Merge pull request #90 from bolna-ai/local_setup_updates_v1

updating with latest local setup
bolna-ai · Mar 12, 2024 · c8a0d14 · c8a0d14
2 parents 3198e6e + d2acfde
commit c8a0d14
Show file tree

Hide file tree

Showing 12 changed files with 21 additions and 398 deletions.
diff --git a/README.md b/README.md
@@ -33,92 +33,53 @@ https://github.com/bolna-ai/bolna/assets/1313096/2237f64f-1c5b-4723-b7e7-d11466e
 ## Components
 Bolna helps you create AI Voice Agents which can be instructed to do tasks beginning with:
 
-1. Initiating a phone call using telephony providers like `Twilio`, etc.
+1. Initiating a phone call using telephony providers like `Twilio`, `Exotel`, etc.
 2. Transcribing the conversations using `Deepgram`, etc.
-3. Using LLMs like `OpenAI`, etc to handle conversations
-4. Synthesizing LLM responses back to telephony using `AWS Polly`, `XTTS`, etc.
+3. Using LLMs like `OpenAI`, `Llama`, `Cohere`, `Mistral`,  etc to handle conversations
+4. Synthesizing LLM responses back to telephony using `AWS Polly`, `XTTS`, `ElevenLabs`, `Deepgram` etc.
 5. Instructing the Agent to perform tasks like sending emails, text messages, booking calendar after the conversation has ended
 
 Refer to the [docs](https://docs.bolna.dev) for a deepdive into all supported providers.
 
 
-## Agents
-This repo contains the following types of agents in the `agents/agent_types` directory which can be used to create conversational applications:
-
-1. `contextual_conversational_agent`: LLM-based free flow agent
-2. `graph_based_conversational_agent`: LLM-based agent with classification
-3. `extraction_agent`: Currently WIP. [Feel free to contribute and open a PR](https://github.com/bolna-ai/bolna/compare)
-
-
 ## Local setup
-A basic local setup uses Twilio for telephony. We have dockerized the setup in `local_setup/`. One will need to populate an environment `.env` file from `.env.sample`.
+A basic local setup uses `Twilio` for telephony. We have dockerized the setup in `local_setup/`. One will need to populate an environment `.env` file from `.env.sample`.
 
 The setup consists of four containers:
 
 1. Twilio web server: for initiating the calls one will need to set up a [Twilio account]([https://www.twilio.com/docs/usage/tutorials/how-to-use-your-free-trial-account](https://www.twilio.com/docs/messaging/guides/how-to-use-your-free-trial-account))
 2. Bolna server: for creating and handling agents 
 3. `ngrok`: for tunneling. One will need to add the `authtoken` to `ngrok-config.yml`
-4. `redis`: for persisting agents & users contextual data
+4. `redis`: for persisting agents & prompt data
 
-Running `docker-compose up --build` will use the `.env` as the environment file and the `agent_data` to start all containers.
+Running `docker-compose up --build` will use the `.env` as the environment file.
 
 Once the docker containers are up, you can now start to create your agents and instruct them to initiate calls.
 
 
-## Agent Examples
-The repo contains examples as a reference for creating for application agents in the `agent_data` directory:
-
-1. `airbnb_job`: A `streaming` `conversation` agent where the agent screens potential candidates for a job at AirBnB
-2. `sorting_hat`: A `preprocessed` `conversation` agent which acts as a Sorting Hat for Hogwarts
-3. `yc_screening`: A `streaming` `conversation` agent which acts as a Y Combinator partner asking questions around the idea/startup
-4. `indian_elections_vernacular`: A `streaming` `conversation` agent which asks people for their outlook towards Indian elections in Hindi language
-5. `sample_agent`: A boilerplate sample agent to start building your own agent!
-
-
-## Anatomy of an agent
-All agents are read from the `agent_data` directory. We have provided some samples for getting started. There's a dashboard coming up [still in WIP] which will easily facilitate towards creating agents.
-
-General structure of the agents:
-
-    your-awesome-agent-name
-    ├── conversation_details.json         # Compiled prompt
-    └── users.json                        # List of users that the call would be made to
-
-| Agent type    | `streaming` agent                                                              | `preprocessed` agent                                                                                                                                                                                     |
-|---------------|--------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| Introduction  | A streaming agent will work like a free-flow conversation following the prompt | Apart from following the prompt, a preprocessed agent will have all responses <br/>from the agent preprocessed in the form of audio which will be streamed <br/>as per the classification of human's response |
-| Prompt        | Required (defined in `conversation_details.json`)                              | Required (defined in `conversation_details.json`)                                                                                                                                                        |
-| Preprocessing | Not required                                                                   | Required (using `scripts/preprocessed.py`)                                                                                                                                                               |
 
