmallow"
+version = "3.26.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "packaging" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/ab/5e/5e53d26b42ab75491cda89b871dab9e97c840bf12c63ec58a1919710cd06/marshmallow-3.26.1.tar.gz", hash = "sha256:e6d8affb6cb61d39d26402096dc0aee12d5a26d490a121f118d2e81dc0719dc6", size = 221825, upload-time = "2025-02-03T15:32:25.093Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/34/75/51952c7b2d3873b44a0028b1bd26a25078c18f92f256608e8d1dc61b39fd/marshmallow-3.26.1-py3-none-any.whl", hash = "sha256:3350409f20a70a7e4e11a27661187b77cdcaeb20abca41c1454fe33636bea09c", size = 50878, upload-time = "2025-02-03T15:32:22.295Z" },
+]
+
 [[package]]
 name = "mdurl"
 version = "0.1.2"
@@ -1391,6 +1783,24 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/79/7b/2c79738432f5c924bef5071f933bcc9efd0473bac3b4aa584a6f7c1c8df8/mypy_extensions-1.1.0-py3-none-any.whl", hash = "sha256:1be4cccdb0f2482337c4743e60421de3a356cd97508abadd57d47403e94f5505", size = 4963, upload-time = "2025-04-22T14:54:22.983Z" },
 ]
 
+[[package]]
+name = "nest-asyncio"
+version = "1.6.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/83/f8/51569ac65d696c8ecbee95938f89d4abf00f47d58d48f6fbabfe8f0baefe/nest_asyncio-1.6.0.tar.gz", hash = "sha256:6f172d5449aca15afd6c646851f4e31e02c598d553a667e38cafa997cfec55fe", size = 7418, upload-time = "2024-01-21T14:25:19.227Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a0/c4/c2971a3ba4c6103a3d10c4b0f24f461ddc027f0f09763220cf35ca1401b3/nest_asyncio-1.6.0-py3-none-any.whl", hash = "sha256:87af6efd6b5e897c81050477ef65c62e2b2f35d51703cae01aff2905b1852e1c", size = 5195, upload-time = "2024-01-21T14:25:17.223Z" },
+]
+
+[[package]]
+name = "networkx"
+version = "3.5"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/6c/4f/ccdb8ad3a38e583f214547fd2f7ff1fc160c43a75af88e6aec213404b96a/networkx-3.5.tar.gz", hash = "sha256:d4c6f9cf81f52d69230866796b82afbccdec3db7ae4fbd1b65ea750feed50037", size = 2471065, upload-time = "2025-05-29T11:35:07.804Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/eb/8d/776adee7bbf76365fdd7f2552710282c79a4ead5d2a46408c9043a2b70ba/networkx-3.5-py3-none-any.whl", hash = "sha256:0030d386a9a06dee3565298b4a734b68589749a544acbb6c412dc9e2489ec6ec", size = 2034406, upload-time = "2025-05-29T11:35:04.961Z" },
+]
+
 [[package]]
 name = "nltk"
 version = "3.9.1"
@@ -1493,6 +1903,34 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/20/12/38679034af332785aac8774540895e234f4d07f7545804097de4b666afd8/packaging-25.0-py3-none-any.whl", hash = "sha256:29572ef2b1f17581046b3a2227d5c611fb25ec70ca1ba8554b24b0e69331a484", size = 66469, upload-time = "2025-04-19T11:48:57.875Z" },
 ]
 
+[[package]]
+name = "pandas"
+version = "2.2.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "numpy" },
+    { name = "python-dateutil" },
+    { name = "pytz" },
+    { name = "tzdata" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/9c/d6/9f8431bacc2e19dca897724cd097b1bb224a6ad5433784a44b587c7c13af/pandas-2.2.3.tar.gz", hash = "sha256:4f18ba62b61d7e192368b84517265a99b4d7ee8912f8708660fb4a366cc82667", size = 4399213, upload-time = "2024-09-20T13:10:04.827Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a8/44/d9502bf0ed197ba9bf1103c9867d5904ddcaf869e52329787fc54ed70cc8/pandas-2.2.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:66108071e1b935240e74525006034333f98bcdb87ea116de573a6a0dccb6c039", size = 12602222, upload-time = "2024-09-20T13:08:56.254Z" },
