feat: implement RAG system with ChromaDB for knowledge base retrieval#5
Open
ketanjain7981 wants to merge 47 commits into
Open
feat: implement RAG system with ChromaDB for knowledge base retrieval#5ketanjain7981 wants to merge 47 commits into
ketanjain7981 wants to merge 47 commits into
Conversation
* sip integration-twillio * changes * refactor changes * refactor changes * changes * changes * Minor bug fix * handle transport events * ruff fix --------- Co-authored-by: nischay41 <nischay.kumar@think41.com> Co-authored-by: Apoorv <apoorva.bhatnagar@think41.com>
* sip integration-twillio * changes * refactor changes * refactor changes * changes * changes * Minor bug fix * handle transport events * ruff fix * added the mit license (#16) * added the mit license * added the contributing.md file * added ruff checks * make slight change * Create main.yml * remove the ruff.yaml * added the main.yml * Feature/fix multisession issue (#19) * fix requirements and sdk path * user now able to create multiple room in daily * fix the docker * added the ruff --------- Co-authored-by: nischay41 <nischay.kumar@think41.com> Co-authored-by: Apoorv <apoorva.bhatnagar@think41.com> Co-authored-by: ketanjain7981 <ketan.jain@think41.com> Co-authored-by: Aniket <aniket.lnu@think41.com>
* Version update and fix initial errors * Added tracing logic to agent.py * Update requirements.txt --------- Co-authored-by: banshu41 <shubham.bansal@think41.com>
Monitor/latency
* added the session id in daily * added the resume_data in contexts * pass the session id in the events * revert the custom_plugin changes * fix custom plugin * successfully resume the session * added the sesion and metadata in the connectionhandler too * fix main * fix main * integrate the session_resume and session_id * fix the requirments.txt * added the sip_call and remove the transcript from metadat
* added the session id in daily * added the resume_data in contexts * pass the session id in the events * revert the custom_plugin changes * fix custom plugin * successfully resume the session * added the sesion and metadata in the connectionhandler too * fix main * fix main * integrate the session_resume and session_id * fix the requirments.txt * added the sip_call and remove the transcript from metadat * sip assistant * fixed
* added the session id in daily * added the resume_data in contexts * pass the session id in the events * revert the custom_plugin changes * fix custom plugin * successfully resume the session * added the sesion and metadata in the connectionhandler too * fix main * fix main * integrate the session_resume and session_id * fix the requirments.txt * added the sip_call and remove the transcript from metadat * sip assistant * fixed * remove the $ sign and change the place of metdata_without_trancript * fixed
* added the session id in daily * added the resume_data in contexts * pass the session id in the events * revert the custom_plugin changes * fix custom plugin * successfully resume the session * added the sesion and metadata in the connectionhandler too * fix main * fix main * integrate the session_resume and session_id * fix the requirments.txt * added the sip_call and remove the transcript from metadat * sip assistant * fixed * remove the $ sign and change the place of metdata_without_trancript * fixed * fixed * fixed duplicay
* feat: add modular API key handling and lazy dependency imports for providers * refactor: centralize provider imports and API key handling across LLM, STT, and TTS services * added changelog * remove reduandent changelog * feat: add configurable VAD params and ElevenLabs TTS, groq llm provider support * reset tools * optimize imports * fixed installation
* feat: add modular API key handling and lazy dependency imports for providers * refactor: centralize provider imports and API key handling across LLM, STT, and TTS services * added changelog * remove reduandent changelog * feat: add configurable VAD params and ElevenLabs TTS, groq llm provider support * reset tools * optimize imports * fixed installation * added missing imports for sip
- Current only Cerebras is used as the reasoning model. - Custom class inheriting the OpenAILLMService class overides process_context method.
