From 499733bde6a63b616c42fa7b89fc9712e4583d41 Mon Sep 17 00:00:00 2001
From: Dillon Laird <dillonalaird@gmail.com>
Date: Thu, 29 Aug 2024 08:32:32 -0700
Subject: [PATCH] fixed type errors

---
 vision_agent/agent/vision_agent.py       | 10 +++++++---
 vision_agent/agent/vision_agent_coder.py |  2 +-
 vision_agent/lmm/lmm.py                  |  6 ++++--
 3 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/vision_agent/agent/vision_agent.py b/vision_agent/agent/vision_agent.py
index 04cafd5e..58bea5ca 100644
--- a/vision_agent/agent/vision_agent.py
+++ b/vision_agent/agent/vision_agent.py
@@ -198,7 +198,7 @@ def chat_with_code(
             for chat_i in int_chat:
                 if "media" in chat_i:
                     for media in chat_i["media"]:
-                        media = code_interpreter.upload_file(media)
+                        media = code_interpreter.upload_file(cast(str, media))
                         chat_i["content"] += f" Media name {media}"  # type: ignore
                         # Save dummy value for now since we just need to know the path
                         # name in the key 'media'. Later on we can add artifact support
@@ -264,8 +264,12 @@ def chat_with_code(
 
                     if self.verbosity >= 1:
                         _LOGGER.info(obs)
-                    int_chat.append({"role": "observation", "content": obs, "execution": result})
-                    orig_chat.append({"role": "observation", "content": obs, "execution": result})
+                    int_chat.append(
+                        {"role": "observation", "content": obs, "execution": result}
+                    )
+                    orig_chat.append(
+                        {"role": "observation", "content": obs, "execution": result}
+                    )
 
                 iterations += 1
                 last_response = response
diff --git a/vision_agent/agent/vision_agent_coder.py b/vision_agent/agent/vision_agent_coder.py
index 3f731b24..2a2dba97 100644
--- a/vision_agent/agent/vision_agent_coder.py
+++ b/vision_agent/agent/vision_agent_coder.py
@@ -718,7 +718,7 @@ def chat_with_workflow(
             for chat_i in chat:
                 if "media" in chat_i:
                     for media in chat_i["media"]:
-                        media = code_interpreter.upload_file(media)
+                        media = code_interpreter.upload_file(cast(str, media))
                         chat_i["content"] += f" Media name {media}"  # type: ignore
                         media_list.append(str(media))
 
diff --git a/vision_agent/lmm/lmm.py b/vision_agent/lmm/lmm.py
index e78a0593..485bf7f3 100644
--- a/vision_agent/lmm/lmm.py
+++ b/vision_agent/lmm/lmm.py
@@ -132,7 +132,7 @@ def chat(
             fixed_c["content"] = [{"type": "text", "text": c["content"]}]  # type: ignore
             if "media" in c:
                 for media in c["media"]:
-                    encoded_media = encode_media(media)
+                    encoded_media = encode_media(cast(str, media))
 
                     fixed_c["content"].append(  # type: ignore
                         {
@@ -379,7 +379,9 @@ def chat(
         fixed_chat = []
         for message in chat:
             if "media" in message:
-                message["images"] = [encode_media(m) for m in message["media"]]
+                message["images"] = [
+                    encode_media(cast(str, m)) for m in message["media"]
+                ]
                 del message["media"]
             fixed_chat.append(message)
         url = f"{self.url}/chat"