+    { url = "https://files.pythonhosted.org/packages/52/11/9eac327a38834f162b8250aab32a6781339c69afe7574368fffe46387edf/pandas-2.2.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7c2875855b0ff77b2a64a0365e24455d9990730d6431b9e0ee18ad8acee13dbd", size = 11321274, upload-time = "2024-09-20T13:08:58.645Z" },
+    { url = "https://files.pythonhosted.org/packages/45/fb/c4beeb084718598ba19aa9f5abbc8aed8b42f90930da861fcb1acdb54c3a/pandas-2.2.3-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cd8d0c3be0515c12fed0bdbae072551c8b54b7192c7b1fda0ba56059a0179698", size = 15579836, upload-time = "2024-09-20T19:01:57.571Z" },
+    { url = "https://files.pythonhosted.org/packages/cd/5f/4dba1d39bb9c38d574a9a22548c540177f78ea47b32f99c0ff2ec499fac5/pandas-2.2.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c124333816c3a9b03fbeef3a9f230ba9a737e9e5bb4060aa2107a86cc0a497fc", size = 13058505, upload-time = "2024-09-20T13:09:01.501Z" },
+    { url = "https://files.pythonhosted.org/packages/b9/57/708135b90391995361636634df1f1130d03ba456e95bcf576fada459115a/pandas-2.2.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:63cc132e40a2e084cf01adf0775b15ac515ba905d7dcca47e9a251819c575ef3", size = 16744420, upload-time = "2024-09-20T19:02:00.678Z" },
+    { url = "https://files.pythonhosted.org/packages/86/4a/03ed6b7ee323cf30404265c284cee9c65c56a212e0a08d9ee06984ba2240/pandas-2.2.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:29401dbfa9ad77319367d36940cd8a0b3a11aba16063e39632d98b0e931ddf32", size = 14440457, upload-time = "2024-09-20T13:09:04.105Z" },
+    { url = "https://files.pythonhosted.org/packages/ed/8c/87ddf1fcb55d11f9f847e3c69bb1c6f8e46e2f40ab1a2d2abadb2401b007/pandas-2.2.3-cp311-cp311-win_amd64.whl", hash = "sha256:3fc6873a41186404dad67245896a6e440baacc92f5b716ccd1bc9ed2995ab2c5", size = 11617166, upload-time = "2024-09-20T13:09:06.917Z" },
+    { url = "https://files.pythonhosted.org/packages/17/a3/fb2734118db0af37ea7433f57f722c0a56687e14b14690edff0cdb4b7e58/pandas-2.2.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b1d432e8d08679a40e2a6d8b2f9770a5c21793a6f9f47fdd52c5ce1948a5a8a9", size = 12529893, upload-time = "2024-09-20T13:09:09.655Z" },
+    { url = "https://files.pythonhosted.org/packages/e1/0c/ad295fd74bfac85358fd579e271cded3ac969de81f62dd0142c426b9da91/pandas-2.2.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a5a1595fe639f5988ba6a8e5bc9649af3baf26df3998a0abe56c02609392e0a4", size = 11363475, upload-time = "2024-09-20T13:09:14.718Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/2a/4bba3f03f7d07207481fed47f5b35f556c7441acddc368ec43d6643c5777/pandas-2.2.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:5de54125a92bb4d1c051c0659e6fcb75256bf799a732a87184e5ea503965bce3", size = 15188645, upload-time = "2024-09-20T19:02:03.88Z" },
+    { url = "https://files.pythonhosted.org/packages/38/f8/d8fddee9ed0d0c0f4a2132c1dfcf0e3e53265055da8df952a53e7eaf178c/pandas-2.2.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fffb8ae78d8af97f849404f21411c95062db1496aeb3e56f146f0355c9989319", size = 12739445, upload-time = "2024-09-20T13:09:17.621Z" },
+    { url = "https://files.pythonhosted.org/packages/20/e8/45a05d9c39d2cea61ab175dbe6a2de1d05b679e8de2011da4ee190d7e748/pandas-2.2.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6dfcb5ee8d4d50c06a51c2fffa6cff6272098ad6540aed1a76d15fb9318194d8", size = 16359235, upload-time = "2024-09-20T19:02:07.094Z" },
+    { url = "https://files.pythonhosted.org/packages/1d/99/617d07a6a5e429ff90c90da64d428516605a1ec7d7bea494235e1c3882de/pandas-2.2.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:062309c1b9ea12a50e8ce661145c6aab431b1e99530d3cd60640e255778bd43a", size = 14056756, upload-time = "2024-09-20T13:09:20.474Z" },