+## Creating your agent and invoking calls
+Once you have the above docker setup and running, you can create agents and initiate calls.
+1. Refer to the official [`Agent` API](https://docs.bolna.dev/api-reference/agent/create) to create an agent
+2. Initiate a call via API similar to [`Call` API](https://docs.bolna.dev/api-reference/calls/make) to receive a call
 
-> [!note]
-> Currently, the `users.json` has the following user attributes which gets substituted in the prompt to make it customized for the call. More to be added soon! 
-> - first_name
-> - last_name
-> - honorific
-> 
-> 
-> 
-> For instance, in the case of a preprocessed agent, the initial intro could be customized to have the user's name.
-> 
-> Even the prompt could be customized to fill in user contextual details from users.json. For example, [{first_name} defined in prompt](https://github.com/bolna-ai/bolna/blob/master/agent_data/airbnb_job/conversation_details.json#L3) and [prompt intro](https://github.com/bolna-ai/bolna/blob/master/agent_data/sorting_hat/conversation_details.json#L10)
 
+## Using your own providers
+You can populate the `.env` file to use your own keys for providers.
+<details>
 
-## Setting up your agent
-1. Create a directory under `agent_data` directory with the name for your agent
-2. Create your prompt and save in a file called `conversation_details.json` using the example provided
-3. Optional: In case if you are creating a `preprocessed` agent, generate the audio data used by using the script `scripts/preprocess.py`
+<summary>LLM Providers</summary>
 
+#### You can add a header
 
-## Creating your agent and invoking calls
-1. At this point, the docker containers should be up and running
-2. Your agent prompt should be defined in the `agent_data/` directory with `conversation_details.json` with the user list in `users.json`
-3. Create your agent using the [Bolna Create Agent API](https://docs.bolna.dev/api-reference/endpoint/create). An agent will get created with an `agent_id`
-4. Instruct the agent to initiate call to users via `scripts/initiate_agent_call.py <agent_name> <agent_id>`
+```ruby
+   puts "Hello World"
+```
+</details>
 
 
 ## Open-source v/s Paid
-Though the repository is completely open source, you can connect with us if interested in managed offerings or more customized solutions.
+Though the repository is completely open source, you can connect with us if interested in managed hosted offerings or more customized solutions.
 
 <a href="https://calendly.com/bolna/30min"><img alt="Schedule a meeting" src="https://cdn.cookielaw.org/logos/122ecfc3-4694-42f1-863f-2db42d1b1e68/0bcbbcf4-9b83-4684-ba59-bc913c0d5905/c21bea90-f4f1-43d1-8118-8938bbb27a9d/logo.png" /></a>
 

diff --git a/agent_data/airbnb_job/conversation_details.json b/agent_data/airbnb_job/conversation_details.json
diff --git a/agent_data/airbnb_job/users.json b/agent_data/airbnb_job/users.json
diff --git a/agent_data/indian_elections_vernacular/conversation_details.json b/agent_data/indian_elections_vernacular/conversation_details.json
diff --git a/agent_data/indian_elections_vernacular/users.json b/agent_data/indian_elections_vernacular/users.json
diff --git a/agent_data/sample_agent/conversaton_details.json.sample b/agent_data/sample_agent/conversaton_details.json.sample
diff --git a/agent_data/sample_agent/users.json.sample b/agent_data/sample_agent/users.json.sample
diff --git a/agent_data/sorting_hat/conversation_details.json b/agent_data/sorting_hat/conversation_details.json
diff --git a/agent_data/sorting_hat/users.json b/agent_data/sorting_hat/users.json
diff --git a/local_setup/telephony_server/twilio_api_server.py b/local_setup/telephony_server/twilio_api_server.py
@@ -47,7 +47,7 @@ async def close_redis_connection():
     await redis_client.aclose()
 
 
-@app.post('/make_call')
+@app.post('/call')
 async def make_call(request: Request):
     try:
         call_details = await request.json()

diff --git a/scripts/initiate_agent_call.py b/scripts/initiate_agent_call.py