* Leap Scholar POC * Kept only session_id addition change
* Guardrail fix: - Get assistant's last message. Include it in context when running guardrails. * Guardrail fix: - Check the system prompt so that function call requests don't get treated as guardrail triggers
* Guardrail fix: - Get assistant's last message. Include it in context when running guardrails. * Guardrail fix: - Check the system prompt so that function call requests don't get treated as guardrail triggers * Guardrail Fix: - Fix function calling by the LLM --------- Co-authored-by: banshu41 <shubham.bansal@think41.com>
Feature/websocket fixes new
chore: add semantic-release and commitizen configuration Co-authored-by: ketanjain7981 <ketan.jain@think41.com>
* Issue #55: - Replaced custom user_bot_latency observer with pipecat's observer. * New changes * New changes * New changes * New changes * Merge (#68) * updated hard coded uuid * applied ruff fix * refactor: clean up imports and remove unused variables across multiple files * style: format imports by breaking into individual lines --------- --------- Co-authored-by: nischay41 <nischay.kumar@think41.com> Co-authored-by: MayurGowda-Think41 <mayur.gowda@think41.com> Co-authored-by: Apoorv <apoorva.bhatnagar@think41.com>
chore: add semantic-release and commitizen configuration
* Dev (#66) * Issue #55: - Replaced custom user_bot_latency observer with pipecat's observer. * New changes * New changes * New changes * New changes * Merge (#68) * updated hard coded uuid * applied ruff fix * refactor: clean up imports and remove unused variables across multiple files * style: format imports by breaking into individual lines --------- Co-authored-by: nischay41 <nischay.kumar@think41.com> --------- Co-authored-by: MayurGowda-Think41 <mayur.gowda@think41.com> Co-authored-by: Apoorv <apoorva.bhatnagar@think41.com> Co-authored-by: nischay41 <nischay.kumar@think41.com> * Dev updated (#76) * Issue #55: - Replaced custom user_bot_latency observer with pipecat's observer. * New changes * New changes * New changes * New changes * Merge (#68) * updated hard coded uuid * applied ruff fix * refactor: clean up imports and remove unused variables across multiple files * style: format imports by breaking into individual lines --------- Co-authored-by: nischay41 <nischay.kumar@think41.com> * build: chore: add semantic-release and commitizen configuration (#72) chore: add semantic-release and commitizen configuration Co-authored-by: ketanjain7981 <ketan.jain@think41.com> --------- Co-authored-by: MayurGowda-Think41 <mayur.gowda@think41.com> Co-authored-by: Apoorv <apoorva.bhatnagar@think41.com> Co-authored-by: nischay41 <nischay.kumar@think41.com> Co-authored-by: Aniket <aniket.lnu@think41.com> * feat: implement OpenTelemetry token usage tracking with shared context * refactor: improve token usage tracking with dedicated TokenUsageExporter class and metrics context * refactor: remove debug logging for transport type conversion * refactor: remove debug logging from TokenUsageExporter span processing * refactor: remove unused imports from agent.py and clean up dependencies * refactor: remove unused imports from metrics and observer modules * style: improve code formatting and line wrapping in CallSummaryMetricsObserver --------- Co-authored-by: nischay41 <nischay.kumar@think41.com> Co-authored-by: MayurGowda-Think41 <mayur.gowda@think41.com> Co-authored-by: Apoorv <apoorva.bhatnagar@think41.com> Co-authored-by: Aniket <aniket.lnu@think41.com>
* Add a method to generate agent * Add new api to generate agent file * Add new api to generate agent file * Change openai model * Change openai model * Change openai model * Change openai model * Change openai model * Change openai model * Change openai model * Change openai model * Change openai model * Fix guardrails varaible name * Fix prompts * Fix logging * Add conversation store util * Fixing template * Fixing template * ruff fixed * updated format * docs: add comprehensive docstrings and type hints to agent file generator * style: replace single quotes with double quotes in string formatting --------- Co-authored-by: Apoorv <apoorva.bhatnagar@think41.com> Co-authored-by: ketanjain7981 <ketan.jain@think41.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.