+    { url = "https://files.pythonhosted.org/packages/29/d4/1244ab8edf173a10fd601f7e13b9566c1b525c4f365d6bee918e68381889/pandas-2.2.3-cp312-cp312-win_amd64.whl", hash = "sha256:59ef3764d0fe818125a5097d2ae867ca3fa64df032331b7e0917cf5d7bf66b13", size = 11504248, upload-time = "2024-09-20T13:09:23.137Z" },
+]
+
 [[package]]
 name = "pathspec"
 version = "0.12.1"
@@ -1502,6 +1940,43 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/cc/20/ff623b09d963f88bfde16306a54e12ee5ea43e9b597108672ff3a408aad6/pathspec-0.12.1-py3-none-any.whl", hash = "sha256:a0d503e138a4c123b27490a4f7beda6a01c6f288df0e4a8b79c7eb0dc7b4cc08", size = 31191, upload-time = "2023-12-10T22:30:43.14Z" },
 ]
 
+[[package]]
+name = "pillow"
+version = "11.3.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f3/0d/d0d6dea55cd152ce3d6767bb38a8fc10e33796ba4ba210cbab9354b6d238/pillow-11.3.0.tar.gz", hash = "sha256:3828ee7586cd0b2091b6209e5ad53e20d0649bbe87164a459d0676e035e8f523", size = 47113069, upload-time = "2025-07-01T09:16:30.666Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/db/26/77f8ed17ca4ffd60e1dcd220a6ec6d71210ba398cfa33a13a1cd614c5613/pillow-11.3.0-cp311-cp311-macosx_10_10_x86_64.whl", hash = "sha256:1cd110edf822773368b396281a2293aeb91c90a2db00d78ea43e7e861631b722", size = 5316531, upload-time = "2025-07-01T09:13:59.203Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/39/ee475903197ce709322a17a866892efb560f57900d9af2e55f86db51b0a5/pillow-11.3.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:9c412fddd1b77a75aa904615ebaa6001f169b26fd467b4be93aded278266b288", size = 4686560, upload-time = "2025-07-01T09:14:01.101Z" },
+    { url = "https://files.pythonhosted.org/packages/d5/90/442068a160fd179938ba55ec8c97050a612426fae5ec0a764e345839f76d/pillow-11.3.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:7d1aa4de119a0ecac0a34a9c8bde33f34022e2e8f99104e47a3ca392fd60e37d", size = 5870978, upload-time = "2025-07-03T13:09:55.638Z" },
+    { url = "https://files.pythonhosted.org/packages/13/92/dcdd147ab02daf405387f0218dcf792dc6dd5b14d2573d40b4caeef01059/pillow-11.3.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:91da1d88226663594e3f6b4b8c3c8d85bd504117d043740a8e0ec449087cc494", size = 7641168, upload-time = "2025-07-03T13:10:00.37Z" },
+    { url = "https://files.pythonhosted.org/packages/6e/db/839d6ba7fd38b51af641aa904e2960e7a5644d60ec754c046b7d2aee00e5/pillow-11.3.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:643f189248837533073c405ec2f0bb250ba54598cf80e8c1e043381a60632f58", size = 5973053, upload-time = "2025-07-01T09:14:04.491Z" },
+    { url = "https://files.pythonhosted.org/packages/f2/2f/d7675ecae6c43e9f12aa8d58b6012683b20b6edfbdac7abcb4e6af7a3784/pillow-11.3.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:106064daa23a745510dabce1d84f29137a37224831d88eb4ce94bb187b1d7e5f", size = 6640273, upload-time = "2025-07-01T09:14:06.235Z" },
+    { url = "https://files.pythonhosted.org/packages/45/ad/931694675ede172e15b2ff03c8144a0ddaea1d87adb72bb07655eaffb654/pillow-11.3.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:cd8ff254faf15591e724dc7c4ddb6bf4793efcbe13802a4ae3e863cd300b493e", size = 6082043, upload-time = "2025-07-01T09:14:07.978Z" },
+    { url = "https://files.pythonhosted.org/packages/3a/04/ba8f2b11fc80d2dd462d7abec16351b45ec99cbbaea4387648a44190351a/pillow-11.3.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:932c754c2d51ad2b2271fd01c3d121daaa35e27efae2a616f77bf164bc0b3e94", size = 6715516, upload-time = "2025-07-01T09:14:10.233Z" },
