Add Support For Local LLMs

[Yiannis128]

The following PR adds support for local LLMs that are running through an Ollama server. As the TextGenerationInference custom AIs were no longer supported, the config object ai_custom has been repurposed for specifying Ollama models to connect to. The reason Ollama was chosen is due to the wide array of available models that they support. As Ollama supports ChatModels directly (rather than text completion models), the ESBMC-AI code has been adapted to use Chat style code only from Lang Chain for simplicity. Additionally, the parameter server_type has been added, which in the future could provide additional types of server support. Currently, it only supports ollama.

This PR closes #138

Example config:

"ai_custom": {
    "llama3.1:70b": {
      "server_type": "ollama",
      "url": "localhost:11434",
      "max_tokens": 128000
    },
    "falcon2:11b": {
      "server_type": "ollama",
      "url": "localhost:11434",
      "max_tokens": 8192
    },
    "mixtral:8x22b": {
      "server_type": "ollama",
      "url": "localhost:11434",
      "max_tokens": 64000
    }
  }