+    { url = "https://files.pythonhosted.org/packages/48/59/8cd06d7f3944cc7d892e8533c56b0acb68399f640786313275faec1e3b6f/pillow-11.3.0-cp311-cp311-win32.whl", hash = "sha256:b4b8f3efc8d530a1544e5962bd6b403d5f7fe8b9e08227c6b255f98ad82b4ba0", size = 6274768, upload-time = "2025-07-01T09:14:11.921Z" },
+    { url = "https://files.pythonhosted.org/packages/f1/cc/29c0f5d64ab8eae20f3232da8f8571660aa0ab4b8f1331da5c2f5f9a938e/pillow-11.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:1a992e86b0dd7aeb1f053cd506508c0999d710a8f07b4c791c63843fc6a807ac", size = 6986055, upload-time = "2025-07-01T09:14:13.623Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/df/90bd886fabd544c25addd63e5ca6932c86f2b701d5da6c7839387a076b4a/pillow-11.3.0-cp311-cp311-win_arm64.whl", hash = "sha256:30807c931ff7c095620fe04448e2c2fc673fcbb1ffe2a7da3fb39613489b1ddd", size = 2423079, upload-time = "2025-07-01T09:14:15.268Z" },
+    { url = "https://files.pythonhosted.org/packages/40/fe/1bc9b3ee13f68487a99ac9529968035cca2f0a51ec36892060edcc51d06a/pillow-11.3.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:fdae223722da47b024b867c1ea0be64e0df702c5e0a60e27daad39bf960dd1e4", size = 5278800, upload-time = "2025-07-01T09:14:17.648Z" },
+    { url = "https://files.pythonhosted.org/packages/2c/32/7e2ac19b5713657384cec55f89065fb306b06af008cfd87e572035b27119/pillow-11.3.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:921bd305b10e82b4d1f5e802b6850677f965d8394203d182f078873851dada69", size = 4686296, upload-time = "2025-07-01T09:14:19.828Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/1e/b9e12bbe6e4c2220effebc09ea0923a07a6da1e1f1bfbc8d7d29a01ce32b/pillow-11.3.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:eb76541cba2f958032d79d143b98a3a6b3ea87f0959bbe256c0b5e416599fd5d", size = 5871726, upload-time = "2025-07-03T13:10:04.448Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/33/e9200d2bd7ba00dc3ddb78df1198a6e80d7669cce6c2bdbeb2530a74ec58/pillow-11.3.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:67172f2944ebba3d4a7b54f2e95c786a3a50c21b88456329314caaa28cda70f6", size = 7644652, upload-time = "2025-07-03T13:10:10.391Z" },
+    { url = "https://files.pythonhosted.org/packages/41/f1/6f2427a26fc683e00d985bc391bdd76d8dd4e92fac33d841127eb8fb2313/pillow-11.3.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:97f07ed9f56a3b9b5f49d3661dc9607484e85c67e27f3e8be2c7d28ca032fec7", size = 5977787, upload-time = "2025-07-01T09:14:21.63Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/c9/06dd4a38974e24f932ff5f98ea3c546ce3f8c995d3f0985f8e5ba48bba19/pillow-11.3.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:676b2815362456b5b3216b4fd5bd89d362100dc6f4945154ff172e206a22c024", size = 6645236, upload-time = "2025-07-01T09:14:23.321Z" },
+    { url = "https://files.pythonhosted.org/packages/40/e7/848f69fb79843b3d91241bad658e9c14f39a32f71a301bcd1d139416d1be/pillow-11.3.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:3e184b2f26ff146363dd07bde8b711833d7b0202e27d13540bfe2e35a323a809", size = 6086950, upload-time = "2025-07-01T09:14:25.237Z" },
+    { url = "https://files.pythonhosted.org/packages/0b/1a/7cff92e695a2a29ac1958c2a0fe4c0b2393b60aac13b04a4fe2735cad52d/pillow-11.3.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:6be31e3fc9a621e071bc17bb7de63b85cbe0bfae91bb0363c893cbe67247780d", size = 6723358, upload-time = "2025-07-01T09:14:27.053Z" },
+    { url = "https://files.pythonhosted.org/packages/26/7d/73699ad77895f69edff76b0f332acc3d497f22f5d75e5360f78cbcaff248/pillow-11.3.0-cp312-cp312-win32.whl", hash = "sha256:7b161756381f0918e05e7cb8a371fff367e807770f8fe92ecb20d905d0e1c149", size = 6275079, upload-time = "2025-07-01T09:14:30.104Z" },
+    { url = "https://files.pythonhosted.org/packages/8c/ce/e7dfc873bdd9828f3b6e5c2bbb74e47a98ec23cc5c74fc4e54462f0d9204/pillow-11.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:a6444696fce635783440b7f7a9fc24b3ad10a9ea3f0ab66c5905be1c19ccf17d", size = 6986324, upload-time = "2025-07-01T09:14:31.899Z" },
+    { url = "https://files.pythonhosted.org/packages/16/8f/b13447d1bf0b1f7467ce7d86f6e6edf66c0ad7cf44cf5c87a37f9bed9936/pillow-11.3.0-cp312-cp312-win_arm64.whl", hash = "sha256:2aceea54f957dd4448264f9bf40875da0415c83eb85f55069d89c0ed436e3542", size = 2423067, upload-time = "2025-07-01T09:14:33.709Z" },
+    { url = "https://files.pythonhosted.org/packages/9e/e3/6fa84033758276fb31da12e5fb66ad747ae83b93c67af17f8c6ff4cc8f34/pillow-11.3.0-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:7c8ec7a017ad1bd562f93dbd8505763e688d388cde6e4a010ae1486916e713e6", size = 5270566, upload-time = "2025-07-01T09:16:19.801Z" },
+    { url = "https://files.pythonhosted.org/packages/5b/ee/e8d2e1ab4892970b561e1ba96cbd59c0d28cf66737fc44abb2aec3795a4e/pillow-11.3.0-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:9ab6ae226de48019caa8074894544af5b53a117ccb9d3b3dcb2871464c829438", size = 4654618, upload-time = "2025-07-01T09:16:21.818Z" },
+    { url = "https://files.pythonhosted.org/packages/f2/6d/17f80f4e1f0761f02160fc433abd4109fa1548dcfdca46cfdadaf9efa565/pillow-11.3.0-pp311-pypy311_pp73-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:fe27fb049cdcca11f11a7bfda64043c37b30e6b91f10cb5bab275806c32f6ab3", size = 4874248, upload-time = "2025-07-03T13:11:20.738Z" },
+    { url = "https://files.pythonhosted.org/packages/de/5f/c22340acd61cef960130585bbe2120e2fd8434c214802f07e8c03596b17e/pillow-11.3.0-pp311-pypy311_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:465b9e8844e3c3519a983d58b80be3f668e2a7a5db97f2784e7079fbc9f9822c", size = 6583963, upload-time = "2025-07-03T13:11:26.283Z" },
+    { url = "https://files.pythonhosted.org/packages/31/5e/03966aedfbfcbb4d5f8aa042452d3361f325b963ebbadddac05b122e47dd/pillow-11.3.0-pp311-pypy311_pp73-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5418b53c0d59b3824d05e029669efa023bbef0f3e92e75ec8428f3799487f361", size = 4957170, upload-time = "2025-07-01T09:16:23.762Z" },
+    { url = "https://files.pythonhosted.org/packages/cc/2d/e082982aacc927fc2cab48e1e731bdb1643a1406acace8bed0900a61464e/pillow-11.3.0-pp311-pypy311_pp73-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:504b6f59505f08ae014f724b6207ff6222662aab5cc9542577fb084ed0676ac7", size = 5581505, upload-time = "2025-07-01T09:16:25.593Z" },
+    { url = "https://files.pythonhosted.org/packages/34/e7/ae39f538fd6844e982063c3a5e4598b8ced43b9633baa3a85ef33af8c05c/pillow-11.3.0-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:c84d689db21a1c397d001aa08241044aa2069e7587b398c8cc63020390b1c1b8", size = 6984598, upload-time = "2025-07-01T09:16:27.732Z" },
+]
+
 [[package]]
 name = "platformdirs"
 version = "4.3.8"
@@ -1847,6 +2322,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/80/28/2659c02301b9500751f8d42f9a6632e1508aa5120de5e43042b8b30f8d5d/pyopenssl-25.1.0-py3-none-any.whl", hash = "sha256:2b11f239acc47ac2e5aca04fd7fa829800aeee22a2eb30d744572a157bd8a1ab", size = 56771, upload-time = "2025-05-17T16:28:29.197Z" },
 ]
 
+[[package]]
+name = "pypdf"
+version = "5.8.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/28/5a/139b1a3ec3789cc77a7cb9d5d3bc9e97e742e6d03708baeb7719f8ad0827/pypdf-5.8.0.tar.gz", hash = "sha256:f8332f80606913e6f0ce65488a870833c9d99ccdb988c17bb6c166f7c8e140cb", size = 5029494, upload-time = "2025-07-13T12:51:35.125Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/8b/94/05d0310bfa92c26aa50a9d2dea2c6448a1febfdfcf98fb340a99d48a3078/pypdf-5.8.0-py3-none-any.whl", hash = "sha256:bfe861285cd2f79cceecefde2d46901e4ee992a9f4b42c56548c4a6e9236a0d1", size = 309718, upload-time = "2025-07-13T12:51:33.159Z" },
+]
+
 [[package]]
 name = "pyreadline3"
 version = "3.5.4"
@@ -2006,6 +2490,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/45/58/38b5afbc1a800eeea951b9285d3912613f2603bdf897a4ab0f4bd7f405fc/python_multipart-0.0.20-py3-none-any.whl", hash = "sha256:8a62d3a8335e06589fe01f2a3e178cdcc632f3fbe0d492ad9ee0ec35aab1f104", size = 24546, upload-time = "2024-12-16T19:45:44.423Z" },
 ]
 
+[[package]]
+name = "pytz"
+version = "2025.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f8/bf/abbd3cdfb8fbc7fb3d4d38d320f2441b1e7cbe29be4f23797b4a2b5d8aac/pytz-2025.2.tar.gz", hash = "sha256:360b9e3dbb49a209c21ad61809c7fb453643e048b38924c765813546746e81c3", size = 320884, upload-time = "2025-03-25T02:25:00.538Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/81/c4/34e93fe5f5429d7570ec1fa436f1986fb1f00c3e0f43a589fe2bbcd22c3f/pytz-2025.2-py2.py3-none-any.whl", hash = "sha256:5ddf76296dd8c44c26eb8f4b6f35488f3ccbf6fbbd7adee0b7262d43f0ec2f00", size = 509225, upload-time = "2025-03-25T02:24:58.468Z" },
+]
+
 [[package]]
 name = "pywin32"
 version = "311"
@@ -2133,6 +2626,8 @@ dependencies = [
     { name = "faster-whisper" },
     { name = "httpx" },
     { name = "jsonschema" },
+    { name = "llama-index" },
+    { name = "llama-index-llms-openai-like" },
     { name = "loguru" },
     { name = "nltk" },
     { name = "openai" },
@@ -2194,6 +2689,8 @@ requires-dist = [
     { name = "faster-whisper", specifier = ">=0.10.0" },
     { name = "httpx", specifier = ">=0.24.1" },
     { name = "jsonschema", specifier = ">=4.23.0" },
+    { name = "llama-index", specifier = ">=0.12.52" },
+    { name = "llama-index-llms-openai-like", specifier = ">=0.4.0" },
     { name = "loguru", specifier = ">=0.7.0" },
     { name = "nltk", specifier = ">=3.8.1" },
     { name = "openai", specifier = ">=1.59.7" },
@@ -2544,6 +3041,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/32/46/9cb0e58b2deb7f82b84065f37f3bffeb12413f947f9388e4cac22c4621ce/sortedcontainers-2.4.0-py2.py3-none-any.whl", hash = "sha256:a163dcaede0f1c021485e957a39245190e74249897e2ae4b2aa38595db237ee0", size = 29575, upload-time = "2021-05-16T22:03:41.177Z" },
 ]
 
+[[package]]
+name = "soupsieve"
+version = "2.7"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/3f/f4/4a80cd6ef364b2e8b65b15816a843c0980f7a5a2b4dc701fc574952aa19f/soupsieve-2.7.tar.gz", hash = "sha256:ad282f9b6926286d2ead4750552c8a6142bc4c783fd66b0293547c8fe6ae126a", size = 103418, upload-time = "2025-04-20T18:50:08.518Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e7/9c/0e6afc12c269578be5c0c1c9f4b49a8d32770a080260c333ac04cc1c832d/soupsieve-2.7-py3-none-any.whl", hash = "sha256:6e60cc5c1ffaf1cebcc12e8188320b72071e922c2e897f737cadce79ad5d30c4", size = 36677, upload-time = "2025-04-20T18:50:07.196Z" },
+]
+
 [[package]]
 name = "sqlalchemy"
 version = "1.4.54"
@@ -2565,6 +3071,11 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/01/c3/c690d037be57efd3a69cde16a2ef1bd2a905dafe869434d33836de0983d0/SQLAlchemy-1.4.54-cp312-cp312-win_amd64.whl", hash = "sha256:f941aaf15f47f316123e1933f9ea91a6efda73a161a6ab6046d1cde37be62c88", size = 1593827, upload-time = "2024-09-05T17:52:07.454Z" },
 ]
 
+[package.optional-dependencies]
+asyncio = [
+    { name = "greenlet" },
+]
+
 [[package]]
 name = "stamina"
 version = "25.1.0"
@@ -2590,6 +3101,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/82/95/38ef0cd7fa11eaba6a99b3c4f5ac948d8bc6ff199aabd327a29cc000840c/starlette-0.47.1-py3-none-any.whl", hash = "sha256:5e11c9f5c7c3f24959edbf2dffdc01bba860228acf657129467d8a7468591527", size = 72747, upload-time = "2025-06-21T04:03:15.705Z" },
 ]
 
+[[package]]
+name = "striprtf"
+version = "0.0.26"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/25/20/3d419008265346452d09e5dadfd5d045b64b40d8fc31af40588e6c76997a/striprtf-0.0.26.tar.gz", hash = "sha256:fdb2bba7ac440072d1c41eab50d8d74ae88f60a8b6575c6e2c7805dc462093aa", size = 6258, upload-time = "2023-07-20T14:30:36.29Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a3/cf/0fea4f4ba3fc2772ac2419278aa9f6964124d4302117d61bc055758e000c/striprtf-0.0.26-py3-none-any.whl", hash = "sha256:8c8f9d32083cdc2e8bfb149455aa1cc5a4e0a035893bedc75db8b73becb3a1bb", size = 6914, upload-time = "2023-07-20T14:30:35.338Z" },
+]
+
 [[package]]
 name = "structlog"
 version = "25.4.0"
@@ -2620,6 +3140,30 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e5/30/643397144bfbfec6f6ef821f36f33e57d35946c44a2352d3c9f0ae847619/tenacity-9.1.2-py3-none-any.whl", hash = "sha256:f77bf36710d8b73a50b2dd155c97b870017ad21afe6ab300326b0371b3b05138", size = 28248, upload-time = "2025-04-02T08:25:07.678Z" },
 ]
 
+[[package]]
+name = "tiktoken"
+version = "0.9.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "regex" },
+    { name = "requests" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/ea/cf/756fedf6981e82897f2d570dd25fa597eb3f4459068ae0572d7e888cfd6f/tiktoken-0.9.0.tar.gz", hash = "sha256:d02a5ca6a938e0490e1ff957bc48c8b078c88cb83977be1625b1fd8aac792c5d", size = 35991, upload-time = "2025-02-14T06:03:01.003Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/4d/ae/4613a59a2a48e761c5161237fc850eb470b4bb93696db89da51b79a871f1/tiktoken-0.9.0-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:f32cc56168eac4851109e9b5d327637f15fd662aa30dd79f964b7c39fbadd26e", size = 1065987, upload-time = "2025-02-14T06:02:14.174Z" },
+    { url = "https://files.pythonhosted.org/packages/3f/86/55d9d1f5b5a7e1164d0f1538a85529b5fcba2b105f92db3622e5d7de6522/tiktoken-0.9.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:45556bc41241e5294063508caf901bf92ba52d8ef9222023f83d2483a3055348", size = 1009155, upload-time = "2025-02-14T06:02:15.384Z" },
+    { url = "https://files.pythonhosted.org/packages/03/58/01fb6240df083b7c1916d1dcb024e2b761213c95d576e9f780dfb5625a76/tiktoken-0.9.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:03935988a91d6d3216e2ec7c645afbb3d870b37bcb67ada1943ec48678e7ee33", size = 1142898, upload-time = "2025-02-14T06:02:16.666Z" },
+    { url = "https://files.pythonhosted.org/packages/b1/73/41591c525680cd460a6becf56c9b17468d3711b1df242c53d2c7b2183d16/tiktoken-0.9.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8b3d80aad8d2c6b9238fc1a5524542087c52b860b10cbf952429ffb714bc1136", size = 1197535, upload-time = "2025-02-14T06:02:18.595Z" },
+    { url = "https://files.pythonhosted.org/packages/7d/7c/1069f25521c8f01a1a182f362e5c8e0337907fae91b368b7da9c3e39b810/tiktoken-0.9.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:b2a21133be05dc116b1d0372af051cd2c6aa1d2188250c9b553f9fa49301b336", size = 1259548, upload-time = "2025-02-14T06:02:20.729Z" },
+    { url = "https://files.pythonhosted.org/packages/6f/07/c67ad1724b8e14e2b4c8cca04b15da158733ac60136879131db05dda7c30/tiktoken-0.9.0-cp311-cp311-win_amd64.whl", hash = "sha256:11a20e67fdf58b0e2dea7b8654a288e481bb4fc0289d3ad21291f8d0849915fb", size = 893895, upload-time = "2025-02-14T06:02:22.67Z" },
+    { url = "https://files.pythonhosted.org/packages/cf/e5/21ff33ecfa2101c1bb0f9b6df750553bd873b7fb532ce2cb276ff40b197f/tiktoken-0.9.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:e88f121c1c22b726649ce67c089b90ddda8b9662545a8aeb03cfef15967ddd03", size = 1065073, upload-time = "2025-02-14T06:02:24.768Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/03/a95e7b4863ee9ceec1c55983e4cc9558bcfd8f4f80e19c4f8a99642f697d/tiktoken-0.9.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a6600660f2f72369acb13a57fb3e212434ed38b045fd8cc6cdd74947b4b5d210", size = 1008075, upload-time = "2025-02-14T06:02:26.92Z" },
+    { url = "https://files.pythonhosted.org/packages/40/10/1305bb02a561595088235a513ec73e50b32e74364fef4de519da69bc8010/tiktoken-0.9.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:95e811743b5dfa74f4b227927ed86cbc57cad4df859cb3b643be797914e41794", size = 1140754, upload-time = "2025-02-14T06:02:28.124Z" },
+    { url = "https://files.pythonhosted.org/packages/1b/40/da42522018ca496432ffd02793c3a72a739ac04c3794a4914570c9bb2925/tiktoken-0.9.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:99376e1370d59bcf6935c933cb9ba64adc29033b7e73f5f7569f3aad86552b22", size = 1196678, upload-time = "2025-02-14T06:02:29.845Z" },
+    { url = "https://files.pythonhosted.org/packages/5c/41/1e59dddaae270ba20187ceb8aa52c75b24ffc09f547233991d5fd822838b/tiktoken-0.9.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:badb947c32739fb6ddde173e14885fb3de4d32ab9d8c591cbd013c22b4c31dd2", size = 1259283, upload-time = "2025-02-14T06:02:33.838Z" },
+    { url = "https://files.pythonhosted.org/packages/5b/64/b16003419a1d7728d0d8c0d56a4c24325e7b10a21a9dd1fc0f7115c02f0a/tiktoken-0.9.0-cp312-cp312-win_amd64.whl", hash = "sha256:5a62d7a25225bafed786a524c1b9f0910a1128f4232615bf3f8257a73aaa3b16", size = 894897, upload-time = "2025-02-14T06:02:36.265Z" },
+]
+
 [[package]]
 name = "tokenizers"
 version = "0.21.2"
@@ -2731,6 +3275,19 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/b5/00/d631e67a838026495268c2f6884f3711a15a9a2a96cd244fdaea53b823fb/typing_extensions-4.14.1-py3-none-any.whl", hash = "sha256:d1e1e3b58374dc93031d6eda2420a48ea44a36c2b4766a4fdeb3710755731d76", size = 43906, upload-time = "2025-07-04T13:28:32.743Z" },
 ]
 
+[[package]]
+name = "typing-inspect"
+version = "0.9.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "mypy-extensions" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/dc/74/1789779d91f1961fa9438e9a8710cdae6bd138c80d7303996933d117264a/typing_inspect-0.9.0.tar.gz", hash = "sha256:b23fc42ff6f6ef6954e4852c1fb512cdd18dbea03134f91f856a95ccc9461f78", size = 13825, upload-time = "2023-05-24T20:25:47.612Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/65/f3/107a22063bf27bdccf2024833d3445f4eea42b2e598abfbd46f6a63b6cb0/typing_inspect-0.9.0-py3-none-any.whl", hash = "sha256:9ee6fc59062311ef8547596ab6b955e1b8aa46242d854bfc78f4f6b0eff35f9f", size = 8827, upload-time = "2023-05-24T20:25:45.287Z" },
+]
+
 [[package]]
 name = "typing-inspection"
 version = "0.4.1"